System

Abstract

A system is provided.SOLUTION: A system includes means for uploading materials provided by a corporate customer, means for analyzing the uploaded materials using a natural language processing technology to extract information related to carbon neutrality, means for collating the extracted information with a database to select an optimal carbon-neutral-related proposal, means for calculating an introduction cost of the selected proposal, an expected CO2 reduction amount, and an investment effect, means for generating a proposal document including a calculation result, and means for providing the generated proposal document to a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Companies need to invest significant resources to achieve carbon neutrality, but it is difficult to select the optimal measures and accurately understand their cost-effectiveness. In particular, there is a lack of systems that can quickly and accurately extract relevant information from provided materials and propose effective measures. For this reason, there is a strong demand for systems that can accurately analyze energy consumption and CO2 emissions, make optimal proposals, and clearly present their cost-effectiveness. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for uploading documents provided by corporate clients, a means for analyzing the uploaded documents using natural language processing technology to extract information related to carbon neutrality, a means for comparing the extracted information with a database to select the optimal carbon neutrality-related proposal, a means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, a means for generating a proposal including the calculation results, and a means for providing the generated proposal to a user. This system enables companies to efficiently formulate and implement carbon neutrality plans.

[0006] "Corporate Customer" refers to a customer with legal personality such as a company or organization.

[0007] "Documents" refers to documents such as securities reports and environmental, social and governance (ESG) related reports that contain information related to carbon neutrality.

[0008] "Means for uploading" refers to a function that allows a user to send materials from a terminal to a server.

[0009] "Natural language processing technology" refers to technology for analyzing text data and converting it into an understandable format.

[0010] "Means of analysis" refers to the function of analyzing uploaded materials using natural language processing technology and extracting necessary information.

[0011] "Information related to carbon neutrality" refers to data related to carbon neutrality, such as energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0012] "Database" refers to a collection of digital data that stores information about carbon neutrality-related proposals and measures.

[0013] "Means of matching" refers to the function of comparing the information obtained from the analysis with a database and selecting the most appropriate proposal.

[0014] "Proposals" refer to specific measures and plans for achieving carbon neutrality.

[0015] "Implementation costs" refer to the initial and operational costs required to implement the selected carbon neutral measures.

[0016] "CO2 reduction" refers to the amount of carbon dioxide that can be reduced by implementing the selected measures.

[0017] "Return on investment (ROI)" refers to the ratio of expected effects or benefits to the investment cost.

[0018] "Means of calculation" refers to the function for calculating implementation costs, CO2 reductions, and return on investment based on the proposal.

[0019] "Proposal" refers to a document that describes the proposal, implementation costs, expected CO2 reductions, and return on investment.

[0020] "Means for providing" refers to a function for providing the generated proposal to the user in a format that can be viewed or downloaded. [Brief explanation of the drawings]

[0021] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0022] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0023] First, the terms used in the following description will be explained.

[0024] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0025] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0026] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0027] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0032] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0034] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0035] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0041] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0042] The present invention is a system that analyzes materials provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system operates through multiple steps to propose efficient and effective carbon neutral measures to corporate clients.

[0043] Equipment and network configuration used

[0044] The system consists of the following hardware and software components:

[0045] User devices: Includes PCs and mobile devices.

[0046] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[0047] Database: Contains carbon neutral related proposals and measures.

[0048] Each function of this system is executed by the terminal communicating with the server via the network.

[0049] System flow and specific operations

[0050] Uploading materials

[0051] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents.

[0052] The terminal transmits the selected material file to the server.

[0053] Analysis of data

[0054] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file, it uses the PDF processing engine, if it is a DOCX file, it uses the DOCX processing engine.

[0055] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0056] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0057] Database Matching

[0058] The server compares the extracted information with the system's database, which contains information on the various policies, technologies, and costs that can be achieved within the carbon neutral range.

[0059] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment, expanding renewable energy sources, or purchasing carbon credits.

[0060] Proposal Generation

[0061] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[0062] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[0063] Providing suggestions

[0064] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[0065] Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[0066] Specific examples

[0067] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the results with the database, proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," and calculates the implementation costs, expected CO2 reductions, and long-term return on investment.

[0068] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the most appropriate measures.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[0072] Step 2:

[0073] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[0074] Step 3:

[0075] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[0076] Step 4:

[0077] The device sends the selected file to the server, completing the upload of the file.

[0078] Step 5:

[0079] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[0080] Step 6:

[0081] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[0082] Step 7:

[0083] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0084] Step 8:

[0085] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[0086] Step 9:

[0087] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[0088] Step 10:

[0089] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[0090] Step 11:

[0091] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[0092] Step 12:

[0093] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[0094] Step 13:

[0095] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[0096] Example 1

[0097] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0098] Achieving carbon neutrality is an important issue for companies, but selecting the optimal measures and evaluating their cost-effectiveness requires advanced analytical capabilities and a large amount of information. Current systems often rely on manual work to extract and analyze the necessary information, resulting in a lack of efficiency. In addition, the creation of proposals and the incorporation of user feedback are not sufficiently automated, making it difficult to quickly provide optimal proposals. Therefore, a more efficient and automated method is needed.

[0099] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0100] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutrality-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for including charts and visual information when generating the proposal, means for a user to log in and download or view the generated proposal, and means for a user to provide additional feedback or questions through the system. This enables the proposal and evaluation of optimal carbon neutrality measures to be made quickly and efficiently.

[0101] "Corporate Customer" means a corporate customer that uses the system to receive carbon neutral related proposals.

[0102] "Documents" refer to documents such as securities reports and ESG-related materials that corporate clients upload to the system.

[0103] "Means of uploading" refers to the functions and methods by which corporate clients can submit their company materials to the system.

[0104] "Natural language processing technology" is a technology for analyzing text data and extracting meaning and information.

[0105] "Means for extracting information" refers to a method for extracting information related to carbon neutrality from uploaded materials using natural language processing technology.

[0106] A "database matching means" is a method for comparing extracted information with existing information stored in a database.

[0107] "Carbon neutrality-related proposals" are specific policies and measures that companies should take to achieve carbon neutrality.

[0108] "Implementation costs" are the costs required to implement carbon neutral proposals.

[0109] "CO2 reduction" refers to the amount of carbon dioxide reduced by implementing carbon neutral proposals.

[0110] "Return on investment (ROI)" is an indicator obtained by comparing the benefits and effects obtained by implementing carbon neutral proposals with the costs involved.

[0111] The "means for generating a proposal" is a method for automatically creating a document that describes the content of a carbon-neutral proposal, its implementation costs, expected effects, etc.

[0112] The "means for providing a proposal" is a method for distributing the generated proposal to the corporate client.

[0113] "Means for including diagrams and visual information" refers to the ability to insert diagrams, charts, etc. to make the information in the proposal easier to understand visually.

[0114] "Means for downloading or viewing" means a method by which a corporate client obtains or displays a generated proposal via the Internet.

[0115] "Means for providing feedback and questions" is a function that allows corporate customers to submit opinions and questions about proposals within the system.

[0116] The present invention is a system that analyzes documents provided by corporate clients and presents optimal carbon neutral proposals. This system operates using specific hardware and software components to provide efficient and effective carbon neutral proposals to corporate clients.

[0117] The equipment and network configuration used in this system are as follows:

[0118] Hardware and software used

[0119] User devices: Includes PCs and mobile devices.

[0120] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[0121] Database: Contains carbon neutrality-related proposals and measures.

[0122] The terminal communicates with the server via the network to execute the various functions of this system. This system operates as follows.

[0123] Basic system operation

[0124] First, a user logs in to the system using a terminal and selects and uploads their company's securities report and ESG-related documents. The terminal then sends the selected document files to the server, which then processes them.

[0125] The server automatically identifies the file format of the uploaded material. For example, if it is a PDF file, it uses a PDF processing engine (e.g., Apache® PDFBox), and if it is a DOCX file, it uses a DOCX processing engine (e.g., Apache POI). The server then invokes the parsing engine for the corresponding file format and converts the content into text data.

[0126] The server then applies natural language processing (NLP) techniques (e.g., spaCy, NLTK) to extract information related to carbon neutrality from the text data, such as energy consumption, CO2 emissions, and renewable energy usage.

[0127] The extracted information is then compared with the system's database by the server. This database contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the results of the comparison, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[0128] The server designs a detailed plan based on the optimal proposal, calculates its implementation cost, expected CO2 reduction, and return on investment (ROI), and automatically generates a proposal for the reduction plan incorporating this information. This proposal specifies specific measures, costs, and expected effects, and also includes charts and visual information.

[0129] The generated proposal can be downloaded or viewed by the user by logging in to the system. The user can also check the proposal contents using a terminal and provide additional feedback or questions through the system.

[0130] Specific examples

[0131] For example, suppose a company uploads a file called "2023_ESG_Report.pdf" to the system. This file contains information about annual energy consumption and CO2 emissions. The server uses Apache PDFBox to analyze the PDF file and extract the energy consumption and CO2 emissions data as text. It then uses NLP technology such as spaCy to organize this data, compare it with a database, and propose optimal measures.

[0132] Prompt Sentence Examples

[0133] You can ask the generative AI model to explain the system using prompts like the following:

[0134] "Please provide a description of a system that analyzes documents provided by corporate customers and presents optimal carbon-neutral related proposals. This system will include the following steps: uploading documents, analyzing the documents, comparing them with a database, generating proposals, and providing the proposals. Please also provide a detailed description of the specific hardware, software, and analysis engine used."

[0135] In this way, the present invention provides companies with the information they need to achieve carbon neutrality and helps them select the most appropriate measures.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1: Upload your materials

[0138] 1. A user logs in to the system using a terminal.

[0139] Input: User ID and password.

[0140] Output: A successful login message to the system.

[0141] Specific operation: "The user accesses the dedicated web application from their own PC and logs in by entering their ID and password."

[0142] 2. The user selects and uploads their company's securities report and ESG-related documents.

[0143] Input: The file to upload.

[0144] Output: File upload successful message.

[0145] Specific operation: "The user clicks the file upload button, selects "2023_ESG_Report.pdf" from the local drive, and uploads it."

[0146] 3. The terminal sends the selected document file to the server.

[0147] Input: Document file.

[0148] Output: Notification that file has been sent to the server.

[0149] Specific operation: "The device uses the API to send a file to the server. At this time, the file's metadata (file name, extension, size) is also sent."

[0150] Step 2: Analyze the data

[0151] 1. The server automatically identifies the file format of the uploaded material.

[0152] Input: Document file.

[0153] Output: File format specific information (e.g. "PDF").

[0154] Specific behavior: "The server checks the file extension, and if it is ".pdf", selects the PDF processing engine."

[0155] 2. The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0156] Input: Document file.

[0157] Output: Text data.

[0158] What it does: "The server uses a PDF processing engine to parse the PDF file and extract text data, such as Chapter 1, "Corporate Energy Consumption," and Chapter 2, "CO2 Emissions."

[0159] 3. The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from the text data.

[0160] Input: Text data.

[0161] Output: Extracted information (energy consumption, CO2 emissions, renewable energy share, etc.).

[0162] Specific operation: "The server uses an NLP library to analyze the extracted text data. Energy consumption, CO2 emissions, and the percentage of renewable energy used are automatically identified and extracted as numerical values."

[0163] Step 3: Check against the database

[0164] 1. The server checks the extracted information against the database in the system.

[0165] Input: Extracted information.

[0166] Output: Matching results (optimal action candidates).

[0167] How it works: "The server queries the database to obtain information about energy-efficient technologies and policies. For example, it applies rules such as, 'If the renewable energy usage rate is less than 10%, then the installation of solar panels is recommended.'"

[0168] 2. Based on the matching results, the server selects the most appropriate carbon-neutral measures for the user.

[0169] Input: Matching result.

[0170] Output: The selected optimal strategy.

[0171] Specific operation: "Based on the matching results, the server creates a list of measures, such as introducing energy-efficient lighting or installing solar panels, and selects the most efficient measure from among them."

[0172] Step 4: Generate proposals

[0173] 1. The server designs a detailed plan based on the optimal proposal and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[0174] Input: The selected optimal measure.

[0175] Output: installation cost, CO2 reduction, ROI.

[0176] Specific operation: "The server uses a spreadsheet or similar to calculate the implementation cost of each measure (e.g., "Implementation of energy-efficient lighting: 3 million yen"), the expected CO2 reduction (e.g., "CO2 reduction of 20 tons per year"), and ROI (e.g., "Payback in 5 years").

[0177] 2. The server incorporates this information and automatically generates a reduction plan proposal.

[0178] Inputs: installation cost, CO2 reduction, ROI.

[0179] Output: Proposed reduction plan.

[0180] Specific operation: "The server creates a proposal using a document template, specifying the details of each measure, implementation costs, and expected effects. The proposal also includes diagrams and charts, and is output in a visually easy-to-understand format."

[0181] Step 5: Provide a proposal

[0182] 1. The server provides the generated proposal to the user.

[0183] Input: Abatement plan proposal.

[0184] Output: A file link or download link for the proposal.

[0185] Specific behavior: "The server converts the generated proposal to PDF format, associates it with the user's account, and generates a download link."

[0186] 2. The user logs into the system and downloads or views the proposal.

[0187] Input: Login information to the system.

[0188] Output: Proposal download or viewing page.

[0189] Specific operation: "The user logs in to the system again and clicks the 'Download Proposal' button on the dashboard to download the proposal."

[0190] 3. Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[0191] Input: Your feedback or question.

[0192] Output: A confirmation that feedback or questions have been submitted.

[0193] Specific behavior: "Users review the proposal and, if necessary, submit additional questions or requests using the feedback form within the system."

[0194] (Application example 1)

[0195] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0196] In today's world, reducing energy consumption and CO2 emissions in factories is an important issue from the perspectives of both environmental protection and cost reduction. However, existing systems that provide carbon-neutral measures lack the functionality to collect energy consumption data for each piece of equipment in real time and visually present optimal measures on the spot, making it difficult for factory workers to make quick decisions. In addition, the process of analyzing data and generating recommendations is not automated, requiring a huge amount of time and effort. Therefore, there is a need to develop a new system that can implement carbon-neutral measures efficiently and effectively.

[0197] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0198] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for collecting energy consumption and CO2 emissions for each piece of equipment in the factory in real time; and means for proposing optimal carbon neutral measures based on the collected data and visually presenting the proposal to factory workers. This not only enables real-time monitoring of energy consumption and CO2 emissions in the factory, but also enables workers to instantly understand carbon neutral measures and make quick decisions.

[0199] "Corporate Customer" means a company or organization that conducts business or commercial activities.

[0200] "Materials" means documents, reports, data files and other information-containing media provided by Corporate Clients.

[0201] "Upload" refers to the act of sending data from a local device to a remote system, such as a server.

[0202] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[0203] "Analysis" refers to the act of understanding the information contained in a material and breaking it down for a specific purpose.

[0204] "Carbon neutral" refers to efforts aimed at reducing greenhouse gas emissions to virtually zero.

[0205] "Information extraction" refers to the process of extracting necessary data from documents.

[0206] A "database" refers to a system that organizes, stores, and manages data based on certain rules.

[0207] A "proposal" refers to the presentation of recommended actions or measures to solve a particular problem.

[0208] "Cost" refers to the expenses required to implement the proposed measures.

[0209] "CO2 reduction" refers to the total amount of carbon dioxide that is expected to be reduced as a result of the measures.

[0210] "Return on investment" refers to an indicator that shows the profit or effect of an investment.

[0211] "Proposal" refers to a document summarizing the proposal.

[0212] "User" refers to any individual or legal entity that uses the System.

[0213] "Real-time" refers to operations and processing that are carried out simultaneously with real time.

[0214] "Equipment" refers to the devices and equipment used within a factory.

[0215] "Visual presentation" refers to displaying information or data in a form that can be perceived by the human eye.

[0216] This invention is a system that analyzes documents provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system collects and analyzes data in real time to generate appropriate proposals to reduce corporate clients' energy consumption and CO2 emissions.

[0217] Equipment and network configuration used

[0218] The system consists of the following hardware and software components:

[0219] User devices: PCs, smart glasses, smartphones, etc.

[0220] Server: A server system for analyzing data, generating proposals, creating reports, etc.

[0221] Database: Carbon neutral related proposals and measures are stored

[0222] System flow and specific operations

[0223] Uploading materials

[0224] The user logs into the system using a terminal, selects and uploads their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[0225] Analysis of data

[0226] The server automatically identifies the file format of the uploaded material. For example, if it's a PDF file, it uses a PDF processing engine, and if it's a DOCX file, it uses a DOCX processing engine. The server then launches an analysis engine for the corresponding file format and converts the content into text data. The server then applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data.

[0227] Database Matching

[0228] The server compares the extracted information with the system's database, which contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the comparison results, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[0229] Proposal Generation

[0230] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). This information is then incorporated to automatically generate a proposal for a reduction plan. This proposal clearly states the specific measures, costs, and expected effects.

[0231] Providing suggestions

[0232] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[0233] Real-time data collection and presentation within the factory

[0234] The system also includes a means to collect real-time energy consumption and CO2 emissions data for each piece of equipment in the factory. This is done using smart glasses and other sensor devices. The collected data is sent to a cloud server, where it is compared with an existing database and optimal carbon-neutral measures are proposed. The proposals are visually presented to factory workers through the smart glasses.

[0235] Hardware and software used

[0236] Hardware: Smart glasses (e.g., Google® Glass®, Vuzix Blade), PC, smartphone

[0237] Software Libraries:

[0238] TENSORFLOW(R): Data analysis and NLP models

[0239] OpenCV: Camera data analysis for smart glasses

[0240] Flask: Receiving data and providing API

[0241] Specific examples

[0242] A manufacturing plant uses smart glasses to collect energy consumption data from equipment in real time. Factory engineers use the glasses to monitor the energy data of each piece of equipment in the plant and confirm the optimal measures provided by the Carbon Neutral Assistant (CNA).

[0243] Prompt Sentence Examples

[0244] "Design a system that uses smart glasses to collect real-time energy consumption data from a manufacturing plant and provide optimal carbon-neutral measures. The system will use natural language processing (NLP) techniques to analyze the data and calculate the return on investment (ROI)."

[0245] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0246] Step 1:

[0247] Uploading materials

[0248] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[0249] Input: User selected material file

[0250] Output: The document file sent to the server

[0251] Step 2:

[0252] Identifying the file format of the material

[0253] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file it will use the PDF processing engine, if it is a DOCX file it will use the DOCX processing engine, etc.

[0254] Input: Uploaded file

[0255] Output: Identified file formats

[0256] Step 3:

[0257] Text conversion of material content

[0258] The server starts the analysis engine for the corresponding file format and converts the content into text data. The PDF processing engine converts PDF to text, and the DOCX processing engine converts DOCX to text.

[0259] Input: Identified file format, material file

[0260] Output: Content converted to text

[0261] Step 4:

[0262] Extraction of carbon neutral related information

[0263] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality (energy consumption, CO2 emissions, etc.) from text data.

[0264] Input: Content converted to text

[0265] Output: Extracted carbon-neutral related information

[0266] Step 5:

[0267] Database Matching

[0268] The server compares the extracted information with the system's database, which includes carbon-neutral measures, technologies, and cost information. The server then selects the optimal carbon-neutral measures based on the comparison results.

[0269] Input: Extracted carbon-neutral related information

[0270] Output: Selected optimal carbon-neutral measures

[0271] Step 6:

[0272] Detailed design of proposal and ROI calculation

[0273] Based on the selected proposal, the server designs a detailed policy plan and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[0274] Input: Selected carbon neutral measures

[0275] Output: installation cost, expected CO2 reduction, return on investment (ROI)

[0276] Step 7:

[0277] Proposal generation

[0278] The server automatically generates a proposal for a reduction plan based on the calculation results, which includes specific measures, costs, and expected effects.

[0279] Input: Implementation cost, expected CO2 reduction, return on investment (ROI)

[0280] Output: Proposal

[0281] Step 8:

[0282] Proposal submission

[0283] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[0284] Input: Proposal

[0285] Output: A proposal that users can download or view

[0286] Step 9:

[0287] Real-time monitoring

[0288] Energy consumption and CO2 emissions from each piece of equipment in the factory are collected in real time using smart glasses and sensor devices, which send the data to a cloud server.

[0289] Input: Energy consumption data and CO2 emission data of factory equipment

[0290] Output: Real-time data sent to cloud server

[0291] Step 10:

[0292] Real-time suggestions

[0293] Based on the collected data, the server compares it with existing databases and generates optimal carbon-neutral measures, which are visually presented to factory workers through smart glasses.

[0294] Input: Real-time data, database

[0295] Output: Carbon neutral measures presented to the worker

[0296] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0297] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[0298] Equipment and network configuration used

[0299] The system consists of the following hardware and software components:

[0300] User devices: Includes PCs and mobile devices.

[0301] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[0302] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[0303] Each function of the system is executed by the terminal communicating with the server via the network.

[0304] System flow and specific operations

[0305] Uploading materials

[0306] Users log in to the system, select their company's securities report and ESG-related documents, and upload them. The upload process is carried out via a terminal.

[0307] The terminal transmits the selected material file to the server, thereby completing the upload of the material.

[0308] Analysis of data

[0309] The server automatically identifies the file format of the uploaded document, for example, if it is a PDF file, it uses the PDF parsing engine, if it is a DOCX file, it uses the DOCX parsing engine.

[0310] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0311] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0312] Database Matching

[0313] The server compares the extracted information with a built-in database containing information on a wide variety of measures, technologies, and costs that can be achieved within the carbon neutral range.

[0314] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment or expanding renewable energy.

[0315] Proposal Generation

[0316] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[0317] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[0318] Providing suggestions and recognizing user emotions

[0319] The server provides the generated proposal to the user, who can then log into the system to download or view the proposal.

[0320] The server activates an emotion engine to recognize the user's emotions while viewing the proposal, and senses feedback and reactions in real time.

[0321] Processing and using emotional data

[0322] The server processes the user's emotional data collected by the emotion engine and customizes the suggestions as needed, for example by providing additional information or alternative suggestions if the user has a negative reaction to a suggestion.

[0323] The server stores the user's emotional data in a database and uses it when generating future suggestions, allowing for more optimal suggestions.

[0324] Specific examples

[0325] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the report with the database and proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. A proposal is generated and provided to the user, and the emotion engine senses the user's reactions in real time and adjusts the proposal as necessary.

[0326] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the optimal strategy. Furthermore, by recognizing the user's emotions, it is possible to make more effective suggestions.

[0327] The processing flow will be explained below.

[0328] Step 1:

[0329] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[0330] Step 2:

[0331] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[0332] Step 3:

[0333] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[0334] Step 4:

[0335] The device sends the selected file to the server, completing the upload of the file.

[0336] Step 5:

[0337] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[0338] Step 6:

[0339] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[0340] Step 7:

[0341] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the proportion of renewable energy used.

[0342] Step 8:

[0343] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[0344] Step 9:

[0345] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[0346] Step 10:

[0347] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[0348] Step 11:

[0349] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[0350] Step 12:

[0351] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[0352] Step 13:

[0353] The server activates the emotion engine while the user logs in and views the proposal, and senses the user's feedback and reactions in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[0354] Step 14:

[0355] The server determines the user's sentiment based on the data collected from the emotion engine, and if the user responds negatively to the suggestion, it presents additional information or suggests an alternative.

[0356] Step 15:

[0357] The server stores the user's emotion data obtained by the emotion engine in a database, which is used as a reference for future proposal generation.

[0358] Step 16:

[0359] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[0360] Example 2

[0361] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0362] Carbon neutrality measures are an important issue for companies, but collecting appropriate information and creating proposals for this purpose requires a lot of time and effort. Furthermore, because the optimal measures vary from company to company, individual responses are required rather than general-purpose proposals. Furthermore, conventional systems do not adjust proposals to reflect user reactions and emotions, which can lead to proposals not being fully effective.

[0363] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0364] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for recognizing the user's emotions while the user is viewing the proposal, and means for adjusting the proposal content based on the recognized emotions. This enables the server to propose optimal carbon neutral measures for each company and to make effective proposals that reflect the user's emotions.

[0365] "Corporate customers" refer to companies and organizations that receive proposals for carbon neutral measures.

[0366] "Documents" refers to document files to be analyzed provided by corporate clients, including securities reports and ESG-related documents.

[0367] "Means for uploading" refers to the function by which a user uses a terminal to send a document file to a server.

[0368] "Natural language processing technology" refers to language analysis technology for extracting meaningful information from text data, and is particularly a technology for identifying information such as energy consumption and CO2 emissions.

[0369] "Means for extraction" refers to the ability to automatically identify and extract information related to carbon neutrality from materials.

[0370] "Database" refers to a collection of information that stores carbon neutral policies, technologies, cost information, etc.

[0371] "Means of matching" refers to the function of comparing extracted information with information in the database and selecting the most suitable proposal.

[0372] "Selected proposal" refers to the carbon-neutral measure that is deemed optimal for the user, based on the results of comparison with the database.

[0373] "Implementation costs" refers to the costs required to implement the selected proposal.

[0374] "Expected CO2 reduction" refers to the amount of CO2 emissions expected to be reduced if the proposal is implemented.

[0375] "Return on Investment (ROI)" refers to the ratio of benefits to costs obtained by implementing a proposal.

[0376] "Means for generating" refers to the function of creating a proposal based on the selected proposal.

[0377] A "proposal" refers to a document that summarizes the details of the proposal, implementation costs, expected effects, etc.

[0378] "Means for providing" refers to a function that allows users to access the generated proposal.

[0379] "Means for recognizing user emotions" refers to a function that detects emotions from facial expressions and voice while the user is viewing the proposal.

[0380] "Means for adjusting the content of suggestions" refers to a function for changing the content of suggestions based on the recognized user sentiment.

[0381] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[0382] The system consists of the following major hardware and software components:

[0383] User devices: Includes PCs and mobile devices.

[0384] Server: Performs document analysis, proposal generation, report creation, emotion recognition, etc.

[0385] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[0386] Each function of the system is executed by the terminal communicating with the server via the network.

[0387] First, a user logs into the system and selects and uploads their company's securities report or ESG-related document file on the upload screen. At this time, the document is sent from the terminal to the server. The server then automatically identifies the file format of the received document and converts the content into text data using an appropriate analysis engine (e.g., PDF analysis engine or DOCX analysis engine). At this stage, libraries such as PyMuPDF and python-docx are used.

[0388] The server then applies natural language processing (NLP) techniques to extract carbon-neutral information from the converted text data, using libraries such as SpaCy and NLTK to identify energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0389] The extracted information is compared with a database by the server, and the optimal carbon-neutral measures are selected. This database contains pre-registered information on a wide range of measures, technologies, and costs related to carbon neutrality. Specific measures are then proposed to the user. The selected proposals include, for example, the introduction of energy-efficient equipment and the expansion of renewable energy, and the introduction costs, expected CO2 reductions, and return on investment (ROI) for each are calculated.

[0390] The server then incorporates this information to automatically generate a detailed proposal, which specifies specific measures, implementation costs, and expected benefits. The generated proposal is then provided to the user, who can then log in to the system and download or view the proposal.

[0391] The server also activates an emotion recognition engine while the proposal is being viewed, detecting emotions in real time from the user's facial expressions and voice. Based on the user's reactions, the proposal content is adjusted as needed. This emotion recognition engine could utilize OpenCV or Microsoft® Azure® emotion recognition APIs, for example.

[0392] The server stores this emotional data in a database and uses it to generate future suggestions. This allows the system to learn the user's emotional tendencies and provide more appropriate suggestions.

[0393] As a specific example, if a company uploads its ESG report to this system, the report will include annual energy consumption and CO2 emissions. The server will analyze this and extract the current energy consumption and CO2 emissions. The server will then compare this with the database and propose specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. As the proposal is generated and provided to the user, an emotion recognition engine will sense the user's reactions in real time and adjust the proposal as necessary.

[0394] An example of a prompt sentence is, "Please analyze the text of the ESG-related materials below, extract information related to carbon neutrality, and generate recommendations."

[0395] As described above, this system provides companies with the information they need to achieve carbon neutrality and enables them to make more effective proposals based on user emotions.

[0396] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0397] Step 1:

[0398] A user logs into the system. They enter their username and password through a terminal, and once authenticated, the dashboard is displayed. The input is the username and password, and the output is a transition to the user interface.

[0399] Step 2:

[0400] The user moves to the upload screen, selects and uploads their company's securities report or ESG-related document file. The input is a document file (e.g. PDF, DOCX), and the output is sending the file to the server and a notification that the upload is complete. Specifically, the user opens the file selection dialog, selects the file, and clicks the "Upload" button.

[0401] Step 3:

[0402] The terminal sends the selected document file to the server. The input is the document file selected by the user, and the output is the file saved on the server. The specific operation is to send the file to the server using an HTTP POST request.

[0403] Step 4:

[0404] The server automatically identifies the file format of the received document, for example by analyzing the file extension and header information. The input is the uploaded file, and the output is the identified file format (e.g. PDF, DOCX). Specific operations include reading the file header and selecting a reader library.

[0405] Step 5:

[0406] The server starts the analysis engine for the corresponding file format (e.g. PDF analysis engine, DOCX analysis engine) and converts the content into text data. The input is the identified file format and the output is text data. Specifically, it uses libraries such as PyMuPDF or python-docx to read the file content and convert it into a string.

[0407] Step 6:

[0408] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from text data. The input is text data, and the output is specific information such as energy consumption, CO2 emissions, and the percentage of renewable energy used. Specifically, it uses SpaCy and NLTK to extract keywords and phrases of interest.

[0409] Step 7:

[0410] The server compares the extracted information with its internal database. The input is the extracted carbon neutral related information, and the output is related policy information from the database. Specifically, it searches for policy information in the database using SQL queries.

[0411] Step 8:

[0412] The server selects the optimal carbon-neutral measures for the user based on the matching results. The input is the matched database information, and the output is the selected measures. Specifically, the measures are ranked using an optimization algorithm.

[0413] Step 9:

[0414] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). The input is the selected measures, and the output is a detailed draft proposal. Specific operations use a cost calculation engine and an effect prediction model.

[0415] Step 10:

[0416] The server automatically generates a proposal based on the calculated information. The input is the detailed proposal, and the output is the completed proposal. Specific operations involve using a document generation library (e.g., ReportLab).

[0417] Step 11:

[0418] The server provides the generated proposal to the user. The input is the completed proposal, and the output is a format that the user can view or download. Specifically, the server uploads the proposal to a file server and generates a URL.

[0419] Step 12:

[0420] The server starts an emotion recognition engine while the user is viewing the proposal, and detects emotions in real time from the user's facial expressions and voice. The input is the user's facial expression and voice data, and the output is the emotion recognition results. Specific operations utilize OpenCV and Microsoft Azure's emotion recognition API.

[0421] Step 13:

[0422] The server adjusts the proposal content based on the recognized emotion. The input is the emotion recognition result, and the output is the revised proposal. Specifically, the server recalculates and regenerates the proposal content based on the emotion feedback.

[0423] Step 14:

[0424] The server stores the user's emotion data in a database and uses it to generate future suggestions. The input is emotion data, and the output is updated database information. Specifically, the server performs an insert operation into the database.

[0425] (Application example 2)

[0426] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0427] Implementing carbon neutral measures is an important challenge for modern companies. However, many companies do not have the resources to analyze vast amounts of data and select the optimal measures. Furthermore, if the sentiment of managers and employees is not taken into account when a proposal is made, it may be difficult to adopt the proposal. Therefore, a system is needed that can accurately and efficiently propose carbon neutral measures and adjust the content based on the sentiment of the recipients of the proposal.

[0428] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0429] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting the optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for recognizing in real time the emotions of users receiving the proposal using cameras installed in the factory; and means for adjusting the proposal content based on the recognized emotions. This makes it easier for companies to adopt carbon neutral measures efficiently and effectively, and by appropriately adjusting the proposal content, it becomes easier for proposals to be accepted.

[0430] "Corporate Customer" means a company or organization registered as a legal entity or its representatives.

[0431] "Materials" means information in the form of documents or files, including reports and data provided by Corporate Clients.

[0432] "Upload" refers to the act of sending materials from a user's device to a server.

[0433] "Natural language processing technology" refers to computer processing technology for understanding, analyzing, and generating human language.

[0434] "Carbon neutral" refers to a state that aims to balance CO2 emissions and absorption.

[0435] "Extraction" refers to the act of finding and extracting necessary information from materials based on specific conditions.

[0436] A "database" refers to a collection of accumulated data that is stored and managed for a specific purpose.

[0437] "Proposals" refer to reports or plans that recommend optimal carbon-neutral measures to corporate clients based on the extracted information.

[0438] "Implementation costs" refer to the expenses required to actually implement the proposed measures or measures.

[0439] "CO2 reduction" refers to the amount of carbon dioxide that will be reduced as a result of implementing the proposed measures.

[0440] "Return on investment" is an indicator that evaluates the effects and benefits obtained in relation to the capital invested.

[0441] A "proposal" refers to a document that clearly states specific measures, costs, and expected effects.

[0442] "User" refers to a corporate client or its representative who uses the system and receives a proposal.

[0443] "Camera" refers to a device for capturing images or video.

[0444] "Emotion" refers to the user's psychological reaction to the suggestion.

[0445] "Recognition" refers to the act of analyzing captured images and data to determine emotions.

[0446] "Adjustment" refers to the act of changing or adapting suggestions based on the user's feelings.

[0447] This invention is a system that analyzes documents provided by corporate clients and provides optimal proposals related to carbon neutrality. It is designed to implement effective carbon neutral measures, particularly in large-scale facilities such as factories. The system also has the ability to recognize the emotions of users who will receive the proposals in real time and adjust the content of the proposals accordingly.

[0448] Equipment and network configuration used

[0449] The system consists of the following hardware and software components:

[0450] User devices: Includes PCs and mobile devices.

[0451] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[0452] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[0453] Camera: A device installed in the factory that recognizes the emotions of users receiving suggestions in real time.

[0454] Each function of the system is executed by the terminal communicating with the server via the network.

[0455] System flow and specific operations

[0456] Users log in to the system and upload their company's carbon neutrality-related documents. The documents are sent to the server via their device, which automatically identifies the format of the documents and launches an analysis engine. The files are converted into text data, and natural language processing technology is used to extract information related to carbon neutrality.

[0457] The server compares the extracted information with a database and selects the optimal carbon-neutral measures, such as introducing energy-efficient lighting or installing solar panels. The implementation costs, expected CO2 reductions, and return on investment of the selected measures are calculated, and a detailed proposal is generated.

[0458] The generated proposal is provided to the user, who can then access the system to view or download it. During this process, cameras installed in the factory recognize the user's emotions in real time as they receive the proposal, and the emotions are transmitted to the server.

[0459] The server uses the emotion recognition data to adjust the suggestions as needed. For example, if the user expresses a negative emotion, additional information or alternative suggestions may be provided. The emotion data is stored in a database and used to generate future suggestions.

[0460] Specific examples

[0461] For example, when a company uploads its energy consumption report to the system, the server analyzes the content and extracts energy consumption and CO2 emissions. The analysis results are compared with the database and measures such as "introducing energy-efficient equipment" or "installing solar panels" are proposed. The proposals clearly state the specific measures, implementation costs, expected CO2 reductions, and return on investment.

[0462] As the user browses the proposal, a camera captures their facial expressions and analyzes them using an emotion recognition model. For example, if a negative emotion is detected, the server adjusts the proposal to make it more acceptable to the user.

[0463] Example of a prompt statement for raw data processing:

[0464] python

[0465] Obtaining power consumption data

[0466] energy_data = get_energy_data()

[0467] Generate energy-efficient proposals

[0468] proposal = generate_proposal(energy_data)

[0469] Proposal Providing and Emotion Recognition

[0470] sentiment = recognize_emotion()

[0471] if sentiment == "negative":

[0472] proposal = adjust_proposal(proposal)

[0473] This system enables companies to efficiently and effectively select and apply carbon neutral measures, and by taking into account the sentiment of users receiving the proposals, it can improve the acceptance rate of the proposals.

[0474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0475] Step 1:

[0476] Users log in to the system using their device and upload carbon neutral-related documents. The input is documents such as ESG reports and energy consumption data provided by corporate clients, and the output is the transfer of these documents to the server. Specifically, the user selects the document using the device's file selection function and presses the upload button.

[0477] Step 2:

[0478] The server automatically identifies the format of the uploaded document and converts it to text data. The input is the uploaded document and the output is text data. The server then launches, for example, a PDF parsing engine or a DOCX parsing engine to convert the document to text format.

[0479] Step 3:

[0480] The server uses natural language processing technology to analyze text data and extract information related to carbon neutrality. The input is the text data of the document, and the output is the extracted information related to carbon neutrality. The server uses NLP (natural language processing) technology to extract energy consumption, CO2 emissions, etc.

[0481] Step 4:

[0482] The server compares the extracted information with the database and selects the best carbon-neutral related proposal. The input is the extracted carbon-neutral information and the output is the selected proposal. As part of the matching process, the server matches it with a database entry.

[0483] Step 5:

[0484] The server calculates the implementation cost, expected CO2 reduction, and return on investment of the selected proposal. The input is the selected proposal, and the output is the implementation cost, CO2 reduction, and return on investment. The server calculates these figures using a cost calculation engine.

[0485] Step 6:

[0486] The server generates a proposal that includes the calculation results. The input is data on implementation costs, CO2 reductions, and ROI, and the output is a proposal. Specifically, the server creates a draft proposal using an automatic generation algorithm.

[0487] Step 7:

[0488] The server provides the generated proposal to the user. The input is the generated proposal, and the output is that the user can view or download the proposal. The server creates and notifies the user of a link that the user can access on their device.

[0489] Step 8:

[0490] The camera is installed in the factory and recognizes the emotions of the user receiving the suggestions in real time. The input is the video data from the camera, and the output is the recognized emotion data. The emotion recognition engine analyzes the captured video and identifies the user's emotion.

[0491] Step 9:

[0492] The server then adjusts the suggestions as needed based on the emotion recognition data. The input is the recognized emotion data, and the output is the adjusted suggestions. For example, if the user expresses a negative emotion, the server generates additional explanatory material or alternative suggestions.

[0493] Step 10:

[0494] The server stores the user's emotional data in a database and uses it to generate future suggestions. The input is the emotional data, and the output is the saved data. Storing the emotional data improves the accuracy of future suggestions.

[0495] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0496] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0497] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0498] [Second embodiment]

[0499] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0500] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0501] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0502] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0503] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0504] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0505] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0506] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0507] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0508] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0509] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0510] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0511] The present invention is a system that analyzes materials provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system operates through multiple steps to propose efficient and effective carbon neutral measures to corporate clients.

[0512] Equipment and network configuration used

[0513] The system consists of the following hardware and software components:

[0514] User devices: Includes PCs and mobile devices.

[0515] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[0516] Database: Contains carbon neutral related proposals and measures.

[0517] Each function of this system is executed by the terminal communicating with the server via the network.

[0518] System flow and specific operations

[0519] Uploading materials

[0520] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents.

[0521] The terminal transmits the selected material file to the server.

[0522] Analysis of data

[0523] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file, it uses the PDF processing engine, if it is a DOCX file, it uses the DOCX processing engine.

[0524] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0525] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0526] Database Matching

[0527] The server compares the extracted information with the system's database, which contains information on the various policies, technologies, and costs that can be achieved within the carbon neutral range.

[0528] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment, expanding renewable energy sources, or purchasing carbon credits.

[0529] Proposal Generation

[0530] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[0531] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[0532] Providing suggestions

[0533] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[0534] Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[0535] Specific examples

[0536] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the results with the database, proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," and calculates the implementation costs, expected CO2 reductions, and long-term return on investment.

[0537] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the most appropriate measures.

[0538] The processing flow will be explained below.

[0539] Step 1:

[0540] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[0541] Step 2:

[0542] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[0543] Step 3:

[0544] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[0545] Step 4:

[0546] The device sends the selected file to the server, completing the upload of the file.

[0547] Step 5:

[0548] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[0549] Step 6:

[0550] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[0551] Step 7:

[0552] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0553] Step 8:

[0554] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[0555] Step 9:

[0556] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[0557] Step 10:

[0558] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[0559] Step 11:

[0560] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[0561] Step 12:

[0562] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[0563] Step 13:

[0564] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[0565] Example 1

[0566] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0567] Achieving carbon neutrality is an important issue for companies, but selecting the optimal measures and evaluating their cost-effectiveness requires advanced analytical capabilities and a large amount of information. Current systems often rely on manual work to extract and analyze the necessary information, resulting in a lack of efficiency. In addition, the creation of proposals and the incorporation of user feedback are not sufficiently automated, making it difficult to quickly provide optimal proposals. Therefore, a more efficient and automated method is needed.

[0568] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0569] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutrality-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for including charts and visual information when generating the proposal, means for a user to log in and download or view the generated proposal, and means for a user to provide additional feedback or questions through the system. This enables the proposal and evaluation of optimal carbon neutrality measures to be made quickly and efficiently.

[0570] "Corporate Customer" means a corporate customer that uses the system to receive carbon neutral related proposals.

[0571] "Documents" refer to documents such as securities reports and ESG-related materials that corporate clients upload to the system.

[0572] "Means of uploading" refers to the functions and methods by which corporate clients can submit their company materials to the system.

[0573] "Natural language processing technology" is a technology for analyzing text data and extracting meaning and information.

[0574] "Means for extracting information" refers to a method for extracting information related to carbon neutrality from uploaded materials using natural language processing technology.

[0575] A "database matching means" is a method for comparing extracted information with existing information stored in a database.

[0576] "Carbon neutrality-related proposals" are specific policies and measures that companies should take to achieve carbon neutrality.

[0577] "Implementation costs" are the costs required to implement carbon neutral proposals.

[0578] "CO2 reduction" refers to the amount of carbon dioxide reduced by implementing carbon neutral proposals.

[0579] "Return on investment (ROI)" is an indicator obtained by comparing the benefits and effects obtained by implementing carbon neutral proposals with the costs involved.

[0580] The "means for generating a proposal" is a method for automatically creating a document that describes the content of a carbon-neutral proposal, its implementation costs, expected effects, etc.

[0581] The "means for providing a proposal" is a method for distributing the generated proposal to the corporate client.

[0582] "Means for including diagrams and visual information" refers to the ability to insert diagrams, charts, etc. to make the information in the proposal easier to understand visually.

[0583] "Means for downloading or viewing" means a method by which a corporate client obtains or displays a generated proposal via the Internet.

[0584] "Means for providing feedback and questions" is a function that allows corporate customers to submit opinions and questions about proposals within the system.

[0585] The present invention is a system that analyzes documents provided by corporate clients and presents optimal carbon neutral proposals. This system operates using specific hardware and software components to provide efficient and effective carbon neutral proposals to corporate clients.

[0586] The equipment and network configuration used in this system are as follows:

[0587] Hardware and software used

[0588] User devices: Includes PCs and mobile devices.

[0589] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[0590] Database: Contains carbon neutrality-related proposals and measures.

[0591] The terminal communicates with the server via the network to execute the various functions of this system. This system operates as follows.

[0592] Basic system operation

[0593] First, a user logs in to the system using a terminal and selects and uploads their company's securities report and ESG-related documents. The terminal then sends the selected document files to the server, which then processes them.

[0594] The server automatically identifies the file format of the uploaded material. For example, if it is a PDF file, it uses a PDF processing engine (e.g., Apache PDFBox), and if it is a DOCX file, it uses a DOCX processing engine (e.g., Apache POI). The server then invokes the corresponding file format analysis engine and converts the content into text data.

[0595] The server then applies natural language processing (NLP) techniques (e.g., spaCy, NLTK) to extract information related to carbon neutrality from the text data, such as energy consumption, CO2 emissions, and renewable energy usage.

[0596] The extracted information is then compared with the system's database by the server. This database contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the results of the comparison, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[0597] The server designs a detailed plan based on the optimal proposal, calculates its implementation cost, expected CO2 reduction, and return on investment (ROI), and automatically generates a proposal for the reduction plan incorporating this information. This proposal specifies specific measures, costs, and expected effects, and also includes charts and visual information.

[0598] The generated proposal can be downloaded or viewed by the user by logging in to the system. The user can also check the proposal contents using a terminal and provide additional feedback or questions through the system.

[0599] Specific examples

[0600] For example, suppose a company uploads a file called "2023_ESG_Report.pdf" to the system. This file contains information about annual energy consumption and CO2 emissions. The server uses Apache PDFBox to analyze the PDF file and extract the energy consumption and CO2 emissions data as text. It then uses NLP technology such as spaCy to organize this data, compare it with a database, and propose optimal measures.

[0601] Prompt Sentence Examples

[0602] You can ask the generative AI model to explain the system using prompts like the following:

[0603] "Please provide a description of a system that analyzes documents provided by corporate customers and presents optimal carbon-neutral related proposals. This system will include the following steps: uploading documents, analyzing the documents, comparing them with a database, generating proposals, and providing the proposals. Please also provide a detailed description of the specific hardware, software, and analysis engine used."

[0604] In this way, the present invention provides companies with the information they need to achieve carbon neutrality and helps them select the most appropriate measures.

[0605] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0606] Step 1: Upload your materials

[0607] 1. A user logs in to the system using a terminal.

[0608] Input: User ID and password.

[0609] Output: A successful login message to the system.

[0610] Specific operation: "The user accesses the dedicated web application from their own PC and logs in by entering their ID and password."

[0611] 2. The user selects and uploads their company's securities report and ESG-related documents.

[0612] Input: The file to upload.

[0613] Output: File upload successful message.

[0614] Specific operation: "The user clicks the file upload button, selects "2023_ESG_Report.pdf" from the local drive, and uploads it."

[0615] 3. The terminal sends the selected document file to the server.

[0616] Input: Document file.

[0617] Output: Notification that file has been sent to the server.

[0618] Specific operation: "The device uses the API to send a file to the server. At this time, the file's metadata (file name, extension, size) is also sent."

[0619] Step 2: Analyze the data

[0620] 1. The server automatically identifies the file format of the uploaded material.

[0621] Input: Document file.

[0622] Output: File format specific information (e.g. "PDF").

[0623] Specific behavior: "The server checks the file extension, and if it is ".pdf", selects the PDF processing engine."

[0624] 2. The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0625] Input: Document file.

[0626] Output: Text data.

[0627] What it does: "The server uses a PDF processing engine to parse the PDF file and extract text data, such as Chapter 1, "Corporate Energy Consumption," and Chapter 2, "CO2 Emissions."

[0628] 3. The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from the text data.

[0629] Input: Text data.

[0630] Output: Extracted information (energy consumption, CO2 emissions, renewable energy share, etc.).

[0631] Specific operation: "The server uses an NLP library to analyze the extracted text data. Energy consumption, CO2 emissions, and the percentage of renewable energy used are automatically identified and extracted as numerical values."

[0632] Step 3: Check against the database

[0633] 1. The server checks the extracted information against the database in the system.

[0634] Input: Extracted information.

[0635] Output: Matching results (optimal action candidates).

[0636] How it works: "The server queries the database to obtain information about energy-efficient technologies and policies. For example, it applies rules such as, 'If the renewable energy usage rate is less than 10%, then the installation of solar panels is recommended.'"

[0637] 2. Based on the matching results, the server selects the most appropriate carbon-neutral measures for the user.

[0638] Input: Matching result.

[0639] Output: The selected optimal strategy.

[0640] Specific operation: "Based on the matching results, the server creates a list of measures, such as introducing energy-efficient lighting or installing solar panels, and selects the most efficient measure from among them."

[0641] Step 4: Generate proposals

[0642] 1. The server designs a detailed plan based on the optimal proposal and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[0643] Input: The selected optimal measure.

[0644] Output: installation cost, CO2 reduction, ROI.

[0645] Specific operation: "The server uses a spreadsheet or similar to calculate the implementation cost of each measure (e.g., "Implementation of energy-efficient lighting: 3 million yen"), the expected CO2 reduction (e.g., "CO2 reduction of 20 tons per year"), and ROI (e.g., "Payback in 5 years").

[0646] 2. The server incorporates this information and automatically generates a reduction plan proposal.

[0647] Inputs: installation cost, CO2 reduction, ROI.

[0648] Output: Proposed reduction plan.

[0649] Specific operation: "The server creates a proposal using a document template, specifying the details of each measure, implementation costs, and expected effects. The proposal also includes diagrams and charts, and is output in a visually easy-to-understand format."

[0650] Step 5: Provide a proposal

[0651] 1. The server provides the generated proposal to the user.

[0652] Input: Abatement plan proposal.

[0653] Output: A file link or download link for the proposal.

[0654] Specific behavior: "The server converts the generated proposal to PDF format, associates it with the user's account, and generates a download link."

[0655] 2. The user logs into the system and downloads or views the proposal.

[0656] Input: Login information to the system.

[0657] Output: Proposal download or viewing page.

[0658] Specific operation: "The user logs in to the system again and clicks the 'Download Proposal' button on the dashboard to download the proposal."

[0659] 3. Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[0660] Input: Your feedback or question.

[0661] Output: A confirmation that feedback or questions have been submitted.

[0662] Specific behavior: "Users review the proposal and, if necessary, submit additional questions or requests using the feedback form within the system."

[0663] (Application example 1)

[0664] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0665] In today's world, reducing energy consumption and CO2 emissions in factories is an important issue from the perspectives of both environmental protection and cost reduction. However, existing systems that provide carbon-neutral measures lack the functionality to collect energy consumption data for each piece of equipment in real time and visually present optimal measures on the spot, making it difficult for factory workers to make quick decisions. In addition, the process of analyzing data and generating recommendations is not automated, requiring a huge amount of time and effort. Therefore, there is a need to develop a new system that can implement carbon-neutral measures efficiently and effectively.

[0666] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0667] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for collecting energy consumption and CO2 emissions for each piece of equipment in the factory in real time; and means for proposing optimal carbon neutral measures based on the collected data and visually presenting the proposal to factory workers. This not only enables real-time monitoring of energy consumption and CO2 emissions in the factory, but also enables workers to instantly understand carbon neutral measures and make quick decisions.

[0668] "Corporate Customer" means a company or organization that conducts business or commercial activities.

[0669] "Materials" means documents, reports, data files and other information-containing media provided by Corporate Clients.

[0670] "Upload" refers to the act of sending data from a local device to a remote system, such as a server.

[0671] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[0672] "Analysis" refers to the act of understanding the information contained in a material and breaking it down for a specific purpose.

[0673] "Carbon neutral" refers to efforts aimed at reducing greenhouse gas emissions to virtually zero.

[0674] "Information extraction" refers to the process of extracting necessary data from documents.

[0675] A "database" refers to a system that organizes, stores, and manages data based on certain rules.

[0676] A "proposal" refers to the presentation of recommended actions or measures to solve a particular problem.

[0677] "Cost" refers to the expenses required to implement the proposed measures.

[0678] "CO2 reduction" refers to the total amount of carbon dioxide that is expected to be reduced as a result of the measures.

[0679] "Return on investment" refers to an indicator that shows the profit or effect of an investment.

[0680] "Proposal" refers to a document summarizing the proposal.

[0681] "User" refers to any individual or legal entity that uses the System.

[0682] "Real-time" refers to operations and processing that are carried out simultaneously with real time.

[0683] "Equipment" refers to the devices and equipment used within a factory.

[0684] "Visual presentation" refers to displaying information or data in a form that can be perceived by the human eye.

[0685] This invention is a system that analyzes documents provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system collects and analyzes data in real time to generate appropriate proposals to reduce corporate clients' energy consumption and CO2 emissions.

[0686] Equipment and network configuration used

[0687] The system consists of the following hardware and software components:

[0688] User devices: PCs, smart glasses, smartphones, etc.

[0689] Server: A server system for analyzing data, generating proposals, creating reports, etc.

[0690] Database: Carbon neutral related proposals and measures are stored

[0691] System flow and specific operations

[0692] Uploading materials

[0693] The user logs into the system using a terminal, selects and uploads their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[0694] Analysis of data

[0695] The server automatically identifies the file format of the uploaded material. For example, if it's a PDF file, it uses a PDF processing engine, and if it's a DOCX file, it uses a DOCX processing engine. The server then launches an analysis engine for the corresponding file format and converts the content into text data. The server then applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data.

[0696] Database Matching

[0697] The server compares the extracted information with the system's database, which contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the comparison results, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[0698] Proposal Generation

[0699] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). This information is then incorporated to automatically generate a proposal for a reduction plan. This proposal clearly states the specific measures, costs, and expected effects.

[0700] Providing suggestions

[0701] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[0702] Real-time data collection and presentation within the factory

[0703] The system also includes a means to collect real-time energy consumption and CO2 emissions data for each piece of equipment in the factory. This is done using smart glasses and other sensor devices. The collected data is sent to a cloud server, where it is compared with an existing database and optimal carbon-neutral measures are proposed. The proposals are visually presented to factory workers through the smart glasses.

[0704] Hardware and software used

[0705] Hardware: Smart glasses (e.g., Google Glass, Vuzix Blade), PC, smartphone

[0706] Software Libraries:

[0707] TensorFlow: Data analysis and NLP models

[0708] OpenCV: Camera data analysis for smart glasses

[0709] Flask: Receiving data and providing API

[0710] Specific examples

[0711] A manufacturing plant uses smart glasses to collect energy consumption data from equipment in real time. Factory engineers use the glasses to monitor the energy data of each piece of equipment in the plant and confirm the optimal measures provided by the Carbon Neutral Assistant (CNA).

[0712] Prompt Sentence Examples

[0713] "Design a system that uses smart glasses to collect real-time energy consumption data from a manufacturing plant and provide optimal carbon-neutral measures. The system will use natural language processing (NLP) techniques to analyze the data and calculate the return on investment (ROI)."

[0714] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0715] Step 1:

[0716] Uploading materials

[0717] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[0718] Input: User selected material file

[0719] Output: The document file sent to the server

[0720] Step 2:

[0721] Identifying the file format of the material

[0722] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file it will use the PDF processing engine, if it is a DOCX file it will use the DOCX processing engine, etc.

[0723] Input: Uploaded file

[0724] Output: Identified file formats

[0725] Step 3:

[0726] Text conversion of material content

[0727] The server starts the analysis engine for the corresponding file format and converts the content into text data. The PDF processing engine converts PDF to text, and the DOCX processing engine converts DOCX to text.

[0728] Input: Identified file format, material file

[0729] Output: Content converted to text

[0730] Step 4:

[0731] Extraction of carbon neutral related information

[0732] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality (energy consumption, CO2 emissions, etc.) from text data.

[0733] Input: Content converted to text

[0734] Output: Extracted carbon-neutral related information

[0735] Step 5:

[0736] Database Matching

[0737] The server compares the extracted information with the system's database, which includes carbon-neutral measures, technologies, and cost information. The server then selects the optimal carbon-neutral measures based on the comparison results.

[0738] Input: Extracted carbon-neutral related information

[0739] Output: Selected optimal carbon-neutral measures

[0740] Step 6:

[0741] Detailed design of proposal and ROI calculation

[0742] Based on the selected proposal, the server designs a detailed policy plan and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[0743] Input: Selected carbon neutral measures

[0744] Output: installation cost, expected CO2 reduction, return on investment (ROI)

[0745] Step 7:

[0746] Proposal generation

[0747] The server automatically generates a proposal for a reduction plan based on the calculation results, which includes specific measures, costs, and expected effects.

[0748] Input: Implementation cost, expected CO2 reduction, return on investment (ROI)

[0749] Output: Proposal

[0750] Step 8:

[0751] Proposal submission

[0752] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[0753] Input: Proposal

[0754] Output: A proposal that users can download or view

[0755] Step 9:

[0756] Real-time monitoring

[0757] Energy consumption and CO2 emissions from each piece of equipment in the factory are collected in real time using smart glasses and sensor devices, which send the data to a cloud server.

[0758] Input: Energy consumption data and CO2 emission data of factory equipment

[0759] Output: Real-time data sent to cloud server

[0760] Step 10:

[0761] Real-time suggestions

[0762] Based on the collected data, the server compares it with existing databases and generates optimal carbon-neutral measures, which are visually presented to factory workers through smart glasses.

[0763] Input: Real-time data, database

[0764] Output: Carbon neutral measures presented to the worker

[0765] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0766] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[0767] Equipment and network configuration used

[0768] The system consists of the following hardware and software components:

[0769] User devices: Includes PCs and mobile devices.

[0770] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[0771] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[0772] Each function of the system is executed by the terminal communicating with the server via the network.

[0773] System flow and specific operations

[0774] Uploading materials

[0775] Users log in to the system, select their company's securities report and ESG-related documents, and upload them. The upload process is carried out via a terminal.

[0776] The terminal transmits the selected material file to the server, thereby completing the upload of the material.

[0777] Analysis of data

[0778] The server automatically identifies the file format of the uploaded document, for example, if it is a PDF file, it uses the PDF parsing engine, if it is a DOCX file, it uses the DOCX parsing engine.

[0779] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0780] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0781] Database Matching

[0782] The server compares the extracted information with a built-in database containing information on a wide variety of measures, technologies, and costs that can be achieved within the carbon neutral range.

[0783] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment or expanding renewable energy.

[0784] Proposal Generation

[0785] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[0786] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[0787] Providing suggestions and recognizing user emotions

[0788] The server provides the generated proposal to the user, who can then log into the system to download or view the proposal.

[0789] The server activates an emotion engine to recognize the user's emotions while viewing the proposal, and senses feedback and reactions in real time.

[0790] Processing and using emotional data

[0791] The server processes the user's emotional data collected by the emotion engine and customizes the suggestions as needed, for example by providing additional information or alternative suggestions if the user has a negative reaction to a suggestion.

[0792] The server stores the user's emotional data in a database and uses it when generating future suggestions, allowing for more optimal suggestions.

[0793] Specific examples

[0794] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the report with the database and proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. A proposal is generated and provided to the user, and the emotion engine senses the user's reactions in real time and adjusts the proposal as necessary.

[0795] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the optimal strategy. Furthermore, by recognizing the user's emotions, it is possible to make more effective suggestions.

[0796] The processing flow will be explained below.

[0797] Step 1:

[0798] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[0799] Step 2:

[0800] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[0801] Step 3:

[0802] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[0803] Step 4:

[0804] The device sends the selected file to the server, completing the upload of the file.

[0805] Step 5:

[0806] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[0807] Step 6:

[0808] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[0809] Step 7:

[0810] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the proportion of renewable energy used.

[0811] Step 8:

[0812] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[0813] Step 9:

[0814] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[0815] Step 10:

[0816] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[0817] Step 11:

[0818] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[0819] Step 12:

[0820] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[0821] Step 13:

[0822] The server activates the emotion engine while the user logs in and views the proposal, and senses the user's feedback and reactions in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[0823] Step 14:

[0824] The server determines the user's sentiment based on the data collected from the emotion engine, and if the user responds negatively to the suggestion, it presents additional information or suggests an alternative.

[0825] Step 15:

[0826] The server stores the user's emotion data obtained by the emotion engine in a database, which is used as a reference for future proposal generation.

[0827] Step 16:

[0828] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[0829] Example 2

[0830] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0831] Carbon neutrality measures are an important issue for companies, but collecting appropriate information and creating proposals for this purpose requires a lot of time and effort. Furthermore, because the optimal measures vary from company to company, individual responses are required rather than general-purpose proposals. Furthermore, conventional systems do not adjust proposals to reflect user reactions and emotions, which can lead to proposals not being fully effective.

[0832] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0833] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for recognizing the user's emotions while the user is viewing the proposal, and means for adjusting the proposal content based on the recognized emotions. This enables the server to propose optimal carbon neutral measures for each company and to make effective proposals that reflect the user's emotions.

[0834] "Corporate customers" refer to companies and organizations that receive proposals for carbon neutral measures.

[0835] "Documents" refers to document files to be analyzed provided by corporate clients, including securities reports and ESG-related documents.

[0836] "Means for uploading" refers to the function by which a user uses a terminal to send a document file to a server.

[0837] "Natural language processing technology" refers to language analysis technology for extracting meaningful information from text data, and is particularly a technology for identifying information such as energy consumption and CO2 emissions.

[0838] "Means for extraction" refers to the ability to automatically identify and extract information related to carbon neutrality from materials.

[0839] "Database" refers to a collection of information that stores carbon neutral policies, technologies, cost information, etc.

[0840] "Means of matching" refers to the function of comparing extracted information with information in the database and selecting the most suitable proposal.

[0841] "Selected proposal" refers to the carbon-neutral measure that is deemed optimal for the user, based on the results of comparison with the database.

[0842] "Implementation costs" refers to the costs required to implement the selected proposal.

[0843] "Expected CO2 reduction" refers to the amount of CO2 emissions expected to be reduced if the proposal is implemented.

[0844] "Return on Investment (ROI)" refers to the ratio of benefits to costs obtained by implementing a proposal.

[0845] "Means for generating" refers to the function of creating a proposal based on the selected proposal.

[0846] A "proposal" refers to a document that summarizes the details of the proposal, implementation costs, expected effects, etc.

[0847] "Means for providing" refers to a function that allows users to access the generated proposal.

[0848] "Means for recognizing user emotions" refers to a function that detects emotions from facial expressions and voice while the user is viewing the proposal.

[0849] "Means for adjusting the content of suggestions" refers to a function for changing the content of suggestions based on the recognized user sentiment.

[0850] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[0851] The system consists of the following major hardware and software components:

[0852] User devices: Includes PCs and mobile devices.

[0853] Server: Performs document analysis, proposal generation, report creation, emotion recognition, etc.

[0854] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[0855] Each function of the system is executed by the terminal communicating with the server via the network.

[0856] First, a user logs into the system and selects and uploads their company's securities report or ESG-related document file on the upload screen. At this time, the document is sent from the terminal to the server. The server then automatically identifies the file format of the received document and converts the content into text data using an appropriate analysis engine (e.g., PDF analysis engine or DOCX analysis engine). At this stage, libraries such as PyMuPDF and python-docx are used.

[0857] The server then applies natural language processing (NLP) techniques to extract carbon-neutral information from the converted text data, using libraries such as SpaCy and NLTK to identify energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0858] The extracted information is compared with a database by the server, and the optimal carbon-neutral measures are selected. This database contains pre-registered information on a wide range of measures, technologies, and costs related to carbon neutrality. Specific measures are then proposed to the user. The selected proposals include, for example, the introduction of energy-efficient equipment and the expansion of renewable energy, and the introduction costs, expected CO2 reductions, and return on investment (ROI) for each are calculated.

[0859] The server then incorporates this information to automatically generate a detailed proposal, which specifies specific measures, implementation costs, and expected benefits. The generated proposal is then provided to the user, who can then log in to the system and download or view the proposal.

[0860] The server also activates an emotion recognition engine while the proposal is being viewed, detecting emotions in real time from the user's facial expressions and voice. Based on the user's reactions, the proposal content is adjusted as needed. This emotion recognition engine could utilize OpenCV or Microsoft Azure's emotion recognition API, for example.

[0861] The server stores this emotional data in a database and uses it to generate future suggestions. This allows the system to learn the user's emotional tendencies and provide more appropriate suggestions.

[0862] As a specific example, if a company uploads its ESG report to this system, the report will include annual energy consumption and CO2 emissions. The server will analyze this and extract the current energy consumption and CO2 emissions. The server will then compare this with the database and propose specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. As the proposal is generated and provided to the user, an emotion recognition engine will sense the user's reactions in real time and adjust the proposal as necessary.

[0863] An example of a prompt sentence is, "Please analyze the text of the ESG-related materials below, extract information related to carbon neutrality, and generate recommendations."

[0864] As described above, this system provides companies with the information they need to achieve carbon neutrality and enables them to make more effective proposals based on user emotions.

[0865] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0866] Step 1:

[0867] A user logs into the system. They enter their username and password through a terminal, and once authenticated, the dashboard is displayed. The input is the username and password, and the output is a transition to the user interface.

[0868] Step 2:

[0869] The user moves to the upload screen, selects and uploads their company's securities report or ESG-related document file. The input is a document file (e.g. PDF, DOCX), and the output is sending the file to the server and a notification that the upload is complete. Specifically, the user opens the file selection dialog, selects the file, and clicks the "Upload" button.

[0870] Step 3:

[0871] The terminal sends the selected document file to the server. The input is the document file selected by the user, and the output is the file saved on the server. The specific operation is to send the file to the server using an HTTP POST request.

[0872] Step 4:

[0873] The server automatically identifies the file format of the received document, for example by analyzing the file extension and header information. The input is the uploaded file, and the output is the identified file format (e.g. PDF, DOCX). Specific operations include reading the file header and selecting a reader library.

[0874] Step 5:

[0875] The server starts the analysis engine for the corresponding file format (e.g. PDF analysis engine, DOCX analysis engine) and converts the content into text data. The input is the identified file format and the output is text data. Specifically, it uses libraries such as PyMuPDF or python-docx to read the file content and convert it into a string.

[0876] Step 6:

[0877] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from text data. The input is text data, and the output is specific information such as energy consumption, CO2 emissions, and the percentage of renewable energy used. Specifically, it uses SpaCy and NLTK to extract keywords and phrases of interest.

[0878] Step 7:

[0879] The server compares the extracted information with its internal database. The input is the extracted carbon neutral related information, and the output is related policy information from the database. Specifically, it searches for policy information in the database using SQL queries.

[0880] Step 8:

[0881] The server selects the optimal carbon-neutral measures for the user based on the matching results. The input is the matched database information, and the output is the selected measures. Specifically, the measures are ranked using an optimization algorithm.

[0882] Step 9:

[0883] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). The input is the selected measures, and the output is a detailed draft proposal. Specific operations use a cost calculation engine and an effect prediction model.

[0884] Step 10:

[0885] The server automatically generates a proposal based on the calculated information. The input is the detailed proposal, and the output is the completed proposal. Specific operations involve using a document generation library (e.g., ReportLab).

[0886] Step 11:

[0887] The server provides the generated proposal to the user. The input is the completed proposal, and the output is a format that the user can view or download. Specifically, the server uploads the proposal to a file server and generates a URL.

[0888] Step 12:

[0889] The server starts an emotion recognition engine while the user is viewing the proposal, and detects emotions in real time from the user's facial expressions and voice. The input is the user's facial expression and voice data, and the output is the emotion recognition results. Specific operations utilize OpenCV and Microsoft Azure's emotion recognition API.

[0890] Step 13:

[0891] The server adjusts the proposal content based on the recognized emotion. The input is the emotion recognition result, and the output is the revised proposal. Specifically, the server recalculates and regenerates the proposal content based on the emotion feedback.

[0892] Step 14:

[0893] The server stores the user's emotion data in a database and uses it to generate future suggestions. The input is emotion data, and the output is updated database information. Specifically, the server performs an insert operation into the database.

[0894] (Application example 2)

[0895] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0896] Implementing carbon neutral measures is an important challenge for modern companies. However, many companies do not have the resources to analyze vast amounts of data and select the optimal measures. Furthermore, if the sentiment of managers and employees is not taken into account when a proposal is made, it may be difficult to adopt the proposal. Therefore, a system is needed that can accurately and efficiently propose carbon neutral measures and adjust the content based on the sentiment of the recipients of the proposal.

[0897] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0898] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting the optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for recognizing in real time the emotions of users receiving the proposal using cameras installed in the factory; and means for adjusting the proposal content based on the recognized emotions. This makes it easier for companies to adopt carbon neutral measures efficiently and effectively, and by appropriately adjusting the proposal content, it becomes easier for proposals to be accepted.

[0899] "Corporate Customer" means a company or organization registered as a legal entity or its representatives.

[0900] "Materials" means information in the form of documents or files, including reports and data provided by Corporate Clients.

[0901] "Upload" refers to the act of sending materials from a user's device to a server.

[0902] "Natural language processing technology" refers to computer processing technology for understanding, analyzing, and generating human language.

[0903] "Carbon neutral" refers to a state that aims to balance CO2 emissions and absorption.

[0904] "Extraction" refers to the act of finding and extracting necessary information from materials based on specific conditions.

[0905] A "database" refers to a collection of accumulated data that is stored and managed for a specific purpose.

[0906] "Proposals" refer to reports or plans that recommend optimal carbon-neutral measures to corporate clients based on the extracted information.

[0907] "Implementation costs" refer to the expenses required to actually implement the proposed measures or measures.

[0908] "CO2 reduction" refers to the amount of carbon dioxide that will be reduced as a result of implementing the proposed measures.

[0909] "Return on investment" is an indicator that evaluates the effects and benefits obtained in relation to the capital invested.

[0910] A "proposal" refers to a document that clearly states specific measures, costs, and expected effects.

[0911] "User" refers to a corporate client or its representative who uses the system and receives a proposal.

[0912] "Camera" refers to a device for capturing images or video.

[0913] "Emotion" refers to the user's psychological reaction to the suggestion.

[0914] "Recognition" refers to the act of analyzing captured images and data to determine emotions.

[0915] "Adjustment" refers to the act of changing or adapting suggestions based on the user's feelings.

[0916] This invention is a system that analyzes documents provided by corporate clients and provides optimal proposals related to carbon neutrality. It is designed to implement effective carbon neutral measures, particularly in large-scale facilities such as factories. The system also has the ability to recognize the emotions of users who will receive the proposals in real time and adjust the content of the proposals accordingly.

[0917] Equipment and network configuration used

[0918] The system consists of the following hardware and software components:

[0919] User devices: Includes PCs and mobile devices.

[0920] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[0921] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[0922] Camera: A device installed in the factory that recognizes the emotions of users receiving suggestions in real time.

[0923] Each function of the system is executed by the terminal communicating with the server via the network.

[0924] System flow and specific operations

[0925] Users log in to the system and upload their company's carbon neutrality-related documents. The documents are sent to the server via their device, which automatically identifies the format of the documents and launches an analysis engine. The files are converted into text data, and natural language processing technology is used to extract information related to carbon neutrality.

[0926] The server compares the extracted information with a database and selects the optimal carbon-neutral measures, such as introducing energy-efficient lighting or installing solar panels. The implementation costs, expected CO2 reductions, and return on investment of the selected measures are calculated, and a detailed proposal is generated.

[0927] The generated proposal is provided to the user, who can then access the system to view or download it. During this process, cameras installed in the factory recognize the user's emotions in real time as they receive the proposal, and the emotions are transmitted to the server.

[0928] The server uses the emotion recognition data to adjust the suggestions as needed. For example, if the user expresses a negative emotion, additional information or alternative suggestions may be provided. The emotion data is stored in a database and used to generate future suggestions.

[0929] Specific examples

[0930] For example, when a company uploads its energy consumption report to the system, the server analyzes the content and extracts energy consumption and CO2 emissions. The analysis results are compared with the database and measures such as "introducing energy-efficient equipment" or "installing solar panels" are proposed. The proposals clearly state the specific measures, implementation costs, expected CO2 reductions, and return on investment.

[0931] As the user browses the proposal, a camera captures their facial expressions and analyzes them using an emotion recognition model. For example, if a negative emotion is detected, the server adjusts the proposal to make it more acceptable to the user.

[0932] Example of a prompt statement for raw data processing:

[0933] python

[0934] Obtaining power consumption data

[0935] energy_data = get_energy_data()

[0936] Generate energy-efficient proposals

[0937] proposal = generate_proposal(energy_data)

[0938] Proposal Providing and Emotion Recognition

[0939] sentiment = recognize_emotion()

[0940] if sentiment == "negative":

[0941] proposal = adjust_proposal(proposal)

[0942] This system enables companies to efficiently and effectively select and apply carbon neutral measures, and by taking into account the sentiment of users receiving the proposals, it can improve the acceptance rate of the proposals.

[0943] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0944] Step 1:

[0945] Users log in to the system using their device and upload carbon neutral-related documents. The input is documents such as ESG reports and energy consumption data provided by corporate clients, and the output is the transfer of these documents to the server. Specifically, the user selects the document using the device's file selection function and presses the upload button.

[0946] Step 2:

[0947] The server automatically identifies the format of the uploaded document and converts it to text data. The input is the uploaded document and the output is text data. The server then launches, for example, a PDF parsing engine or a DOCX parsing engine to convert the document to text format.

[0948] Step 3:

[0949] The server uses natural language processing technology to analyze text data and extract information related to carbon neutrality. The input is the text data of the document, and the output is the extracted information related to carbon neutrality. The server uses NLP (natural language processing) technology to extract energy consumption, CO2 emissions, etc.

[0950] Step 4:

[0951] The server compares the extracted information with the database and selects the best carbon-neutral related proposal. The input is the extracted carbon-neutral information and the output is the selected proposal. As part of the matching process, the server matches it with a database entry.

[0952] Step 5:

[0953] The server calculates the implementation cost, expected CO2 reduction, and return on investment of the selected proposal. The input is the selected proposal, and the output is the implementation cost, CO2 reduction, and return on investment. The server calculates these figures using a cost calculation engine.

[0954] Step 6:

[0955] The server generates a proposal that includes the calculation results. The input is data on implementation costs, CO2 reductions, and ROI, and the output is a proposal. Specifically, the server creates a draft proposal using an automatic generation algorithm.

[0956] Step 7:

[0957] The server provides the generated proposal to the user. The input is the generated proposal, and the output is that the user can view or download the proposal. The server creates and notifies the user of a link that the user can access on their device.

[0958] Step 8:

[0959] The camera is installed in the factory and recognizes the emotions of the user receiving the suggestions in real time. The input is the video data from the camera, and the output is the recognized emotion data. The emotion recognition engine analyzes the captured video and identifies the user's emotion.

[0960] Step 9:

[0961] The server then adjusts the suggestions as needed based on the emotion recognition data. The input is the recognized emotion data, and the output is the adjusted suggestions. For example, if the user expresses a negative emotion, the server generates additional explanatory material or alternative suggestions.

[0962] Step 10:

[0963] The server stores the user's emotional data in a database and uses it to generate future suggestions. The input is the emotional data, and the output is the saved data. Storing the emotional data improves the accuracy of future suggestions.

[0964] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0965] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0966] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0967] [Third embodiment]

[0968] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0969] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0970] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0971] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0972] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0973] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0974] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0975] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0976] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0977] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0978] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0979] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0980] The present invention is a system that analyzes materials provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system operates through multiple steps to propose efficient and effective carbon neutral measures to corporate clients.

[0981] Equipment and network configuration used

[0982] The system consists of the following hardware and software components:

[0983] User devices: Includes PCs and mobile devices.

[0984] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[0985] Database: Contains carbon neutral related proposals and measures.

[0986] Each function of this system is executed by the terminal communicating with the server via the network.

[0987] System flow and specific operations

[0988] Uploading materials

[0989] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents.

[0990] The terminal transmits the selected material file to the server.

[0991] Analysis of data

[0992] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file, it uses the PDF processing engine, if it is a DOCX file, it uses the DOCX processing engine.

[0993] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[0994] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[0995] Database Matching

[0996] The server compares the extracted information with the system's database, which contains information on the various policies, technologies, and costs that can be achieved within the carbon neutral range.

[0997] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment, expanding renewable energy sources, or purchasing carbon credits.

[0998] Proposal Generation

[0999] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[1000] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[1001] Providing suggestions

[1002] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[1003] Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[1004] Specific examples

[1005] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the results with the database, proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," and calculates the implementation costs, expected CO2 reductions, and long-term return on investment.

[1006] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the most appropriate measures.

[1007] The processing flow will be explained below.

[1008] Step 1:

[1009] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[1010] Step 2:

[1011] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[1012] Step 3:

[1013] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[1014] Step 4:

[1015] The device sends the selected file to the server, completing the upload of the file.

[1016] Step 5:

[1017] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[1018] Step 6:

[1019] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[1020] Step 7:

[1021] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1022] Step 8:

[1023] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[1024] Step 9:

[1025] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[1026] Step 10:

[1027] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[1028] Step 11:

[1029] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[1030] Step 12:

[1031] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[1032] Step 13:

[1033] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[1034] Example 1

[1035] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1036] Achieving carbon neutrality is an important issue for companies, but selecting the optimal measures and evaluating their cost-effectiveness requires advanced analytical capabilities and a large amount of information. Current systems often rely on manual work to extract and analyze the necessary information, resulting in a lack of efficiency. In addition, the creation of proposals and the incorporation of user feedback are not sufficiently automated, making it difficult to quickly provide optimal proposals. Therefore, a more efficient and automated method is needed.

[1037] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1038] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutrality-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for including charts and visual information when generating the proposal, means for a user to log in and download or view the generated proposal, and means for a user to provide additional feedback or questions through the system. This enables the proposal and evaluation of optimal carbon neutrality measures to be made quickly and efficiently.

[1039] "Corporate Customer" means a corporate customer that uses the system to receive carbon neutral related proposals.

[1040] "Documents" refer to documents such as securities reports and ESG-related materials that corporate clients upload to the system.

[1041] "Means of uploading" refers to the functions and methods by which corporate clients can submit their company materials to the system.

[1042] "Natural language processing technology" is a technology for analyzing text data and extracting meaning and information.

[1043] "Means for extracting information" refers to a method for extracting information related to carbon neutrality from uploaded materials using natural language processing technology.

[1044] A "database matching means" is a method for comparing extracted information with existing information stored in a database.

[1045] "Carbon neutrality-related proposals" are specific policies and measures that companies should take to achieve carbon neutrality.

[1046] "Implementation costs" are the costs required to implement carbon neutral proposals.

[1047] "CO2 reduction" refers to the amount of carbon dioxide reduced by implementing carbon neutral proposals.

[1048] "Return on investment (ROI)" is an indicator obtained by comparing the benefits and effects obtained by implementing carbon neutral proposals with the costs involved.

[1049] The "means for generating a proposal" is a method for automatically creating a document that describes the content of a carbon-neutral proposal, its implementation costs, expected effects, etc.

[1050] The "means for providing a proposal" is a method for distributing the generated proposal to the corporate client.

[1051] "Means for including diagrams and visual information" refers to the ability to insert diagrams, charts, etc. to make the information in the proposal easier to understand visually.

[1052] "Means for downloading or viewing" means a method by which a corporate client obtains or displays a generated proposal via the Internet.

[1053] "Means for providing feedback and questions" is a function that allows corporate customers to submit opinions and questions about proposals within the system.

[1054] The present invention is a system that analyzes documents provided by corporate clients and presents optimal carbon neutral proposals. This system operates using specific hardware and software components to provide efficient and effective carbon neutral proposals to corporate clients.

[1055] The equipment and network configuration used in this system are as follows:

[1056] Hardware and software used

[1057] User devices: Includes PCs and mobile devices.

[1058] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[1059] Database: Contains carbon neutrality-related proposals and measures.

[1060] The terminal communicates with the server via the network to execute the various functions of this system. This system operates as follows.

[1061] Basic system operation

[1062] First, a user logs in to the system using a terminal and selects and uploads their company's securities report and ESG-related documents. The terminal then sends the selected document files to the server, which then processes them.

[1063] The server automatically identifies the file format of the uploaded material. For example, if it is a PDF file, it uses a PDF processing engine (e.g., Apache PDFBox), and if it is a DOCX file, it uses a DOCX processing engine (e.g., Apache POI). The server then invokes the corresponding file format analysis engine and converts the content into text data.

[1064] The server then applies natural language processing (NLP) techniques (e.g., spaCy, NLTK) to extract information related to carbon neutrality from the text data, such as energy consumption, CO2 emissions, and renewable energy usage.

[1065] The extracted information is then compared with the system's database by the server. This database contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the results of the comparison, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[1066] The server designs a detailed plan based on the optimal proposal, calculates its implementation cost, expected CO2 reduction, and return on investment (ROI), and automatically generates a proposal for the reduction plan incorporating this information. This proposal specifies specific measures, costs, and expected effects, and also includes charts and visual information.

[1067] The generated proposal can be downloaded or viewed by the user by logging in to the system. The user can also check the proposal contents using a terminal and provide additional feedback or questions through the system.

[1068] Specific examples

[1069] For example, suppose a company uploads a file called "2023_ESG_Report.pdf" to the system. This file contains information about annual energy consumption and CO2 emissions. The server uses Apache PDFBox to analyze the PDF file and extract the energy consumption and CO2 emissions data as text. It then uses NLP technology such as spaCy to organize this data, compare it with a database, and propose optimal measures.

[1070] Prompt Sentence Examples

[1071] You can ask the generative AI model to explain the system using prompts like the following:

[1072] "Please provide a description of a system that analyzes documents provided by corporate customers and presents optimal carbon-neutral related proposals. This system will include the following steps: uploading documents, analyzing the documents, comparing them with a database, generating proposals, and providing the proposals. Please also provide a detailed description of the specific hardware, software, and analysis engine used."

[1073] In this way, the present invention provides companies with the information they need to achieve carbon neutrality and helps them select the most appropriate measures.

[1074] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1075] Step 1: Upload your materials

[1076] 1. A user logs in to the system using a terminal.

[1077] Input: User ID and password.

[1078] Output: A successful login message to the system.

[1079] Specific operation: "The user accesses the dedicated web application from their own PC and logs in by entering their ID and password."

[1080] 2. The user selects and uploads their company's securities report and ESG-related documents.

[1081] Input: The file to upload.

[1082] Output: File upload successful message.

[1083] Specific operation: "The user clicks the file upload button, selects "2023_ESG_Report.pdf" from the local drive, and uploads it."

[1084] 3. The terminal sends the selected document file to the server.

[1085] Input: Document file.

[1086] Output: Notification that file has been sent to the server.

[1087] Specific operation: "The device uses the API to send a file to the server. At this time, the file's metadata (file name, extension, size) is also sent."

[1088] Step 2: Analyze the data

[1089] 1. The server automatically identifies the file format of the uploaded material.

[1090] Input: Document file.

[1091] Output: File format specific information (e.g. "PDF").

[1092] Specific behavior: "The server checks the file extension, and if it is ".pdf", selects the PDF processing engine."

[1093] 2. The server starts the parsing engine for the appropriate file format and converts the content into text data.

[1094] Input: Document file.

[1095] Output: Text data.

[1096] What it does: "The server uses a PDF processing engine to parse the PDF file and extract text data, such as Chapter 1, "Corporate Energy Consumption," and Chapter 2, "CO2 Emissions."

[1097] 3. The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from the text data.

[1098] Input: Text data.

[1099] Output: Extracted information (energy consumption, CO2 emissions, renewable energy share, etc.).

[1100] Specific operation: "The server uses an NLP library to analyze the extracted text data. Energy consumption, CO2 emissions, and the percentage of renewable energy used are automatically identified and extracted as numerical values."

[1101] Step 3: Check against the database

[1102] 1. The server checks the extracted information against the database in the system.

[1103] Input: Extracted information.

[1104] Output: Matching results (optimal action candidates).

[1105] How it works: "The server queries the database to obtain information about energy-efficient technologies and policies. For example, it applies rules such as, 'If the renewable energy usage rate is less than 10%, then the installation of solar panels is recommended.'"

[1106] 2. Based on the matching results, the server selects the most appropriate carbon-neutral measures for the user.

[1107] Input: Matching result.

[1108] Output: The selected optimal strategy.

[1109] Specific operation: "Based on the matching results, the server creates a list of measures, such as introducing energy-efficient lighting or installing solar panels, and selects the most efficient measure from among them."

[1110] Step 4: Generate proposals

[1111] 1. The server designs a detailed plan based on the optimal proposal and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[1112] Input: The selected optimal measure.

[1113] Output: installation cost, CO2 reduction, ROI.

[1114] Specific operation: "The server uses a spreadsheet or similar to calculate the implementation cost of each measure (e.g., "Implementation of energy-efficient lighting: 3 million yen"), the expected CO2 reduction (e.g., "CO2 reduction of 20 tons per year"), and ROI (e.g., "Payback in 5 years").

[1115] 2. The server incorporates this information and automatically generates a reduction plan proposal.

[1116] Inputs: installation cost, CO2 reduction, ROI.

[1117] Output: Proposed reduction plan.

[1118] Specific operation: "The server creates a proposal using a document template, specifying the details of each measure, implementation costs, and expected effects. The proposal also includes diagrams and charts, and is output in a visually easy-to-understand format."

[1119] Step 5: Provide a proposal

[1120] 1. The server provides the generated proposal to the user.

[1121] Input: Abatement plan proposal.

[1122] Output: A file link or download link for the proposal.

[1123] Specific behavior: "The server converts the generated proposal to PDF format, associates it with the user's account, and generates a download link."

[1124] 2. The user logs into the system and downloads or views the proposal.

[1125] Input: Login information to the system.

[1126] Output: Proposal download or viewing page.

[1127] Specific operation: "The user logs in to the system again and clicks the 'Download Proposal' button on the dashboard to download the proposal."

[1128] 3. Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[1129] Input: Your feedback or question.

[1130] Output: A confirmation that feedback or questions have been submitted.

[1131] Specific behavior: "Users review the proposal and, if necessary, submit additional questions or requests using the feedback form within the system."

[1132] (Application example 1)

[1133] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1134] In today's world, reducing energy consumption and CO2 emissions in factories is an important issue from the perspectives of both environmental protection and cost reduction. However, existing systems that provide carbon-neutral measures lack the functionality to collect energy consumption data for each piece of equipment in real time and visually present optimal measures on the spot, making it difficult for factory workers to make quick decisions. In addition, the process of analyzing data and generating recommendations is not automated, requiring a huge amount of time and effort. Therefore, there is a need to develop a new system that can implement carbon-neutral measures efficiently and effectively.

[1135] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1136] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for collecting energy consumption and CO2 emissions for each piece of equipment in the factory in real time; and means for proposing optimal carbon neutral measures based on the collected data and visually presenting the proposal to factory workers. This not only enables real-time monitoring of energy consumption and CO2 emissions in the factory, but also enables workers to instantly understand carbon neutral measures and make quick decisions.

[1137] "Corporate Customer" means a company or organization that conducts business or commercial activities.

[1138] "Materials" means documents, reports, data files and other information-containing media provided by Corporate Clients.

[1139] "Upload" refers to the act of sending data from a local device to a remote system, such as a server.

[1140] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[1141] "Analysis" refers to the act of understanding the information contained in a material and breaking it down for a specific purpose.

[1142] "Carbon neutral" refers to efforts aimed at reducing greenhouse gas emissions to virtually zero.

[1143] "Information extraction" refers to the process of extracting necessary data from documents.

[1144] A "database" refers to a system that organizes, stores, and manages data based on certain rules.

[1145] A "proposal" refers to the presentation of recommended actions or measures to solve a particular problem.

[1146] "Cost" refers to the expenses required to implement the proposed measures.

[1147] "CO2 reduction" refers to the total amount of carbon dioxide that is expected to be reduced as a result of the measures.

[1148] "Return on investment" refers to an indicator that shows the profit or effect of an investment.

[1149] "Proposal" refers to a document summarizing the proposal.

[1150] "User" refers to any individual or legal entity that uses the System.

[1151] "Real-time" refers to operations and processing that are carried out simultaneously with real time.

[1152] "Equipment" refers to the devices and equipment used within a factory.

[1153] "Visual presentation" refers to displaying information or data in a form that can be perceived by the human eye.

[1154] This invention is a system that analyzes documents provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system collects and analyzes data in real time to generate appropriate proposals to reduce corporate clients' energy consumption and CO2 emissions.

[1155] Equipment and network configuration used

[1156] The system consists of the following hardware and software components:

[1157] User devices: PCs, smart glasses, smartphones, etc.

[1158] Server: A server system for analyzing data, generating proposals, creating reports, etc.

[1159] Database: Carbon neutral related proposals and measures are stored

[1160] System flow and specific operations

[1161] Uploading materials

[1162] The user logs into the system using a terminal, selects and uploads their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[1163] Analysis of data

[1164] The server automatically identifies the file format of the uploaded material. For example, if it's a PDF file, it uses a PDF processing engine, and if it's a DOCX file, it uses a DOCX processing engine. The server then launches an analysis engine for the corresponding file format and converts the content into text data. The server then applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data.

[1165] Database Matching

[1166] The server compares the extracted information with the system's database, which contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the comparison results, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[1167] Proposal Generation

[1168] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). This information is then incorporated to automatically generate a proposal for a reduction plan. This proposal clearly states the specific measures, costs, and expected effects.

[1169] Providing suggestions

[1170] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[1171] Real-time data collection and presentation within the factory

[1172] The system also includes a means to collect real-time energy consumption and CO2 emissions data for each piece of equipment in the factory. This is done using smart glasses and other sensor devices. The collected data is sent to a cloud server, where it is compared with an existing database and optimal carbon-neutral measures are proposed. The proposals are visually presented to factory workers through the smart glasses.

[1173] Hardware and software used

[1174] Hardware: Smart glasses (e.g., Google Glass, Vuzix Blade), PC, smartphone

[1175] Software Libraries:

[1176] TensorFlow: Data analysis and NLP models

[1177] OpenCV: Camera data analysis for smart glasses

[1178] Flask: Receiving data and providing API

[1179] Specific examples

[1180] A manufacturing plant uses smart glasses to collect energy consumption data from equipment in real time. Factory engineers use the glasses to monitor the energy data of each piece of equipment in the plant and confirm the optimal measures provided by the Carbon Neutral Assistant (CNA).

[1181] Prompt Sentence Examples

[1182] "Design a system that uses smart glasses to collect real-time energy consumption data from a manufacturing plant and provide optimal carbon-neutral measures. The system will use natural language processing (NLP) techniques to analyze the data and calculate the return on investment (ROI)."

[1183] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1184] Step 1:

[1185] Uploading materials

[1186] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[1187] Input: User selected material file

[1188] Output: The document file sent to the server

[1189] Step 2:

[1190] Identifying the file format of the material

[1191] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file it will use the PDF processing engine, if it is a DOCX file it will use the DOCX processing engine, etc.

[1192] Input: Uploaded file

[1193] Output: Identified file formats

[1194] Step 3:

[1195] Text conversion of material content

[1196] The server starts the analysis engine for the corresponding file format and converts the content into text data. The PDF processing engine converts PDF to text, and the DOCX processing engine converts DOCX to text.

[1197] Input: Identified file format, material file

[1198] Output: Content converted to text

[1199] Step 4:

[1200] Extraction of carbon neutral related information

[1201] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality (energy consumption, CO2 emissions, etc.) from text data.

[1202] Input: Content converted to text

[1203] Output: Extracted carbon-neutral related information

[1204] Step 5:

[1205] Database Matching

[1206] The server compares the extracted information with the system's database, which includes carbon-neutral measures, technologies, and cost information. The server then selects the optimal carbon-neutral measures based on the comparison results.

[1207] Input: Extracted carbon-neutral related information

[1208] Output: Selected optimal carbon-neutral measures

[1209] Step 6:

[1210] Detailed design of proposal and ROI calculation

[1211] Based on the selected proposal, the server designs a detailed policy plan and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[1212] Input: Selected carbon neutral measures

[1213] Output: installation cost, expected CO2 reduction, return on investment (ROI)

[1214] Step 7:

[1215] Proposal generation

[1216] The server automatically generates a proposal for a reduction plan based on the calculation results, which includes specific measures, costs, and expected effects.

[1217] Input: Implementation cost, expected CO2 reduction, return on investment (ROI)

[1218] Output: Proposal

[1219] Step 8:

[1220] Proposal submission

[1221] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[1222] Input: Proposal

[1223] Output: A proposal that users can download or view

[1224] Step 9:

[1225] Real-time monitoring

[1226] Energy consumption and CO2 emissions from each piece of equipment in the factory are collected in real time using smart glasses and sensor devices, which send the data to a cloud server.

[1227] Input: Energy consumption data and CO2 emission data of factory equipment

[1228] Output: Real-time data sent to cloud server

[1229] Step 10:

[1230] Real-time suggestions

[1231] Based on the collected data, the server compares it with existing databases and generates optimal carbon-neutral measures, which are visually presented to factory workers through smart glasses.

[1232] Input: Real-time data, database

[1233] Output: Carbon neutral measures presented to the worker

[1234] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1235] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[1236] Equipment and network configuration used

[1237] The system consists of the following hardware and software components:

[1238] User devices: Includes PCs and mobile devices.

[1239] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[1240] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[1241] Each function of the system is executed by the terminal communicating with the server via the network.

[1242] System flow and specific operations

[1243] Uploading materials

[1244] Users log in to the system, select their company's securities report and ESG-related documents, and upload them. The upload process is carried out via a terminal.

[1245] The terminal transmits the selected material file to the server, thereby completing the upload of the material.

[1246] Analysis of data

[1247] The server automatically identifies the file format of the uploaded document, for example, if it is a PDF file, it uses the PDF parsing engine, if it is a DOCX file, it uses the DOCX parsing engine.

[1248] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[1249] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1250] Database Matching

[1251] The server compares the extracted information with a built-in database containing information on a wide variety of measures, technologies, and costs that can be achieved within the carbon neutral range.

[1252] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment or expanding renewable energy.

[1253] Proposal Generation

[1254] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[1255] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[1256] Providing suggestions and recognizing user emotions

[1257] The server provides the generated proposal to the user, who can then log into the system to download or view the proposal.

[1258] The server activates an emotion engine to recognize the user's emotions while viewing the proposal, and senses feedback and reactions in real time.

[1259] Processing and using emotional data

[1260] The server processes the user's emotional data collected by the emotion engine and customizes the suggestions as needed, for example by providing additional information or alternative suggestions if the user has a negative reaction to a suggestion.

[1261] The server stores the user's emotional data in a database and uses it when generating future suggestions, allowing for more optimal suggestions.

[1262] Specific examples

[1263] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the report with the database and proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. A proposal is generated and provided to the user, and the emotion engine senses the user's reactions in real time and adjusts the proposal as necessary.

[1264] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the optimal strategy. Furthermore, by recognizing the user's emotions, it is possible to make more effective suggestions.

[1265] The processing flow will be explained below.

[1266] Step 1:

[1267] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[1268] Step 2:

[1269] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[1270] Step 3:

[1271] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[1272] Step 4:

[1273] The device sends the selected file to the server, completing the upload of the file.

[1274] Step 5:

[1275] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[1276] Step 6:

[1277] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[1278] Step 7:

[1279] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the proportion of renewable energy used.

[1280] Step 8:

[1281] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[1282] Step 9:

[1283] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[1284] Step 10:

[1285] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[1286] Step 11:

[1287] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[1288] Step 12:

[1289] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[1290] Step 13:

[1291] The server activates the emotion engine while the user logs in and views the proposal, and senses the user's feedback and reactions in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[1292] Step 14:

[1293] The server determines the user's sentiment based on the data collected from the emotion engine, and if the user responds negatively to the suggestion, it presents additional information or suggests an alternative.

[1294] Step 15:

[1295] The server stores the user's emotion data obtained by the emotion engine in a database, which is used as a reference for future proposal generation.

[1296] Step 16:

[1297] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[1298] Example 2

[1299] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1300] Carbon neutrality measures are an important issue for companies, but collecting appropriate information and creating proposals for this purpose requires a lot of time and effort. Furthermore, because the optimal measures vary from company to company, individual responses are required rather than general-purpose proposals. Furthermore, conventional systems do not adjust proposals to reflect user reactions and emotions, which can lead to proposals not being fully effective.

[1301] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1302] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for recognizing the user's emotions while the user is viewing the proposal, and means for adjusting the proposal content based on the recognized emotions. This enables the server to propose optimal carbon neutral measures for each company and to make effective proposals that reflect the user's emotions.

[1303] "Corporate customers" refer to companies and organizations that receive proposals for carbon neutral measures.

[1304] "Documents" refers to document files to be analyzed provided by corporate clients, including securities reports and ESG-related documents.

[1305] "Means for uploading" refers to the function by which a user uses a terminal to send a document file to a server.

[1306] "Natural language processing technology" refers to language analysis technology for extracting meaningful information from text data, and is particularly a technology for identifying information such as energy consumption and CO2 emissions.

[1307] "Means for extraction" refers to the ability to automatically identify and extract information related to carbon neutrality from materials.

[1308] "Database" refers to a collection of information that stores carbon neutral policies, technologies, cost information, etc.

[1309] "Means of matching" refers to the function of comparing extracted information with information in the database and selecting the most suitable proposal.

[1310] "Selected proposal" refers to the carbon-neutral measure that is deemed optimal for the user, based on the results of comparison with the database.

[1311] "Implementation costs" refers to the costs required to implement the selected proposal.

[1312] "Expected CO2 reduction" refers to the amount of CO2 emissions expected to be reduced if the proposal is implemented.

[1313] "Return on Investment (ROI)" refers to the ratio of benefits to costs obtained by implementing a proposal.

[1314] "Means for generating" refers to the function of creating a proposal based on the selected proposal.

[1315] A "proposal" refers to a document that summarizes the details of the proposal, implementation costs, expected effects, etc.

[1316] "Means for providing" refers to a function that allows users to access the generated proposal.

[1317] "Means for recognizing user emotions" refers to a function that detects emotions from facial expressions and voice while the user is viewing the proposal.

[1318] "Means for adjusting the content of suggestions" refers to a function for changing the content of suggestions based on the recognized user sentiment.

[1319] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[1320] The system consists of the following major hardware and software components:

[1321] User devices: Includes PCs and mobile devices.

[1322] Server: Performs document analysis, proposal generation, report creation, emotion recognition, etc.

[1323] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[1324] Each function of the system is executed by the terminal communicating with the server via the network.

[1325] First, a user logs into the system and selects and uploads their company's securities report or ESG-related document file on the upload screen. At this time, the document is sent from the terminal to the server. The server then automatically identifies the file format of the received document and converts the content into text data using an appropriate analysis engine (e.g., PDF analysis engine or DOCX analysis engine). At this stage, libraries such as PyMuPDF and python-docx are used.

[1326] The server then applies natural language processing (NLP) techniques to extract carbon-neutral information from the converted text data, using libraries such as SpaCy and NLTK to identify energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1327] The extracted information is compared with a database by the server, and the optimal carbon-neutral measures are selected. This database contains pre-registered information on a wide range of measures, technologies, and costs related to carbon neutrality. Specific measures are then proposed to the user. The selected proposals include, for example, the introduction of energy-efficient equipment and the expansion of renewable energy, and the introduction costs, expected CO2 reductions, and return on investment (ROI) for each are calculated.

[1328] The server then incorporates this information to automatically generate a detailed proposal, which specifies specific measures, implementation costs, and expected benefits. The generated proposal is then provided to the user, who can then log in to the system and download or view the proposal.

[1329] The server also activates an emotion recognition engine while the proposal is being viewed, detecting emotions in real time from the user's facial expressions and voice. Based on the user's reactions, the proposal content is adjusted as needed. This emotion recognition engine could utilize OpenCV or Microsoft Azure's emotion recognition API, for example.

[1330] The server stores this emotional data in a database and uses it to generate future suggestions. This allows the system to learn the user's emotional tendencies and provide more appropriate suggestions.

[1331] As a specific example, if a company uploads its ESG report to this system, the report will include annual energy consumption and CO2 emissions. The server will analyze this and extract the current energy consumption and CO2 emissions. The server will then compare this with the database and propose specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. As the proposal is generated and provided to the user, an emotion recognition engine will sense the user's reactions in real time and adjust the proposal as necessary.

[1332] An example of a prompt sentence is, "Please analyze the text of the ESG-related materials below, extract information related to carbon neutrality, and generate recommendations."

[1333] As described above, this system provides companies with the information they need to achieve carbon neutrality and enables them to make more effective proposals based on user emotions.

[1334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1335] Step 1:

[1336] A user logs into the system. They enter their username and password through a terminal, and once authenticated, the dashboard is displayed. The input is the username and password, and the output is a transition to the user interface.

[1337] Step 2:

[1338] The user moves to the upload screen, selects and uploads their company's securities report or ESG-related document file. The input is a document file (e.g. PDF, DOCX), and the output is sending the file to the server and a notification that the upload is complete. Specifically, the user opens the file selection dialog, selects the file, and clicks the "Upload" button.

[1339] Step 3:

[1340] The terminal sends the selected document file to the server. The input is the document file selected by the user, and the output is the file saved on the server. The specific operation is to send the file to the server using an HTTP POST request.

[1341] Step 4:

[1342] The server automatically identifies the file format of the received document, for example by analyzing the file extension and header information. The input is the uploaded file, and the output is the identified file format (e.g. PDF, DOCX). Specific operations include reading the file header and selecting a reader library.

[1343] Step 5:

[1344] The server starts the analysis engine for the corresponding file format (e.g. PDF analysis engine, DOCX analysis engine) and converts the content into text data. The input is the identified file format and the output is text data. Specifically, it uses libraries such as PyMuPDF or python-docx to read the file content and convert it into a string.

[1345] Step 6:

[1346] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from text data. The input is text data, and the output is specific information such as energy consumption, CO2 emissions, and the percentage of renewable energy used. Specifically, it uses SpaCy and NLTK to extract keywords and phrases of interest.

[1347] Step 7:

[1348] The server compares the extracted information with its internal database. The input is the extracted carbon neutral related information, and the output is related policy information from the database. Specifically, it searches for policy information in the database using SQL queries.

[1349] Step 8:

[1350] The server selects the optimal carbon-neutral measures for the user based on the matching results. The input is the matched database information, and the output is the selected measures. Specifically, the measures are ranked using an optimization algorithm.

[1351] Step 9:

[1352] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). The input is the selected measures, and the output is a detailed draft proposal. Specific operations use a cost calculation engine and an effect prediction model.

[1353] Step 10:

[1354] The server automatically generates a proposal based on the calculated information. The input is the detailed proposal, and the output is the completed proposal. Specific operations involve using a document generation library (e.g., ReportLab).

[1355] Step 11:

[1356] The server provides the generated proposal to the user. The input is the completed proposal, and the output is a format that the user can view or download. Specifically, the server uploads the proposal to a file server and generates a URL.

[1357] Step 12:

[1358] The server starts an emotion recognition engine while the user is viewing the proposal, and detects emotions in real time from the user's facial expressions and voice. The input is the user's facial expression and voice data, and the output is the emotion recognition results. Specific operations utilize OpenCV and Microsoft Azure's emotion recognition API.

[1359] Step 13:

[1360] The server adjusts the proposal content based on the recognized emotion. The input is the emotion recognition result, and the output is the revised proposal. Specifically, the server recalculates and regenerates the proposal content based on the emotion feedback.

[1361] Step 14:

[1362] The server stores the user's emotion data in a database and uses it to generate future suggestions. The input is emotion data, and the output is updated database information. Specifically, the server performs an insert operation into the database.

[1363] (Application example 2)

[1364] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1365] Implementing carbon neutral measures is an important challenge for modern companies. However, many companies do not have the resources to analyze vast amounts of data and select the optimal measures. Furthermore, if the sentiment of managers and employees is not taken into account when a proposal is made, it may be difficult to adopt the proposal. Therefore, a system is needed that can accurately and efficiently propose carbon neutral measures and adjust the content based on the sentiment of the recipients of the proposal.

[1366] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1367] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting the optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for recognizing in real time the emotions of users receiving the proposal using cameras installed in the factory; and means for adjusting the proposal content based on the recognized emotions. This makes it easier for companies to adopt carbon neutral measures efficiently and effectively, and by appropriately adjusting the proposal content, it becomes easier for proposals to be accepted.

[1368] "Corporate Customer" means a company or organization registered as a legal entity or its representatives.

[1369] "Materials" means information in the form of documents or files, including reports and data provided by Corporate Clients.

[1370] "Upload" refers to the act of sending materials from a user's device to a server.

[1371] "Natural language processing technology" refers to computer processing technology for understanding, analyzing, and generating human language.

[1372] "Carbon neutral" refers to a state that aims to balance CO2 emissions and absorption.

[1373] "Extraction" refers to the act of finding and extracting necessary information from materials based on specific conditions.

[1374] A "database" refers to a collection of accumulated data that is stored and managed for a specific purpose.

[1375] "Proposals" refer to reports or plans that recommend optimal carbon-neutral measures to corporate clients based on the extracted information.

[1376] "Implementation costs" refer to the expenses required to actually implement the proposed measures or measures.

[1377] "CO2 reduction" refers to the amount of carbon dioxide that will be reduced as a result of implementing the proposed measures.

[1378] "Return on investment" is an indicator that evaluates the effects and benefits obtained in relation to the capital invested.

[1379] A "proposal" refers to a document that clearly states specific measures, costs, and expected effects.

[1380] "User" refers to a corporate client or its representative who uses the system and receives a proposal.

[1381] "Camera" refers to a device for capturing images or video.

[1382] "Emotion" refers to the user's psychological reaction to the suggestion.

[1383] "Recognition" refers to the act of analyzing captured images and data to determine emotions.

[1384] "Adjustment" refers to the act of changing or adapting suggestions based on the user's feelings.

[1385] This invention is a system that analyzes documents provided by corporate clients and provides optimal proposals related to carbon neutrality. It is designed to implement effective carbon neutral measures, particularly in large-scale facilities such as factories. The system also has the ability to recognize the emotions of users who will receive the proposals in real time and adjust the content of the proposals accordingly.

[1386] Equipment and network configuration used

[1387] The system consists of the following hardware and software components:

[1388] User devices: Includes PCs and mobile devices.

[1389] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[1390] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[1391] Camera: A device installed in the factory that recognizes the emotions of users receiving suggestions in real time.

[1392] Each function of the system is executed by the terminal communicating with the server via the network.

[1393] System flow and specific operations

[1394] Users log in to the system and upload their company's carbon neutrality-related documents. The documents are sent to the server via their device, which automatically identifies the format of the documents and launches an analysis engine. The files are converted into text data, and natural language processing technology is used to extract information related to carbon neutrality.

[1395] The server compares the extracted information with a database and selects the optimal carbon-neutral measures, such as introducing energy-efficient lighting or installing solar panels. The implementation costs, expected CO2 reductions, and return on investment of the selected measures are calculated, and a detailed proposal is generated.

[1396] The generated proposal is provided to the user, who can then access the system to view or download it. During this process, cameras installed in the factory recognize the user's emotions in real time as they receive the proposal, and the emotions are transmitted to the server.

[1397] The server uses the emotion recognition data to adjust the suggestions as needed. For example, if the user expresses a negative emotion, additional information or alternative suggestions may be provided. The emotion data is stored in a database and used to generate future suggestions.

[1398] Specific examples

[1399] For example, when a company uploads its energy consumption report to the system, the server analyzes the content and extracts energy consumption and CO2 emissions. The analysis results are compared with the database and measures such as "introducing energy-efficient equipment" or "installing solar panels" are proposed. The proposals clearly state the specific measures, implementation costs, expected CO2 reductions, and return on investment.

[1400] As the user browses the proposal, a camera captures their facial expressions and analyzes them using an emotion recognition model. For example, if a negative emotion is detected, the server adjusts the proposal to make it more acceptable to the user.

[1401] Example of a prompt statement for raw data processing:

[1402] python

[1403] Obtaining power consumption data

[1404] energy_data = get_energy_data()

[1405] Generate energy-efficient proposals

[1406] proposal = generate_proposal(energy_data)

[1407] Proposal Providing and Emotion Recognition

[1408] sentiment = recognize_emotion()

[1409] if sentiment == "negative":

[1410] proposal = adjust_proposal(proposal)

[1411] This system enables companies to efficiently and effectively select and apply carbon neutral measures, and by taking into account the sentiment of users receiving the proposals, it can improve the acceptance rate of the proposals.

[1412] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1413] Step 1:

[1414] Users log in to the system using their device and upload carbon neutral-related documents. The input is documents such as ESG reports and energy consumption data provided by corporate clients, and the output is the transfer of these documents to the server. Specifically, the user selects the document using the device's file selection function and presses the upload button.

[1415] Step 2:

[1416] The server automatically identifies the format of the uploaded document and converts it to text data. The input is the uploaded document and the output is text data. The server then launches, for example, a PDF parsing engine or a DOCX parsing engine to convert the document to text format.

[1417] Step 3:

[1418] The server uses natural language processing technology to analyze text data and extract information related to carbon neutrality. The input is the text data of the document, and the output is the extracted information related to carbon neutrality. The server uses NLP (natural language processing) technology to extract energy consumption, CO2 emissions, etc.

[1419] Step 4:

[1420] The server compares the extracted information with the database and selects the best carbon-neutral related proposal. The input is the extracted carbon-neutral information and the output is the selected proposal. As part of the matching process, the server matches it with a database entry.

[1421] Step 5:

[1422] The server calculates the implementation cost, expected CO2 reduction, and return on investment of the selected proposal. The input is the selected proposal, and the output is the implementation cost, CO2 reduction, and return on investment. The server calculates these figures using a cost calculation engine.

[1423] Step 6:

[1424] The server generates a proposal that includes the calculation results. The input is data on implementation costs, CO2 reductions, and ROI, and the output is a proposal. Specifically, the server creates a draft proposal using an automatic generation algorithm.

[1425] Step 7:

[1426] The server provides the generated proposal to the user. The input is the generated proposal, and the output is that the user can view or download the proposal. The server creates and notifies the user of a link that the user can access on their device.

[1427] Step 8:

[1428] The camera is installed in the factory and recognizes the emotions of the user receiving the suggestions in real time. The input is the video data from the camera, and the output is the recognized emotion data. The emotion recognition engine analyzes the captured video and identifies the user's emotion.

[1429] Step 9:

[1430] The server then adjusts the suggestions as needed based on the emotion recognition data. The input is the recognized emotion data, and the output is the adjusted suggestions. For example, if the user expresses a negative emotion, the server generates additional explanatory material or alternative suggestions.

[1431] Step 10:

[1432] The server stores the user's emotional data in a database and uses it to generate future suggestions. The input is the emotional data, and the output is the saved data. Storing the emotional data improves the accuracy of future suggestions.

[1433] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1434] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1435] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1436] [Fourth embodiment]

[1437] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1438] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1439] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1440] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1441] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1443] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1444] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1445] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1446] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1447] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1448] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1449] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1450] The present invention is a system that analyzes materials provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system operates through multiple steps to propose efficient and effective carbon neutral measures to corporate clients.

[1451] Equipment and network configuration used

[1452] The system consists of the following hardware and software components:

[1453] User devices: Includes PCs and mobile devices.

[1454] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[1455] Database: Contains carbon neutral related proposals and measures.

[1456] Each function of this system is executed by the terminal communicating with the server via the network.

[1457] System flow and specific operations

[1458] Uploading materials

[1459] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents.

[1460] The terminal transmits the selected material file to the server.

[1461] Analysis of data

[1462] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file, it uses the PDF processing engine, if it is a DOCX file, it uses the DOCX processing engine.

[1463] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[1464] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1465] Database Matching

[1466] The server compares the extracted information with the system's database, which contains information on the various policies, technologies, and costs that can be achieved within the carbon neutral range.

[1467] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment, expanding renewable energy sources, or purchasing carbon credits.

[1468] Proposal Generation

[1469] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[1470] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[1471] Providing suggestions

[1472] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[1473] Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[1474] Specific examples

[1475] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the results with the database, proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," and calculates the implementation costs, expected CO2 reductions, and long-term return on investment.

[1476] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the most appropriate measures.

[1477] The processing flow will be explained below.

[1478] Step 1:

[1479] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[1480] Step 2:

[1481] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[1482] Step 3:

[1483] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[1484] Step 4:

[1485] The device sends the selected file to the server, completing the upload of the file.

[1486] Step 5:

[1487] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[1488] Step 6:

[1489] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[1490] Step 7:

[1491] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1492] Step 8:

[1493] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[1494] Step 9:

[1495] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[1496] Step 10:

[1497] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[1498] Step 11:

[1499] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[1500] Step 12:

[1501] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[1502] Step 13:

[1503] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[1504] Example 1

[1505] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1506] Achieving carbon neutrality is an important issue for companies, but selecting the optimal measures and evaluating their cost-effectiveness requires advanced analytical capabilities and a large amount of information. Current systems often rely on manual work to extract and analyze the necessary information, resulting in a lack of efficiency. In addition, the creation of proposals and the incorporation of user feedback are not sufficiently automated, making it difficult to quickly provide optimal proposals. Therefore, a more efficient and automated method is needed.

[1507] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1508] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutrality-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for including charts and visual information when generating the proposal, means for a user to log in and download or view the generated proposal, and means for a user to provide additional feedback or questions through the system. This enables the proposal and evaluation of optimal carbon neutrality measures to be made quickly and efficiently.

[1509] "Corporate Customer" means a corporate customer that uses the system to receive carbon neutral related proposals.

[1510] "Documents" refer to documents such as securities reports and ESG-related materials that corporate clients upload to the system.

[1511] "Means of uploading" refers to the functions and methods by which corporate clients can submit their company materials to the system.

[1512] "Natural language processing technology" is a technology for analyzing text data and extracting meaning and information.

[1513] "Means for extracting information" refers to a method for extracting information related to carbon neutrality from uploaded materials using natural language processing technology.

[1514] A "database matching means" is a method for comparing extracted information with existing information stored in a database.

[1515] "Carbon neutrality-related proposals" are specific policies and measures that companies should take to achieve carbon neutrality.

[1516] "Implementation costs" are the costs required to implement carbon neutral proposals.

[1517] "CO2 reduction" refers to the amount of carbon dioxide reduced by implementing carbon neutral proposals.

[1518] "Return on investment (ROI)" is an indicator obtained by comparing the benefits and effects obtained by implementing carbon neutral proposals with the costs involved.

[1519] The "means for generating a proposal" is a method for automatically creating a document that describes the content of a carbon-neutral proposal, its implementation costs, expected effects, etc.

[1520] The "means for providing a proposal" is a method for distributing the generated proposal to the corporate client.

[1521] "Means for including diagrams and visual information" refers to the ability to insert diagrams, charts, etc. to make the information in the proposal easier to understand visually.

[1522] "Means for downloading or viewing" means a method by which a corporate client obtains or displays a generated proposal via the Internet.

[1523] "Means for providing feedback and questions" is a function that allows corporate customers to submit opinions and questions about proposals within the system.

[1524] The present invention is a system that analyzes documents provided by corporate clients and presents optimal carbon neutral proposals. This system operates using specific hardware and software components to provide efficient and effective carbon neutral proposals to corporate clients.

[1525] The equipment and network configuration used in this system are as follows:

[1526] Hardware and software used

[1527] User devices: Includes PCs and mobile devices.

[1528] Server: A server system for performing data analysis, proposal generation, report creation, etc.

[1529] Database: Contains carbon neutrality-related proposals and measures.

[1530] The terminal communicates with the server via the network to execute the various functions of this system. This system operates as follows.

[1531] Basic system operation

[1532] First, a user logs in to the system using a terminal and selects and uploads their company's securities report and ESG-related documents. The terminal then sends the selected document files to the server, which then processes them.

[1533] The server automatically identifies the file format of the uploaded material. For example, if it is a PDF file, it uses a PDF processing engine (e.g., Apache PDFBox), and if it is a DOCX file, it uses a DOCX processing engine (e.g., Apache POI). The server then invokes the corresponding file format analysis engine and converts the content into text data.

[1534] The server then applies natural language processing (NLP) techniques (e.g., spaCy, NLTK) to extract information related to carbon neutrality from the text data, such as energy consumption, CO2 emissions, and renewable energy usage.

[1535] The extracted information is then compared with the system's database by the server. This database contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the results of the comparison, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[1536] The server designs a detailed plan based on the optimal proposal, calculates its implementation cost, expected CO2 reduction, and return on investment (ROI), and automatically generates a proposal for the reduction plan incorporating this information. This proposal specifies specific measures, costs, and expected effects, and also includes charts and visual information.

[1537] The generated proposal can be downloaded or viewed by the user by logging in to the system. The user can also check the proposal contents using a terminal and provide additional feedback or questions through the system.

[1538] Specific examples

[1539] For example, suppose a company uploads a file called "2023_ESG_Report.pdf" to the system. This file contains information about annual energy consumption and CO2 emissions. The server uses Apache PDFBox to analyze the PDF file and extract the energy consumption and CO2 emissions data as text. It then uses NLP technology such as spaCy to organize this data, compare it with a database, and propose optimal measures.

[1540] Prompt Sentence Examples

[1541] You can ask the generative AI model to explain the system using prompts like the following:

[1542] "Please provide a description of a system that analyzes documents provided by corporate customers and presents optimal carbon-neutral related proposals. This system will include the following steps: uploading documents, analyzing the documents, comparing them with a database, generating proposals, and providing the proposals. Please also provide a detailed description of the specific hardware, software, and analysis engine used."

[1543] In this way, the present invention provides companies with the information they need to achieve carbon neutrality and helps them select the most appropriate measures.

[1544] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1545] Step 1: Upload your materials

[1546] 1. A user logs in to the system using a terminal.

[1547] Input: User ID and password.

[1548] Output: A successful login message to the system.

[1549] Specific operation: "The user accesses the dedicated web application from their own PC and logs in by entering their ID and password."

[1550] 2. The user selects and uploads their company's securities report and ESG-related documents.

[1551] Input: The file to upload.

[1552] Output: File upload successful message.

[1553] Specific operation: "The user clicks the file upload button, selects "2023_ESG_Report.pdf" from the local drive, and uploads it."

[1554] 3. The terminal sends the selected document file to the server.

[1555] Input: Document file.

[1556] Output: Notification that file has been sent to the server.

[1557] Specific operation: "The device uses the API to send a file to the server. At this time, the file's metadata (file name, extension, size) is also sent."

[1558] Step 2: Analyze the data

[1559] 1. The server automatically identifies the file format of the uploaded material.

[1560] Input: Document file.

[1561] Output: File format specific information (e.g. "PDF").

[1562] Specific behavior: "The server checks the file extension, and if it is ".pdf", selects the PDF processing engine."

[1563] 2. The server starts the parsing engine for the appropriate file format and converts the content into text data.

[1564] Input: Document file.

[1565] Output: Text data.

[1566] What it does: "The server uses a PDF processing engine to parse the PDF file and extract text data, such as Chapter 1, "Corporate Energy Consumption," and Chapter 2, "CO2 Emissions."

[1567] 3. The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from the text data.

[1568] Input: Text data.

[1569] Output: Extracted information (energy consumption, CO2 emissions, renewable energy share, etc.).

[1570] Specific operation: "The server uses an NLP library to analyze the extracted text data. Energy consumption, CO2 emissions, and the percentage of renewable energy used are automatically identified and extracted as numerical values."

[1571] Step 3: Check against the database

[1572] 1. The server checks the extracted information against the database in the system.

[1573] Input: Extracted information.

[1574] Output: Matching results (optimal action candidates).

[1575] How it works: "The server queries the database to obtain information about energy-efficient technologies and policies. For example, it applies rules such as, 'If the renewable energy usage rate is less than 10%, then the installation of solar panels is recommended.'"

[1576] 2. Based on the matching results, the server selects the most appropriate carbon-neutral measures for the user.

[1577] Input: Matching result.

[1578] Output: The selected optimal strategy.

[1579] Specific operation: "Based on the matching results, the server creates a list of measures, such as introducing energy-efficient lighting or installing solar panels, and selects the most efficient measure from among them."

[1580] Step 4: Generate proposals

[1581] 1. The server designs a detailed plan based on the optimal proposal and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[1582] Input: The selected optimal measure.

[1583] Output: installation cost, CO2 reduction, ROI.

[1584] Specific operation: "The server uses a spreadsheet or similar to calculate the implementation cost of each measure (e.g., "Implementation of energy-efficient lighting: 3 million yen"), the expected CO2 reduction (e.g., "CO2 reduction of 20 tons per year"), and ROI (e.g., "Payback in 5 years").

[1585] 2. The server incorporates this information and automatically generates a reduction plan proposal.

[1586] Inputs: installation cost, CO2 reduction, ROI.

[1587] Output: Proposed reduction plan.

[1588] Specific operation: "The server creates a proposal using a document template, specifying the details of each measure, implementation costs, and expected effects. The proposal also includes diagrams and charts, and is output in a visually easy-to-understand format."

[1589] Step 5: Provide a proposal

[1590] 1. The server provides the generated proposal to the user.

[1591] Input: Abatement plan proposal.

[1592] Output: A file link or download link for the proposal.

[1593] Specific behavior: "The server converts the generated proposal to PDF format, associates it with the user's account, and generates a download link."

[1594] 2. The user logs into the system and downloads or views the proposal.

[1595] Input: Login information to the system.

[1596] Output: Proposal download or viewing page.

[1597] Specific operation: "The user logs in to the system again and clicks the 'Download Proposal' button on the dashboard to download the proposal."

[1598] 3. Users can use their devices to review the suggestions and provide additional feedback or questions through the system.

[1599] Input: Your feedback or question.

[1600] Output: A confirmation that feedback or questions have been submitted.

[1601] Specific behavior: "Users review the proposal and, if necessary, submit additional questions or requests using the feedback form within the system."

[1602] (Application example 1)

[1603] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1604] In today's world, reducing energy consumption and CO2 emissions in factories is an important issue from the perspectives of both environmental protection and cost reduction. However, existing systems that provide carbon-neutral measures lack the functionality to collect energy consumption data for each piece of equipment in real time and visually present optimal measures on the spot, making it difficult for factory workers to make quick decisions. In addition, the process of analyzing data and generating recommendations is not automated, requiring a huge amount of time and effort. Therefore, there is a need to develop a new system that can implement carbon-neutral measures efficiently and effectively.

[1605] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1606] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for collecting energy consumption and CO2 emissions for each piece of equipment in the factory in real time; and means for proposing optimal carbon neutral measures based on the collected data and visually presenting the proposal to factory workers. This not only enables real-time monitoring of energy consumption and CO2 emissions in the factory, but also enables workers to instantly understand carbon neutral measures and make quick decisions.

[1607] "Corporate Customer" means a company or organization that conducts business or commercial activities.

[1608] "Materials" means documents, reports, data files and other information-containing media provided by Corporate Clients.

[1609] "Upload" refers to the act of sending data from a local device to a remote system, such as a server.

[1610] "Natural language processing technology" refers to the technology that allows computers to understand and analyze human language.

[1611] "Analysis" refers to the act of understanding the information contained in a material and breaking it down for a specific purpose.

[1612] "Carbon neutral" refers to efforts aimed at reducing greenhouse gas emissions to virtually zero.

[1613] "Information extraction" refers to the process of extracting necessary data from documents.

[1614] A "database" refers to a system that organizes, stores, and manages data based on certain rules.

[1615] A "proposal" refers to the presentation of recommended actions or measures to solve a particular problem.

[1616] "Cost" refers to the expenses required to implement the proposed measures.

[1617] "CO2 reduction" refers to the total amount of carbon dioxide that is expected to be reduced as a result of the measures.

[1618] "Return on investment" refers to an indicator that shows the profit or effect of an investment.

[1619] "Proposal" refers to a document summarizing the proposal.

[1620] "User" refers to any individual or legal entity that uses the System.

[1621] "Real-time" refers to operations and processing that are carried out simultaneously with real time.

[1622] "Equipment" refers to the devices and equipment used within a factory.

[1623] "Visual presentation" refers to displaying information or data in a form that can be perceived by the human eye.

[1624] This invention is a system that analyzes documents provided by corporate clients, presents optimal carbon neutral proposals, and calculates their cost-effectiveness. This system collects and analyzes data in real time to generate appropriate proposals to reduce corporate clients' energy consumption and CO2 emissions.

[1625] Equipment and network configuration used

[1626] The system consists of the following hardware and software components:

[1627] User devices: PCs, smart glasses, smartphones, etc.

[1628] Server: A server system for analyzing data, generating proposals, creating reports, etc.

[1629] Database: Carbon neutral related proposals and measures are stored

[1630] System flow and specific operations

[1631] Uploading materials

[1632] The user logs into the system using a terminal, selects and uploads their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[1633] Analysis of data

[1634] The server automatically identifies the file format of the uploaded material. For example, if it's a PDF file, it uses a PDF processing engine, and if it's a DOCX file, it uses a DOCX processing engine. The server then launches an analysis engine for the corresponding file format and converts the content into text data. The server then applies natural language processing (NLP) technology to extract information related to carbon neutrality from the text data.

[1635] Database Matching

[1636] The server compares the extracted information with the system's database, which contains information on a wide variety of measures, technologies, and costs that can be taken within the scope of carbon neutrality. Based on the comparison results, the server selects the most appropriate carbon neutral measure for the user. Examples include the introduction of energy-efficient equipment, the expansion of renewable energy, and the purchase of carbon credits.

[1637] Proposal Generation

[1638] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). This information is then incorporated to automatically generate a proposal for a reduction plan. This proposal clearly states the specific measures, costs, and expected effects.

[1639] Providing suggestions

[1640] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[1641] Real-time data collection and presentation within the factory

[1642] The system also includes a means to collect real-time energy consumption and CO2 emissions data for each piece of equipment in the factory. This is done using smart glasses and other sensor devices. The collected data is sent to a cloud server, where it is compared with an existing database and optimal carbon-neutral measures are proposed. The proposals are visually presented to factory workers through the smart glasses.

[1643] Hardware and software used

[1644] Hardware: Smart glasses (e.g., Google Glass, Vuzix Blade), PC, smartphone

[1645] Software Libraries:

[1646] TensorFlow: Data analysis and NLP models

[1647] OpenCV: Camera data analysis for smart glasses

[1648] Flask: Receiving data and providing API

[1649] Specific examples

[1650] A manufacturing plant uses smart glasses to collect energy consumption data from equipment in real time. Factory engineers use the glasses to monitor the energy data of each piece of equipment in the plant and confirm the optimal measures provided by the Carbon Neutral Assistant (CNA).

[1651] Prompt Sentence Examples

[1652] "Design a system that uses smart glasses to collect real-time energy consumption data from a manufacturing plant and provide optimal carbon-neutral measures. The system will use natural language processing (NLP) techniques to analyze the data and calculate the return on investment (ROI)."

[1653] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1654] Step 1:

[1655] Uploading materials

[1656] Users log in to the system using a terminal, select and upload their company's securities report and ESG-related documents, and the terminal sends the selected document files to the server.

[1657] Input: User selected material file

[1658] Output: The document file sent to the server

[1659] Step 2:

[1660] Identifying the file format of the material

[1661] The server automatically identifies the file format of the uploaded material, for example, if it is a PDF file it will use the PDF processing engine, if it is a DOCX file it will use the DOCX processing engine, etc.

[1662] Input: Uploaded file

[1663] Output: Identified file formats

[1664] Step 3:

[1665] Text conversion of material content

[1666] The server starts the analysis engine for the corresponding file format and converts the content into text data. The PDF processing engine converts PDF to text, and the DOCX processing engine converts DOCX to text.

[1667] Input: Identified file format, material file

[1668] Output: Content converted to text

[1669] Step 4:

[1670] Extraction of carbon neutral related information

[1671] The server applies natural language processing (NLP) technology to extract information related to carbon neutrality (energy consumption, CO2 emissions, etc.) from text data.

[1672] Input: Content converted to text

[1673] Output: Extracted carbon-neutral related information

[1674] Step 5:

[1675] Database Matching

[1676] The server compares the extracted information with the system's database, which includes carbon-neutral measures, technologies, and cost information. The server then selects the optimal carbon-neutral measures based on the comparison results.

[1677] Input: Extracted carbon-neutral related information

[1678] Output: Selected optimal carbon-neutral measures

[1679] Step 6:

[1680] Detailed design of proposal and ROI calculation

[1681] Based on the selected proposal, the server designs a detailed policy plan and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI).

[1682] Input: Selected carbon neutral measures

[1683] Output: installation cost, expected CO2 reduction, return on investment (ROI)

[1684] Step 7:

[1685] Proposal generation

[1686] The server automatically generates a proposal for a reduction plan based on the calculation results, which includes specific measures, costs, and expected effects.

[1687] Input: Implementation cost, expected CO2 reduction, return on investment (ROI)

[1688] Output: Proposal

[1689] Step 8:

[1690] Proposal submission

[1691] The server provides the generated proposal to the user, who can then log in to the system to download or view the proposal.

[1692] Input: Proposal

[1693] Output: A proposal that users can download or view

[1694] Step 9:

[1695] Real-time monitoring

[1696] Energy consumption and CO2 emissions from each piece of equipment in the factory are collected in real time using smart glasses and sensor devices, which send the data to a cloud server.

[1697] Input: Energy consumption data and CO2 emission data of factory equipment

[1698] Output: Real-time data sent to cloud server

[1699] Step 10:

[1700] Real-time suggestions

[1701] Based on the collected data, the server compares it with existing databases and generates optimal carbon-neutral measures, which are visually presented to factory workers through smart glasses.

[1702] Input: Real-time data, database

[1703] Output: Carbon neutral measures presented to the worker

[1704] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1705] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[1706] Equipment and network configuration used

[1707] The system consists of the following hardware and software components:

[1708] User devices: Includes PCs and mobile devices.

[1709] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[1710] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[1711] Each function of the system is executed by the terminal communicating with the server via the network.

[1712] System flow and specific operations

[1713] Uploading materials

[1714] Users log in to the system, select their company's securities report and ESG-related documents, and upload them. The upload process is carried out via a terminal.

[1715] The terminal transmits the selected material file to the server, thereby completing the upload of the material.

[1716] Analysis of data

[1717] The server automatically identifies the file format of the uploaded document, for example, if it is a PDF file, it uses the PDF parsing engine, if it is a DOCX file, it uses the DOCX parsing engine.

[1718] The server starts the parsing engine for the appropriate file format and converts the content into text data.

[1719] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality, including energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1720] Database Matching

[1721] The server compares the extracted information with a built-in database containing information on a wide variety of measures, technologies, and costs that can be achieved within the carbon neutral range.

[1722] Based on the results of the comparison, the server selects the most appropriate carbon-neutral measures for the user, such as introducing energy-efficient equipment or expanding renewable energy.

[1723] Proposal Generation

[1724] The server designs a detailed plan based on the optimal proposal and calculates the implementation cost, expected CO2 reduction, and return on investment (ROI).

[1725] The server incorporates this information and automatically generates a proposal for a reduction plan, which clearly specifies specific measures, costs, and expected benefits.

[1726] Providing suggestions and recognizing user emotions

[1727] The server provides the generated proposal to the user, who can then log into the system to download or view the proposal.

[1728] The server activates an emotion engine to recognize the user's emotions while viewing the proposal, and senses feedback and reactions in real time.

[1729] Processing and using emotional data

[1730] The server processes the user's emotional data collected by the emotion engine and customizes the suggestions as needed, for example by providing additional information or alternative suggestions if the user has a negative reaction to a suggestion.

[1731] The server stores the user's emotional data in a database and uses it when generating future suggestions, allowing for more optimal suggestions.

[1732] Specific examples

[1733] For example, suppose a company uploads its ESG report to the system. This ESG report includes annual energy consumption and CO2 emissions. The server analyzes it and extracts the current energy consumption and CO2 emissions. The server then compares the report with the database and proposes specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. A proposal is generated and provided to the user, and the emotion engine senses the user's reactions in real time and adjusts the proposal as necessary.

[1734] In this way, this system provides companies with the information they need to achieve carbon neutrality and helps them choose the optimal strategy. Furthermore, by recognizing the user's emotions, it is possible to make more effective suggestions.

[1735] The processing flow will be explained below.

[1736] Step 1:

[1737] A user logs in to the system. The user uses a terminal to enter account information (user ID and password) and sends it to the server.

[1738] Step 2:

[1739] The server verifies the received account information and authenticates the user. If authentication is successful, the user is presented with a dashboard.

[1740] Step 3:

[1741] Users select the documents they want to upload (securities reports or ESG-related documents) and click the upload button. These documents are generally in PDF or DOCX format.

[1742] Step 4:

[1743] The device sends the selected file to the server, completing the upload of the file.

[1744] Step 5:

[1745] The server identifies the format of the uploaded document, for example by checking the file extension and invoking the PDF parsing engine if it is a PDF, or the DOCX parsing engine if it is a DOCX.

[1746] Step 6:

[1747] The server uses a file format reading engine to convert the content into text data, sometimes using OCR technology.

[1748] Step 7:

[1749] The server then applies natural language processing (NLP) technology to the converted text data to extract information related to carbon neutrality, such as energy consumption, CO2 emissions, and the proportion of renewable energy used.

[1750] Step 8:

[1751] The server compares the extracted information with a built-in database that lists specific measures and technologies for achieving carbon neutrality.

[1752] Step 9:

[1753] The server then selects the optimal carbon neutral measures based on the results of the comparison, such as introducing energy-efficient equipment, expanding renewable energy sources, and purchasing carbon credits.

[1754] Step 10:

[1755] The server will design a detailed proposal for the selected measures and calculate their implementation costs, expected CO2 reductions, and return on investment (ROI).

[1756] Step 11:

[1757] The server automatically generates a proposal based on the calculation results, which includes specific measures, implementation costs, and expected benefits.

[1758] Step 12:

[1759] The server sends a notification to the user to provide the generated proposal to the user, who can then log in and download or view the proposal.

[1760] Step 13:

[1761] The server activates the emotion engine while the user logs in and views the proposal, and senses the user's feedback and reactions in real time. The emotion engine uses a camera and microphone to analyze the user's facial expressions and tone of voice.

[1762] Step 14:

[1763] The server determines the user's sentiment based on the data collected from the emotion engine, and if the user responds negatively to the suggestion, it presents additional information or suggests an alternative.

[1764] Step 15:

[1765] The server stores the user's emotion data obtained by the emotion engine in a database, which is used as a reference for future proposal generation.

[1766] Step 16:

[1767] Users log in to the system using their terminals, download the provided proposals, and check them online. Decisions within the company are made based on the proposals.

[1768] Example 2

[1769] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1770] Carbon neutrality measures are an important issue for companies, but collecting appropriate information and creating proposals for this purpose requires a lot of time and effort. Furthermore, because the optimal measures vary from company to company, individual responses are required rather than general-purpose proposals. Furthermore, conventional systems do not adjust proposals to reflect user reactions and emotions, which can lead to proposals not being fully effective.

[1771] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1772] In this invention, the server includes means for uploading materials provided by corporate clients, means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality, means for comparing the extracted information with a database and selecting an optimal carbon neutral-related proposal, means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal, means for generating a proposal including the calculation results, means for providing the generated proposal to a user, means for recognizing the user's emotions while the user is viewing the proposal, and means for adjusting the proposal content based on the recognized emotions. This enables the server to propose optimal carbon neutral measures for each company and to make effective proposals that reflect the user's emotions.

[1773] "Corporate customers" refer to companies and organizations that receive proposals for carbon neutral measures.

[1774] "Documents" refers to document files to be analyzed provided by corporate clients, including securities reports and ESG-related documents.

[1775] "Means for uploading" refers to the function by which a user uses a terminal to send a document file to a server.

[1776] "Natural language processing technology" refers to language analysis technology for extracting meaningful information from text data, and is particularly a technology for identifying information such as energy consumption and CO2 emissions.

[1777] "Means for extraction" refers to the ability to automatically identify and extract information related to carbon neutrality from materials.

[1778] "Database" refers to a collection of information that stores carbon neutral policies, technologies, cost information, etc.

[1779] "Means of matching" refers to the function of comparing extracted information with information in the database and selecting the most suitable proposal.

[1780] "Selected proposal" refers to the carbon-neutral measure that is deemed optimal for the user, based on the results of comparison with the database.

[1781] "Implementation costs" refers to the costs required to implement the selected proposal.

[1782] "Expected CO2 reduction" refers to the amount of CO2 emissions expected to be reduced if the proposal is implemented.

[1783] "Return on Investment (ROI)" refers to the ratio of benefits to costs obtained by implementing a proposal.

[1784] "Means for generating" refers to the function of creating a proposal based on the selected proposal.

[1785] A "proposal" refers to a document that summarizes the details of the proposal, implementation costs, expected effects, etc.

[1786] "Means for providing" refers to a function that allows users to access the generated proposal.

[1787] "Means for recognizing user emotions" refers to a function that detects emotions from facial expressions and voice while the user is viewing the proposal.

[1788] "Means for adjusting the content of suggestions" refers to a function for changing the content of suggestions based on the recognized user sentiment.

[1789] The present invention is a system that analyzes materials provided by corporate clients, extracts information related to carbon neutrality, makes optimal proposals, and further recognizes and utilizes user sentiment regarding these proposals, enabling more effective proposals. This system operates through multiple steps to make efficient and effective carbon neutrality proposals to corporate clients.

[1790] The system consists of the following major hardware and software components:

[1791] User devices: Includes PCs and mobile devices.

[1792] Server: Performs document analysis, proposal generation, report creation, emotion recognition, etc.

[1793] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[1794] Each function of the system is executed by the terminal communicating with the server via the network.

[1795] First, a user logs into the system and selects and uploads their company's securities report or ESG-related document file on the upload screen. At this time, the document is sent from the terminal to the server. The server then automatically identifies the file format of the received document and converts the content into text data using an appropriate analysis engine (e.g., PDF analysis engine or DOCX analysis engine). At this stage, libraries such as PyMuPDF and python-docx are used.

[1796] The server then applies natural language processing (NLP) techniques to extract carbon-neutral information from the converted text data, using libraries such as SpaCy and NLTK to identify energy consumption, CO2 emissions, and the percentage of renewable energy used.

[1797] The extracted information is compared with a database by the server, and the optimal carbon-neutral measures are selected. This database contains pre-registered information on a wide range of measures, technologies, and costs related to carbon neutrality. Specific measures are then proposed to the user. The selected proposals include, for example, the introduction of energy-efficient equipment and the expansion of renewable energy, and the introduction costs, expected CO2 reductions, and return on investment (ROI) for each are calculated.

[1798] The server then incorporates this information to automatically generate a detailed proposal, which specifies specific measures, implementation costs, and expected benefits. The generated proposal is then provided to the user, who can then log in to the system and download or view the proposal.

[1799] The server also activates an emotion recognition engine while the proposal is being viewed, detecting emotions in real time from the user's facial expressions and voice. Based on the user's reactions, the proposal content is adjusted as needed. This emotion recognition engine could utilize OpenCV or Microsoft Azure's emotion recognition API, for example.

[1800] The server stores this emotional data in a database and uses it to generate future suggestions. This allows the system to learn the user's emotional tendencies and provide more appropriate suggestions.

[1801] As a specific example, if a company uploads its ESG report to this system, the report will include annual energy consumption and CO2 emissions. The server will analyze this and extract the current energy consumption and CO2 emissions. The server will then compare this with the database and propose specific measures such as "introducing energy-efficient lighting" or "installing solar panels," calculating the implementation costs, expected CO2 reductions, and long-term return on investment. As the proposal is generated and provided to the user, an emotion recognition engine will sense the user's reactions in real time and adjust the proposal as necessary.

[1802] An example of a prompt sentence is, "Please analyze the text of the ESG-related materials below, extract information related to carbon neutrality, and generate recommendations."

[1803] As described above, this system provides companies with the information they need to achieve carbon neutrality and enables them to make more effective proposals based on user emotions.

[1804] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1805] Step 1:

[1806] A user logs into the system. They enter their username and password through a terminal, and once authenticated, the dashboard is displayed. The input is the username and password, and the output is a transition to the user interface.

[1807] Step 2:

[1808] The user moves to the upload screen, selects and uploads their company's securities report or ESG-related document file. The input is a document file (e.g. PDF, DOCX), and the output is sending the file to the server and a notification that the upload is complete. Specifically, the user opens the file selection dialog, selects the file, and clicks the "Upload" button.

[1809] Step 3:

[1810] The terminal sends the selected document file to the server. The input is the document file selected by the user, and the output is the file saved on the server. The specific operation is to send the file to the server using an HTTP POST request.

[1811] Step 4:

[1812] The server automatically identifies the file format of the received document, for example by analyzing the file extension and header information. The input is the uploaded file, and the output is the identified file format (e.g. PDF, DOCX). Specific operations include reading the file header and selecting a reader library.

[1813] Step 5:

[1814] The server starts the analysis engine for the corresponding file format (e.g. PDF analysis engine, DOCX analysis engine) and converts the content into text data. The input is the identified file format and the output is text data. Specifically, it uses libraries such as PyMuPDF or python-docx to read the file content and convert it into a string.

[1815] Step 6:

[1816] The server applies natural language processing (NLP) techniques to extract information related to carbon neutrality from text data. The input is text data, and the output is specific information such as energy consumption, CO2 emissions, and the percentage of renewable energy used. Specifically, it uses SpaCy and NLTK to extract keywords and phrases of interest.

[1817] Step 7:

[1818] The server compares the extracted information with its internal database. The input is the extracted carbon neutral related information, and the output is related policy information from the database. Specifically, it searches for policy information in the database using SQL queries.

[1819] Step 8:

[1820] The server selects the optimal carbon-neutral measures for the user based on the matching results. The input is the matched database information, and the output is the selected measures. Specifically, the measures are ranked using an optimization algorithm.

[1821] Step 9:

[1822] The server designs a detailed plan based on the optimal proposal, and calculates its implementation cost, expected CO2 reduction, and return on investment (ROI). The input is the selected measures, and the output is a detailed draft proposal. Specific operations use a cost calculation engine and an effect prediction model.

[1823] Step 10:

[1824] The server automatically generates a proposal based on the calculated information. The input is the detailed proposal, and the output is the completed proposal. Specific operations involve using a document generation library (e.g., ReportLab).

[1825] Step 11:

[1826] The server provides the generated proposal to the user. The input is the completed proposal, and the output is a format that the user can view or download. Specifically, the server uploads the proposal to a file server and generates a URL.

[1827] Step 12:

[1828] The server starts an emotion recognition engine while the user is viewing the proposal, and detects emotions in real time from the user's facial expressions and voice. The input is the user's facial expression and voice data, and the output is the emotion recognition results. Specific operations utilize OpenCV and Microsoft Azure's emotion recognition API.

[1829] Step 13:

[1830] The server adjusts the proposal content based on the recognized emotion. The input is the emotion recognition result, and the output is the revised proposal. Specifically, the server recalculates and regenerates the proposal content based on the emotion feedback.

[1831] Step 14:

[1832] The server stores the user's emotion data in a database and uses it to generate future suggestions. The input is emotion data, and the output is updated database information. Specifically, the server performs an insert operation into the database.

[1833] (Application example 2)

[1834] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1835] Implementing carbon neutral measures is an important challenge for modern companies. However, many companies do not have the resources to analyze vast amounts of data and select the optimal measures. Furthermore, if the sentiment of managers and employees is not taken into account when a proposal is made, it may be difficult to adopt the proposal. Therefore, a system is needed that can accurately and efficiently propose carbon neutral measures and adjust the content based on the sentiment of the recipients of the proposal.

[1836] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1837] In this invention, the server includes: means for uploading materials provided by corporate clients; means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; means for comparing the extracted information with a database and selecting the optimal carbon neutral-related proposal; means for calculating the implementation cost, expected CO2 reduction, and return on investment of the selected proposal; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; means for recognizing in real time the emotions of users receiving the proposal using cameras installed in the factory; and means for adjusting the proposal content based on the recognized emotions. This makes it easier for companies to adopt carbon neutral measures efficiently and effectively, and by appropriately adjusting the proposal content, it becomes easier for proposals to be accepted.

[1838] "Corporate Customer" means a company or organization registered as a legal entity or its representatives.

[1839] "Materials" means information in the form of documents or files, including reports and data provided by Corporate Clients.

[1840] "Upload" refers to the act of sending materials from a user's device to a server.

[1841] "Natural language processing technology" refers to computer processing technology for understanding, analyzing, and generating human language.

[1842] "Carbon neutral" refers to a state that aims to balance CO2 emissions and absorption.

[1843] "Extraction" refers to the act of finding and extracting necessary information from materials based on specific conditions.

[1844] A "database" refers to a collection of accumulated data that is stored and managed for a specific purpose.

[1845] "Proposals" refer to reports or plans that recommend optimal carbon-neutral measures to corporate clients based on the extracted information.

[1846] "Implementation costs" refer to the expenses required to actually implement the proposed measures or measures.

[1847] "CO2 reduction" refers to the amount of carbon dioxide that will be reduced as a result of implementing the proposed measures.

[1848] "Return on investment" is an indicator that evaluates the effects and benefits obtained in relation to the capital invested.

[1849] A "proposal" refers to a document that clearly states specific measures, costs, and expected effects.

[1850] "User" refers to a corporate client or its representative who uses the system and receives a proposal.

[1851] "Camera" refers to a device for capturing images or video.

[1852] "Emotion" refers to the user's psychological reaction to the suggestion.

[1853] "Recognition" refers to the act of analyzing captured images and data to determine emotions.

[1854] "Adjustment" refers to the act of changing or adapting suggestions based on the user's feelings.

[1855] This invention is a system that analyzes documents provided by corporate clients and provides optimal proposals related to carbon neutrality. It is designed to implement effective carbon neutral measures, particularly in large-scale facilities such as factories. The system also has the ability to recognize the emotions of users who will receive the proposals in real time and adjust the content of the proposals accordingly.

[1856] Equipment and network configuration used

[1857] The system consists of the following hardware and software components:

[1858] User devices: Includes PCs and mobile devices.

[1859] Server: A server system for performing document analysis, proposal generation, report creation, emotion recognition, etc.

[1860] Database: Carbon neutral-related proposals and measures, as well as user sentiment data, are stored.

[1861] Camera: A device installed in the factory that recognizes the emotions of users receiving suggestions in real time.

[1862] Each function of the system is executed by the terminal communicating with the server via the network.

[1863] System flow and specific operations

[1864] Users log in to the system and upload their company's carbon neutrality-related documents. The documents are sent to the server via their device, which automatically identifies the format of the documents and launches an analysis engine. The files are converted into text data, and natural language processing technology is used to extract information related to carbon neutrality.

[1865] The server compares the extracted information with a database and selects the optimal carbon-neutral measures, such as introducing energy-efficient lighting or installing solar panels. The implementation costs, expected CO2 reductions, and return on investment of the selected measures are calculated, and a detailed proposal is generated.

[1866] The generated proposal is provided to the user, who can then access the system to view or download it. During this process, cameras installed in the factory recognize the user's emotions in real time as they receive the proposal, and the emotions are transmitted to the server.

[1867] The server uses the emotion recognition data to adjust the suggestions as needed. For example, if the user expresses a negative emotion, additional information or alternative suggestions may be provided. The emotion data is stored in a database and used to generate future suggestions.

[1868] Specific examples

[1869] For example, when a company uploads its energy consumption report to the system, the server analyzes the content and extracts energy consumption and CO2 emissions. The analysis results are compared with the database and measures such as "introducing energy-efficient equipment" or "installing solar panels" are proposed. The proposals clearly state the specific measures, implementation costs, expected CO2 reductions, and return on investment.

[1870] As the user browses the proposal, a camera captures their facial expressions and analyzes them using an emotion recognition model. For example, if a negative emotion is detected, the server adjusts the proposal to make it more acceptable to the user.

[1871] Example of a prompt statement for raw data processing:

[1872] python

[1873] Obtaining power consumption data

[1874] energy_data = get_energy_data()

[1875] Generate energy-efficient proposals

[1876] proposal = generate_proposal(energy_data)

[1877] Proposal Providing and Emotion Recognition

[1878] sentiment = recognize_emotion()

[1879] if sentiment == "negative":

[1880] proposal = adjust_proposal(proposal)

[1881] This system enables companies to efficiently and effectively select and apply carbon neutral measures, and by taking into account the sentiment of users receiving the proposals, it can improve the acceptance rate of the proposals.

[1882] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1883] Step 1:

[1884] Users log in to the system using their device and upload carbon neutral-related documents. The input is documents such as ESG reports and energy consumption data provided by corporate clients, and the output is the transfer of these documents to the server. Specifically, the user selects the document using the device's file selection function and presses the upload button.

[1885] Step 2:

[1886] The server automatically identifies the format of the uploaded document and converts it to text data. The input is the uploaded document and the output is text data. The server then launches, for example, a PDF parsing engine or a DOCX parsing engine to convert the document to text format.

[1887] Step 3:

[1888] The server uses natural language processing technology to analyze text data and extract information related to carbon neutrality. The input is the text data of the document, and the output is the extracted information related to carbon neutrality. The server uses NLP (natural language processing) technology to extract energy consumption, CO2 emissions, etc.

[1889] Step 4:

[1890] The server compares the extracted information with the database and selects the best carbon-neutral related proposal. The input is the extracted carbon-neutral information and the output is the selected proposal. As part of the matching process, the server matches it with a database entry.

[1891] Step 5:

[1892] The server calculates the implementation cost, expected CO2 reduction, and return on investment of the selected proposal. The input is the selected proposal, and the output is the implementation cost, CO2 reduction, and return on investment. The server calculates these figures using a cost calculation engine.

[1893] Step 6:

[1894] The server generates a proposal that includes the calculation results. The input is data on implementation costs, CO2 reductions, and ROI, and the output is a proposal. Specifically, the server creates a draft proposal using an automatic generation algorithm.

[1895] Step 7:

[1896] The server provides the generated proposal to the user. The input is the generated proposal, and the output is that the user can view or download the proposal. The server creates and notifies the user of a link that the user can access on their device.

[1897] Step 8:

[1898] The camera is installed in the factory and recognizes the emotions of the user receiving the suggestions in real time. The input is the video data from the camera, and the output is the recognized emotion data. The emotion recognition engine analyzes the captured video and identifies the user's emotion.

[1899] Step 9:

[1900] The server then adjusts the suggestions as needed based on the emotion recognition data. The input is the recognized emotion data, and the output is the adjusted suggestions. For example, if the user expresses a negative emotion, the server generates additional explanatory material or alternative suggestions.

[1901] Step 10:

[1902] The server stores the user's emotional data in a database and uses it to generate future suggestions. The input is the emotional data, and the output is the saved data. Storing the emotional data improves the accuracy of future suggestions.

[1903] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1904] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1905] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1906] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1907] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1908] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1909] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1910] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1911] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."...

Claims

1. a means for uploading materials provided by corporate clients; A means for analyzing the uploaded materials using natural language processing technology and extracting information related to carbon neutrality; A means for comparing the extracted information with a database and selecting the most suitable carbon-neutral related proposal; A method for calculating the implementation costs, expected CO2 reductions and return on investment of the selected proposals; means for generating a proposal including the calculation results; means for providing the generated proposal to a user; A system including:

2. 10. The system of claim 1, further comprising means for automatically identifying the type of material uploaded for analysis and converting the content into text data.

3. 10. The system of claim 1, further comprising means for allowing a user to download or view the generated proposal.

Images