system

Abstract

Provide a system. [Solution] a means for uploading materials; means for extracting text from the uploaded material; a means for analyzing the extracted text to extract key keywords and topics; a means for obtaining relevant and up-to-date external data; a means for comparing the retrieved external data with the extracted text to assess the age of the information; means for generating and providing feedback to the user based on the evaluation results; A system including:

Description

[Technical Field]

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

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

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

[0004] In today's society, it is difficult to keep up with rapidly evolving technologies and trends. While it is extremely important to reflect the latest information when creating and updating presentation materials within a company, this process is time-consuming. As a result, materials are often created based on outdated information, which can lead to poor decision-making and a loss of competitive advantage in the market. Furthermore, there is a lack of a way to efficiently detect when information is out of date and provide appropriate feedback to users. A system that can solve these issues is needed. [Means for solving the problem]

[0005] This invention solves the above-mentioned problems with a system including a means for uploading materials, a means for extracting text from the uploaded materials, a means for analyzing the extracted text to extract key keywords and topics, a means for acquiring the latest related external data, a means for comparing the acquired external data with the extracted text to evaluate the age of the information, and a means for generating and providing feedback to the user based on the evaluation results. This system facilitates updating materials, allowing users to always create and update materials based on the latest information. In particular, the means for acquiring data from news databases and research report databases provides reliable, up-to-date information. Furthermore, by providing an interface for modifying materials based on feedback, user work efficiency is improved.

[0006] "Materials" refers to document files such as presentations, reports, papers, and reports.

[0007] "User" refers to an individual or organization that uses this system to create or update materials.

[0008] "Means" refers to a method, device, system, etc. for achieving a specific purpose.

[0009] "Upload" refers to the act of a user sending materials from their own device to a server.

[0010] "Text extraction" refers to the process of extracting written information from a document in digital form.

[0011] "Analysis" refers to the process of analyzing the extracted text using natural language processing techniques and interpreting its meaning.

[0012] "Keywords" refer to important words or phrases within a document.

[0013] "Topic" refers to the main theme or topic discussed within the document.

[0014] "External data" refers to data that contains the latest information needed to update the materials, such as news databases and research report databases.

[0015] "Comparison" refers to the process of comparing information within a document with external data and evaluating whether the information is new or old and how well it matches.

[0016] "Evaluation" refers to the process of determining how current and accurate the information in a resource is.

[0017] "Feedback" refers to suggestions for corrections or improvements provided to the user based on the evaluation results.

[0018] "Interface" refers to the screen and operating means that allow a user to interact with a system. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram illustrating a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] MODE FOR CARRYING OUT THE INVENTION

[0041] Overall system configuration

[0042] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest related external data, and provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. Each component of the system and its role are described below.

[0043] Uploading materials

[0044] Users upload presentation materials and document files to the system through a user interface, and the uploaded materials are sent to the server and temporarily stored.

[0045] Text Extraction and Analysis

[0046] The server extracts text from the uploaded material (using an appropriate text extraction library for PDF documents, another for PowerPoint documents, for example), and then analyzes the extracted text using a natural language processing (NLP) engine to extract key keywords and topics.

[0047] Retrieving External Data

[0048] The server sends API requests to news databases and research report databases to obtain the latest relevant external data, which is then stored on the server as text data.

[0049] Data comparison and evaluation

[0050] The server compares the extracted text with the latest external data it has retrieved, assessing whether the information in the document is up-to-date or outdated and in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[0051] Generating and Providing Feedback

[0052] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface.

[0053] Specific examples

[0054] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[0055] 1. Uploading materials

[0056] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0057] 2. Text Extraction and Analysis

[0058] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0059] 3. Acquiring external data

[0060] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0061] 4. Data comparison and evaluation

[0062] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0063] 5. Generating and Providing Feedback

[0064] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0065] Users can revise their materials based on the feedback they receive, ensuring that they always reflect the latest information and are of high quality. In this way, the system helps users update and create materials efficiently and accurately.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[0069] Step 2:

[0070] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[0071] Step 3:

[0072] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[0073] Step 4:

[0074] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[0075] Step 5:

[0076] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[0077] Step 6:

[0078] The server generates feedback for the user based on the results of the comparative evaluation, such as making specific suggestions like, "You're using information from 2021, but here's the latest information for 2023."

[0079] Step 7:

[0080] The server notifies the user of the generated feedback through a user interface, and the user is provided with an interface to review the feedback and update the material.

[0081] Step 8:

[0082] The user modifies the material based on the provided feedback, performs the update through the user interface, and then saves the updated material back to the system.

[0083] In this way, the system helps users create and update materials based on the latest information, improving the quality of presentations and reports.

[0084] Example 1

[0085] 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."

[0086] In conventional document creation systems, manual confirmation was required to determine whether the content of documents uploaded by users was based on the latest information, making update work cumbersome. It was also difficult to effectively obtain the latest external data and provide appropriate feedback to reflect that information in documents.

[0087] 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.

[0088] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract key keywords and topics, means for acquiring the latest related external data, means for comparing the extracted text with the acquired external data to evaluate the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for applying an appropriate text extraction library depending on the format of the materials, means for analyzing the extracted text using a natural language processing engine, means for acquiring related external data by sending an API request, and means for comparing text using document similarity calculations and machine learning models. This allows users to significantly improve the efficiency of updating materials and always create high-quality materials that reflect the latest information.

[0089] "Means for uploading materials" refers to a function that provides an interface for users to send materials to the system via the Internet.

[0090] "Means for extracting text from uploaded materials" refers to the libraries or software used by the server to analyze the contents of uploaded files and extract text data.

[0091] "Means for analyzing extracted text to extract key keywords and topics" refers to the function by which the server uses a natural language processing engine to find important keywords and topics from the extracted text.

[0092] The "means for obtaining the latest relevant external data" refers to a function in which the server sends an API request to an external database or information source to obtain the latest relevant information.

[0093] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to the algorithms or models that the server uses to compare the content of the material with the external data to determine whether the information is up-to-date or out-of-date.

[0094] The "means of generating feedback based on the evaluation results and providing it to the user" is a function in which the server provides the user with specific improvement suggestions and the latest information based on the evaluation results of the age of the information.

[0095] "Means for applying an appropriate text extraction library according to the format of the document" refers to a function in which the server automatically identifies the file format of the uploaded document and extracts text using a library appropriate for each format, such as PDF or PowerPoint.

[0096] "Means for analyzing extracted text using a natural language processing engine" refers to a function in which the server uses natural language processing technology to perform semantic analysis and keyword extraction on the extracted text.

[0097] "Means for sending API requests to obtain relevant external data" refers to the function by which the server periodically or as needed creates and sends API requests to external databases or information sources to obtain the latest information.

[0098] "Means for comparing texts using document similarity calculations or machine learning models" refers to a function in which the server uses machine learning models or numerical algorithms to compare the text of a document with the text of external data and evaluate the similarities and differences between them.

[0099] MODE FOR CARRYING OUT THE INVENTION

[0100] Overall system configuration

[0101] This invention is a system that analyzes the content of materials uploaded by users, compares them with the latest external data, and then provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. The specific components of the system and their operation are described below.

[0102] Uploading materials

[0103] Users log in to the system via a browser or a dedicated application and upload documents. This process is carried out through the user interface, and the files specified by the user are sent to the server. Supported file formats include PDF and PowerPoint, and the sent files are temporarily stored on the server.

[0104] Text Extraction and Analysis

[0105] The server determines the format of the uploaded material and extracts the text using the appropriate text extraction library: for PDF materials, the Apache PDFBox library is used, and for PowerPoint materials, the Apache POI library is used. This extracted text is then sent to a natural language processing engine (e.g., SpaCy, NLTK) to extract key keywords and topics.

[0106] Retrieving External Data

[0107] The server retrieves the latest relevant external data based on the keywords extracted from the extracted text. External data sources include news databases and research report databases. The server sends a RESTful API request to retrieve the latest relevant information. An API request uses a format such as requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}).

[0108] Data comparison and evaluation

[0109] The server uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) or machine learning models such as TF-IDF and BERT to compare the text of the document with the acquired external data. For example, when using Cosine Similarity, the calculation is done as follows: cosine_similarity(vectorized_textA, vectorized_textB). This allows the server to evaluate whether the information in the document is up-to-date or if it is old and needs to be updated.

[0110] Generating and Providing Feedback

[0111] Based on the evaluation results, the server generates feedback to provide to the user. This feedback includes specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface. For example, a message such as "The latest information on autonomous driving technology for 2023 is available. Please check the link below." is generated and displayed as feedback.

[0112] Specific examples

[0113] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the process will proceed as follows:

[0114] 1. Uploading materials

[0115] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0116] 2. Text Extraction and Analysis

[0117] The server uses Apache PDFBox to extract text from the PDF and a natural language processing engine (e.g., SpaCy) to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0118] 3. Acquiring external data

[0119] The server sends a RESTful API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0120] 4. Data comparison and evaluation

[0121] The server compares the retrieved news with the extracted text and uses a document similarity algorithm (e.g., Cosine Similarity) to determine that the "2021" information in the document is outdated.

[0122] 5. Generating and Providing Feedback

[0123] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0124] In this way, the system helps users to efficiently update materials and create high-quality materials that always reflect the latest information.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] A user logs into the system using a browser or a dedicated application, clicks the upload button, and selects a document. The input is a file selected by the user (e.g., "Autonomous Driving Technology 2021.pdf"). This file is sent to the server via the Internet. Specifically, the user selects the file using a standard file search window and clicks the upload button. The server receives the file and temporarily stores it in storage.

[0128] Step 2:

[0129] The server determines the format of the uploaded file and extracts the text using the appropriate text extraction library. For example, it uses the Apache PDFBox library for PDF format documents and the Apache POI library for PowerPoint format documents. The input contains the uploaded file. Specifically, it calls the ApachePDFBox.load(file) or ApachePOI.load(file) method to extract text data from the file. The extracted text data is returned as the output.

[0130] Step 3:

[0131] The server sends the extracted text to a natural language processing engine to extract key keywords and topics. The extracted text data is the input. The text is analyzed using a natural language processing engine (e.g., SpaCy, NLTK). Specifically, the model is loaded with nlp = spacy.load('en_core_web_sm') and the text is analyzed with doc = nlp(extracted_text). The output is a list of key keywords and topics.

[0132] Step 4:

[0133] The server retrieves the latest related external data based on the extracted keywords. The input is a list of extracted keywords. A RESTful API request is used to retrieve the external data. Specifically, a request of requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}) is sent to retrieve the latest data. The output is the retrieved external data in text format.

[0134] Step 5:

[0135] The server compares the text of the document with the acquired external data. The inputs include the text of the document and the acquired external data. It uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) and machine learning models such as TF-IDF and BERT. Specifically, it evaluates the similarity using cosine_similarity(vectorized_textA, vectorized_textB). The output is a score indicating the age of the information.

[0136] Step 6:

[0137] The server generates feedback based on the age of the information and provides it to the user. The inputs are the evaluation score and the acquired external data. The server generates a specific feedback message based on the evaluation results. Specifically, it creates a message such as "The latest information on autonomous driving technology as of 2023 is available. Please check the link below." and displays it with user_interface.display(feedback_message). The output is a feedback message to the user.

[0138] Through each step, the system assists users in updating materials efficiently and accurately.

[0139] (Application example 1)

[0140] 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."

[0141] In current factory operations, work procedures and manuals need to be updated regularly, but this process is time-consuming and it is difficult to ensure that they reflect the latest technical standards and regulations. This can also reduce work efficiency and affect quality and safety. To solve this problem, a system is needed that automatically compares the contents of procedure manuals with the latest information and makes any necessary updates quickly and accurately.

[0142] 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.

[0143] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the text to extract key keywords and topics, means for acquiring the latest related external data, means for evaluating the age of the information by comparing the acquired external data with the extracted text, means for generating feedback based on the evaluation results and providing it to the user, means for comparing the extracted text with the latest external data and using a generative AI model to indicate parts of the information that need updating, and means for generating prompts for the generative AI model and analyzing the results. This allows work procedures and manuals to be updated automatically and efficiently, ensuring that work reflects the latest technical standards and regulations.

[0144] The "material uploading means" is a mechanism by which a user can send materials in electronic data format to a server.

[0145] "Text extraction means" refers to a technique for extracting text data from uploaded materials.

[0146] "Keyword and topic extraction" is a technique that analyzes extracted text data to find key words and themes.

[0147] "Means for acquiring the latest external data" refers to a mechanism for collecting information on the latest technical standards and regulations from external data sources.

[0148] "Data comparison and evaluation means" refers to a technique for comparing extracted text with acquired external data to determine the freshness and accuracy of the information.

[0149] A "generative AI model" is a type of artificial intelligence that can understand and generate natural language, and is primarily used for generating and analyzing text.

[0150] A "prompt sentence generation means" is a technology that creates instruction sentences to be input into a generative AI model.

[0151] The "feedback generation means" is a mechanism for presenting to the user areas that require updating or improvement based on the results of data comparison and evaluation.

[0152] Overall system configuration

[0153] This invention is a system that uploads factory work procedures and manuals, extracts text, analyzes it, compares it with the latest technical standards and regulations, and generates and provides feedback. The system consists of a server and terminals, and users access the system via the Internet. This system helps users efficiently update documents and perform work that reflects the latest information.

[0154] Uploading materials

[0155] Users upload factory work procedures and manuals in PDF format through the user interface on their devices, and the uploaded materials are sent to the server and temporarily stored.

[0156] Text Extraction and Analysis

[0157] The server extracts text from the uploaded PDF documents, for example using a text extraction library such as pdfminer.six. The extracted text is then analyzed using a natural language processing (NLP) engine such as dslim / bert-base-NER to extract key keywords and topics.

[0158] Retrieving External Data

[0159] The server sends API requests to news databases and research report databases to obtain relevant and up-to-date external data. External data acquisition involves using news APIs. The acquired data is stored as text data on the server.

[0160] Data comparison and evaluation

[0161] The server compares the extracted text with the latest external data. This process uses a generative AI model, such as GPT-3®.5-Turbo, to provide a prompt and generate a result.

[0162] Generating and Providing Feedback

[0163] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and summaries of the latest information. The generated feedback is provided to the user through a user interface.

[0164] Specific examples

[0165] For example, if a user uploads "Factory Equipment Maintenance Manual 2021.pdf", the steps are as follows: First, the document is uploaded, then text extraction and analysis are performed. During the analysis, keywords such as "equipment maintenance" and "2021" are extracted. The server then retrieves the latest data related to "equipment maintenance 2023" from the news database. The retrieved data is compared with the extracted text, and a prompt sentence is generated using a generative AI model to indicate the parts of the information that need to be updated. A specific example of a prompt sentence is:

[0166] "Compare the contents of the following text: Factory Equipment Maintenance Manual 2021.pdf with the latest data for 2023 to indicate which information is current and which parts need to be updated."

[0167] Finally, feedback is generated and provided to the user in the form of "The information in the 2021 Equipment Maintenance Manual is outdated, so please update the following to reflect the latest information: ..."

[0168] In this way, the system can assist users in quickly implementing accurate work procedures based on the latest technical standards and regulations.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1: Upload your materials

[0171] Users upload factory work procedures and manuals in PDF format to the server via their terminal. The input is a PDF file, and the server temporarily stores this PDF file in its storage. The file upload process is performed via the user interface.

[0172] Step 2: Text extraction

[0173] The server extracts text from the uploaded PDF file. Here, the pdfminer.six library is used. The input is a PDF file and the output is text data. In the text extraction process, the content of the PDF file is obtained as character data.

[0174] Step 3: Keyword and topic analysis

[0175] The server analyzes the extracted text and extracts key keywords and topics. The dslim / bert-base-NER model is used. The input is the extracted text, and the output is a list of keywords and topics. The analysis process uses natural language processing to identify important words and phrases.

[0176] Step 4: Retrieving External Data

[0177] The server sends API requests to the news database and research report database to obtain the latest external data. The input is a list of keywords and topics, and the output is text data as external data. The API request process obtains the latest information based on the specified keywords.

[0178] Step 5: Data comparison and evaluation

[0179] The server compares the extracted text with the latest external data obtained and evaluates the age of the information. A generative AI model is used here. The input is the extracted text and the latest external data, and the output is the evaluation result. In the comparison and evaluation process, a prompt sentence is input to the generative AI model and the model's output is analyzed.

[0180] Step 6: Prompt generation

[0181] The server generates prompt sentences to be input to the generative AI model. The input is the extracted text and external data, and the output is the prompt sentence. The prompt sentence generation process creates the instruction sentences necessary for comparison and evaluation.

[0182] Step 7: Analyze the results

[0183] The server analyzes the output of the generative AI model and identifies areas that need updating or improvement. The input is the output of the generative AI model, and the output is specific findings. The analysis process analyzes the model output and summarizes specific corrections.

[0184] Step 8: Generate and provide feedback

[0185] The server generates feedback based on the evaluation results and provides it to the user. The input is the findings obtained from the analysis, and the output is the feedback information. In the feedback generation process, corrections and suggestions are notified to the user through a user interface.

[0186] 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.

[0187] MODE FOR CARRYING OUT THE INVENTION

[0188] Overall system configuration

[0189] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest relevant external data, and then provides feedback to the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to adjust the content of the feedback and the interface according to the user's emotions. The system is primarily composed of a server, a terminal, and an emotion engine, and users access the system via the Internet. Each component of the system and its role are described below.

[0190] Uploading materials

[0191] Users upload presentation materials and document files to the system by selecting the materials through the user interface and clicking the upload button, which sends the materials to the server and temporarily stores them in storage.

[0192] Text Extraction and Analysis

[0193] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library. The extracted text is passed to a natural language processing (NLP) engine to parse and extract key keywords and topics.

[0194] Retrieving External Data

[0195] The server sends API requests to news databases and research report databases to retrieve relevant and up-to-date external data, which is then stored on the server in text format.

[0196] Data comparison and evaluation

[0197] The server compares the text extracted from the document with the latest information obtained from external sources, assessing whether the information in the document is up-to-date or outdated and therefore in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[0198] Recognizing user emotions with an emotion engine

[0199] The emotion engine analyzes the user's text and voice input to recognize their emotions, allowing the system to understand their emotional state in real time, such as whether they are stressed, excited, or relaxed.

[0200] Generating and Providing Feedback

[0201] The server generates feedback for the user based on the results of the comparative evaluation and the emotion recognition results of the emotion engine. For example, if the user is feeling stressed, the server will express the feedback content in a gentler manner, and if the user is relaxed, it will provide detailed information, and generate feedback that corresponds to the user's emotions. The generated feedback is notified to the user through the user interface.

[0202] Interface customization

[0203] The layout and color of the user interface can be customized based on the emotions recognized by the emotion engine, for example, changing to calming colors when the user is stressed and using bright colors when relaxed.

[0204] Specific examples

[0205] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[0206] 1. Uploading materials

[0207] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0208] 2. Text Extraction and Analysis

[0209] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0210] 3. Acquiring external data

[0211] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0212] 4. Data comparison and evaluation

[0213] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0214] 5. Emotion Recognition by Emotion Engine

[0215] If the user is feeling stressed, the emotion engine will recognize this state.

[0216] 6. Generating and Providing Feedback

[0217] The server generates feedback such as, "We have the latest information on autonomous driving technology for 2023. Check out the link below.", providing gentler language in consideration of the user's stress.

[0218] 7. Interface Customization

[0219] If the user is stressed, change the interface color to a calming color such as blue or green.

[0220] Users can revise their documents based on the feedback they receive, ensuring they always create high-quality documents that reflect the latest information. In addition, the emotion engine allows users to work in a comfortable environment. In this way, the system helps users update and create documents efficiently and accurately, improving the quality of the user experience.

[0221] The processing flow will be explained below.

[0222] Step 1:

[0223] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[0224] Step 2:

[0225] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[0226] Step 3:

[0227] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[0228] Step 4:

[0229] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[0230] Step 5:

[0231] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[0232] Step 6:

[0233] The emotion engine recognizes user emotions, for example by analyzing the user's text and voice inputs to identify emotions such as stress or relaxation, using natural language processing algorithms and machine learning models.

[0234] Step 7:

[0235] The server generates feedback for the user based on the results of the comparative evaluation and the recognition results of the emotion engine. For example, if the user is feeling stressed, the server will soften the feedback.

[0236] Step 8:

[0237] The server notifies the user of the generated feedback through a user interface, including suggestions for updating outdated information and links to the latest information.

[0238] Step 9:

[0239] The emotion engine customizes the layout and color of the user interface based on the emotions it recognizes. For example, if the user is feeling stressed, the interface color will change to calming colors such as blue or green.

[0240] Step 10:

[0241] The user modifies the material based on the provided feedback, making the modifications through the user interface, and then saving the updated material back to the system.

[0242] Example 2

[0243] 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."

[0244] Conventional document management systems often have issues with uploaded documents becoming outdated, making it difficult for users to keep documents up to date. Furthermore, the user interface is fixed and cannot be flexibly changed according to the user's emotional state, potentially resulting in a poor user experience. Furthermore, feedback is generated mechanically and is not tailored to the user's emotions or needs, resulting in a lack of familiarity for users.

[0245] 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.

[0246] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract major keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for recognizing the user's emotions, means for adjusting the content of the feedback based on the recognized emotions, and means for customizing the user interface based on the recognized emotions. This makes it possible to keep the content of the materials up to date and to flexibly adjust the feedback and interface according to the user's emotional state.

[0247] "Means for uploading materials" refers to the method and process by which a user transmits document files and presentation materials to the system via the Internet and stores them on the server.

[0248] "Means for extracting text from uploaded materials" refers to the techniques and processes for analyzing the content of received document files and extracting text data.

[0249] "Means for analyzing extracted text to extract key keywords and topics" refers to the process of analyzing extracted text data using natural language processing techniques to identify important keywords and topics within the document.

[0250] "Means for obtaining relevant and up-to-date external data" means methods and processes for obtaining up-to-date data from external databases and sources based on specified keywords and topics.

[0251] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to methods and techniques for comparing internal text with external data to determine the freshness of the information or whether it needs to be updated.

[0252] The "means for generating and providing feedback to the user based on the evaluation results" is a process for preparing appropriate feedback information for the user based on the results of the comparison and evaluation, and communicating it to the user via the interface.

[0253] "Means for recognizing user emotions" refers to technologies and processes that analyze data such as text and voice input by a user and identify the user's emotional state in real time.

[0254] The "means for adjusting the content of feedback based on the recognized emotion" refers to a method and process for appropriately changing the content and expression of feedback based on the result of the user's emotion recognition.

[0255] "Means for customizing user interfaces based on recognized emotions" refers to techniques and processes for adjusting interface layout, color, and user experience based on the user's emotional state.

[0256] Overall system configuration

[0257] This invention is a system that allows users to upload materials, analyzes the text extracted from the materials, compares it with the latest relevant external data, and provides feedback to the user. The system is combined with an emotion engine that can recognize the user's emotions and adjust the feedback and interface accordingly. The main components are a server, a terminal, and the emotion engine, and users access the system via the Internet.

[0258] Uploading materials

[0259] Users upload document files and presentation materials through the system's web interface. Specifically, users click the "Upload File" button, select the materials to upload from their local environment, and click the "Send" button. The files sent from the device are received by the server and temporarily saved in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed on the user interface.

[0260] Text Extraction and Analysis

[0261] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[0262] Retrieving External Data

[0263] The server issues an API request to an external database (e.g., Google® News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored on the server in text format.

[0264] Data comparison and evaluation

[0265] The server compares the text extracted from the document with external data using a document comparison algorithm (e.g., Cosine Similarity). This comparison determines, for example, that information in the document referring to "2021" is out of date. The results of the comparison and evaluation are scored and stored.

[0266] Recognizing user emotions with an emotion engine

[0267] Users can input messages or voice messages into the system. The server sends the input data to an emotion engine (e.g., Microsoft® Azure® Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[0268] Generating and Providing Feedback

[0269] The server generates appropriate feedback for the user based on the results of the comparative evaluation and emotion recognition. For example, if the user is feeling stressed, it will provide soft feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[0270] Interface customization

[0271] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[0272] Specific examples

[0273] For example, if a user wants to upload a "2021 Report on Autonomous Driving Technology," the process would look like this:

[0274] 1. Uploading materials

[0275] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0276] 2. Text Extraction and Analysis

[0277] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0278] 3. Acquiring external data

[0279] The server sends an API request to the news database using the keyword "autonomous driving technology 2023" to retrieve the latest related news.

[0280] 4. Data comparison and evaluation

[0281] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0282] 5. Emotion Recognition by Emotion Engine

[0283] If the user is feeling stressed, the emotion engine will recognize this state.

[0284] 6. Generating and Providing Feedback

[0285] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0286] 7. Interface Customization

[0287] The user is feeling stressed, so the interface color is changed to blue or green.

[0288] In this way, the system can help users update and create materials efficiently and accurately, improving the quality of the user experience.

[0289] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0290] Step 1:

[0291] Uploading materials

[0292] The user uploads document files or presentation materials from the system's web interface. Specifically, the user clicks the "Upload File" button, selects the material to upload from the local environment (e.g., "Autonomous Driving Technology 2021.pdf"), and clicks the "Send" button. The server receives the file sent from the terminal and temporarily saves it in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed in the user interface.

[0293] Input: A file selected by the user

[0294] Output: Upload successful message

[0295] The server saves the received file in storage and displays a save success message on the user interface.

[0296] Step 2:

[0297] Text Extraction and Analysis

[0298] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[0299] Input: Saved file

[0300] Output: Extracted text and analyzed keywords and topics

[0301] The server inputs the extracted text into a natural language processing engine to analyze and extract key keywords and topics.

[0302] Step 3:

[0303] Retrieving External Data

[0304] The server sends an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored in text format on the server.

[0305] Input: Extracted keywords

[0306] Output: Retrieved external data

[0307] The server sends API requests using keywords to news databases and research report databases to retrieve and store the latest data.

[0308] Step 4:

[0309] Data comparison and evaluation

[0310] The server compares the text extracted from the document with the external data. This comparison uses a document comparison algorithm (e.g., Cosine Similarity). For example, the comparison may determine that the information in the document about "2021" is outdated. The results of the comparison and evaluation are scored and stored on the server.

[0311] Input: Extracted text and retrieved external data

[0312] Output: Information freshness evaluation result

[0313] The server uses a document comparison algorithm to compare the internal text with the external data, assess the age of the information, and store the results.

[0314] Step 5:

[0315] Recognizing user emotions with an emotion engine

[0316] The user inputs a message or voice message into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[0317] Input: User text and voice input

[0318] Output: User emotion recognition results

[0319] The server sends the input user data to the emotion engine and stores the recognized emotional state.

[0320] Step 6:

[0321] Generating and Providing Feedback

[0322] The server generates feedback for the user based on the results of the comparative evaluation of the data and the recognition results of the emotion engine. For example, if the user is feeling stressed, it generates soft-spoken feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[0323] Input: Information freshness evaluation results and emotion recognition results

[0324] Output: Feedback provided to the user

[0325] The server generates appropriate feedback based on the evaluation results and emotion recognition results and provides it to the user.

[0326] Step 7:

[0327] Interface customization

[0328] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[0329] Input: Recognition results of emotion engine

[0330] Output: Customized user interface

[0331] The server adjusts the interface based on the emotion recognition results, providing a comfortable working environment for the user.

[0332] ---

[0333] Through these steps, the system helps users update and create documents efficiently and accurately, while improving the quality of the user experience.

[0334] (Application example 2)

[0335] 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."

[0336] When autonomous vehicles continue to operate, they are required to constantly update the latest traffic and road regulation information. However, if the driver feels fatigued or stressed, it may become difficult for them to accurately and quickly grasp this information. Therefore, in addition to updating the information, it is necessary to provide feedback and adjust the interface according to the driver's emotional state.

[0337] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract main keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, and means for recognizing the user's emotions using an emotion engine and adjusting the content of the feedback and the interface according to the user's emotions. This allows the driver to appropriately receive the latest traffic information and maintain a comfortable driving environment through appropriate feedback according to the user's emotional state.

[0338] "Documents" are documents or files that detail information.

[0339] An "uploading means" is a system or function that allows a user to send data from their device to a remote server.

[0340] "Text extraction methods" are techniques and algorithms used to extract textual information from documents and files.

[0341] "Means for analyzing and extracting key keywords and topics" refers to a technique for analyzing extracted text information and identifying important terms and topics from it.

[0342] "Means for obtaining the latest external data" are systems and processes for collecting current information from the Internet or databases.

[0343] The "means for comparing and assessing the age of information" is a function for comparing the collected external data with the extracted text information to determine how recent the information is.

[0344] "Means for generating feedback and providing it to users" refers to a system or function that creates information or advice based on the evaluation results and presents it to users.

[0345] An "emotion engine" is a technology or algorithm that analyzes and recognizes a user's emotional state from their input (voice, text, etc.).

[0346] "Means for recognizing emotions and adjusting the content of feedback and interface" refers to a system or function for changing the content and display format of feedback to the user based on the recognized emotional state.

[0347] Overall system configuration

[0348] This invention is a system that provides feedback based on the latest traffic information and the driver's emotional state during the operation of an autonomous vehicle, helping the driver continue driving comfortably and efficiently. The system mainly consists of a server, an in-vehicle computer, and an emotion recognition engine.

[0349] Uploading materials

[0350] The driver uploads a document, such as "New Traffic Regulation Information 2023.pdf," through the autonomous vehicle's navigation system. By clicking the upload button, the document file is sent to the server and temporarily stored.

[0351] Text Extraction and Analysis

[0352] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The extracted text is passed to a natural language processing (NLP) engine, which parses and extracts key keywords and topics.

[0353] Retrieving External Data

[0354] The server sends API requests to traffic information systems and news databases to obtain the latest traffic information. The obtained data is stored on the server in text format. The API library used is, for example, "requests".

[0355] Data comparison and evaluation

[0356] The server compares the text extracted from the document with the latest information obtained from external sources, and evaluates whether the information in the document is up-to-date or needs to be updated. The evaluation is performed automatically using comparison algorithms and scoring methods (e.g., similarity calculations).

[0357] Driver emotion recognition using emotion engine

[0358] The vehicle's computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state, allowing the system to understand in real time whether the driver is stressed, tired, or relaxed.

[0359] Generating and Providing Feedback

[0360] The server generates feedback for the driver based on the comparison of the document with external data and the results of the emotion recognition engine. For example, if the driver is feeling stressed, the server generates feedback that corresponds to the driver's emotions, such as softening the content of the feedback and providing more detailed information. The generated feedback is notified to the driver through the navigation system.

[0361] Interface customization

[0362] The emotion engine can customize the layout and color of the in-vehicle navigation system based on the driver's emotions, for example, changing to calming colors like blue and green if the driver is stressed, and using brighter colors if the driver is relaxed.

[0363] Specific examples

[0364] If a driver uploads "New Traffic Regulation Information 2023.pdf", the steps are as follows:

[0365] 1. Uploading materials

[0366] "New Traffic Regulation Information 2023.pdf" has been uploaded.

[0367] Example prompt: "Please upload New Traffic Regulation Information 2023.pdf."

[0368] 2. Text Extraction and Analysis

[0369] The server extracts text from the PDF and uses an NLP engine to extract keywords such as "2023," "traffic regulations," and "new regulations."

[0370] 3. Acquiring external data

[0371] The server sends an API request to the traffic information system to obtain the latest traffic information.

[0372] API request example: "requests.get("https: / / api.trafficinfo.com / data?year=2023")"

[0373] 4. Data comparison and evaluation

[0374] The server compares the extracted text with external data and evaluates whether it needs to be updated to reflect the latest information.

[0375] 5. Emotion Recognition by Emotion Engine

[0376] The emotion engine recognizes the driver's stress level and fatigue.

[0377] Example prompt: "Analyze the driver's emotional state and adjust feedback."

[0378] 6. Generating and Providing Feedback

[0379] The server generates soft feedback saying, "We have the latest 2023 traffic regulation information. Check the link below."

[0380] Example feedback: "Please check the latest traffic regulations and drive safely."

[0381] 7. Interface Customization

[0382] If the driver is feeling stressed, the navigation system changes the background color to blue or green.

[0383] Example prompt: "Due to high stress levels, we are changing the color tone of the navigation system."

[0384] In this way, the system helps drivers receive optimal information and provides a driving environment that takes their emotional state into consideration, supporting comfortable and safe driving.

[0385] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0386] Step 1:

[0387] The user uploads a document file (e.g., "New Traffic Regulation Information 2023.pdf") through the navigation system of the autonomous vehicle. When the upload button is clicked, the document file is sent to the server. At this stage, the input is the document file from the user, and the output is the document file saved on the server.

[0388] Step 2:

[0389] The server determines the format of the saved material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The input is the material file, and the output is the extracted text data.

[0390] Step 3:

[0391] The server passes the extracted text to a natural language processing (NLP) engine to analyze it for key keywords and topics. At this point, the input is the extracted text, and the output is a list of key keywords and topics. Specifically, keyword extraction and topic modeling are performed.

[0392] Step 4:

[0393] The server sends API requests to traffic information systems and news databases to get the latest traffic information. The input is the API query, and the output is the retrieved latest traffic information data. The data is collected using an API library (e.g., "requests").

[0394] Step 5:

[0395] The server compares the retrieved external data with the extracted text to assess the age of the information. The input is the external data and the extracted text, and the output is an assessment of the age of the information and whether it needs to be updated. A comparison algorithm or scoring method (e.g., similarity calculation) is used.

[0396] Step 6:

[0397] The in-vehicle computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state. At this point, the input is voice or text input from the driver, and the output is an evaluation of the driver's emotional state.

[0398] Step 7:

[0399] The server generates feedback for the driver based on the comparative evaluation results and emotion recognition results. The input is the information evaluation results and the driver's emotional state, and the output is the generated feedback message. The server provides softer expressions and detailed information according to the driver's emotional state.

[0400] Step 8:

[0401] The server notifies the driver of the generated feedback through the navigation system. The input is the generated feedback message, and the output is the notification provided to the driver. Specific operations include displaying the feedback message and an audio notification.

[0402] Step 9:

[0403] The in-vehicle computer customizes the navigation system interface based on the emotional state recognized by the emotion recognition engine. The input is the driver's emotional state, and the output is an adjusted interface layout and color tone. Specific actions include changing the background color and adjusting the layout.

[0404] 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.

[0405] 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.

[0406] 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.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 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.

[0410] 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).

[0411] 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.

[0412] 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.

[0413] 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).

[0414] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0415] 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.

[0416] 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.

[0417] 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.

[0418] 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.

[0419] 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."

[0420] MODE FOR CARRYING OUT THE INVENTION

[0421] Overall system configuration

[0422] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest related external data, and provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. Each component of the system and its role are described below.

[0423] Uploading materials

[0424] Users upload presentation materials and document files to the system through a user interface, and the uploaded materials are sent to the server and temporarily stored.

[0425] Text Extraction and Analysis

[0426] The server extracts text from the uploaded material (using an appropriate text extraction library for PDF documents, another for PowerPoint documents, for example), and then analyzes the extracted text using a natural language processing (NLP) engine to extract key keywords and topics.

[0427] Retrieving External Data

[0428] The server sends API requests to news databases and research report databases to obtain the latest relevant external data, which is then stored on the server as text data.

[0429] Data comparison and evaluation

[0430] The server compares the extracted text with the latest external data it has retrieved, assessing whether the information in the document is up-to-date or outdated and in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[0431] Generating and Providing Feedback

[0432] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface.

[0433] Specific examples

[0434] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[0435] 1. Uploading materials

[0436] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0437] 2. Text Extraction and Analysis

[0438] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0439] 3. Acquiring external data

[0440] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0441] 4. Data comparison and evaluation

[0442] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0443] 5. Generating and Providing Feedback

[0444] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0445] Users can revise their materials based on the feedback they receive, ensuring that they always reflect the latest information and are of high quality. In this way, the system helps users update and create materials efficiently and accurately.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[0449] Step 2:

[0450] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[0451] Step 3:

[0452] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[0453] Step 4:

[0454] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[0455] Step 5:

[0456] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[0457] Step 6:

[0458] The server generates feedback for the user based on the results of the comparative evaluation, such as making specific suggestions like, "You're using information from 2021, but here's the latest information for 2023."

[0459] Step 7:

[0460] The server notifies the user of the generated feedback through a user interface, and the user is provided with an interface to review the feedback and update the material.

[0461] Step 8:

[0462] The user modifies the material based on the provided feedback, performs the update through the user interface, and then saves the updated material back to the system.

[0463] In this way, the system helps users create and update materials based on the latest information, improving the quality of presentations and reports.

[0464] Example 1

[0465] 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."

[0466] In conventional document creation systems, manual confirmation was required to determine whether the content of documents uploaded by users was based on the latest information, making update work cumbersome. It was also difficult to effectively obtain the latest external data and provide appropriate feedback to reflect that information in documents.

[0467] 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.

[0468] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract key keywords and topics, means for acquiring the latest related external data, means for comparing the extracted text with the acquired external data to evaluate the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for applying an appropriate text extraction library depending on the format of the materials, means for analyzing the extracted text using a natural language processing engine, means for acquiring related external data by sending an API request, and means for comparing text using document similarity calculations and machine learning models. This allows users to significantly improve the efficiency of updating materials and always create high-quality materials that reflect the latest information.

[0469] "Means for uploading materials" refers to a function that provides an interface for users to send materials to the system via the Internet.

[0470] "Means for extracting text from uploaded materials" refers to the libraries or software used by the server to analyze the contents of uploaded files and extract text data.

[0471] "Means for analyzing extracted text to extract key keywords and topics" refers to the function by which the server uses a natural language processing engine to find important keywords and topics from the extracted text.

[0472] The "means for obtaining the latest relevant external data" refers to a function in which the server sends an API request to an external database or information source to obtain the latest relevant information.

[0473] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to the algorithms or models that the server uses to compare the content of the material with the external data to determine whether the information is up-to-date or out-of-date.

[0474] The "means of generating feedback based on the evaluation results and providing it to the user" is a function in which the server provides the user with specific improvement suggestions and the latest information based on the evaluation results of the age of the information.

[0475] "Means for applying an appropriate text extraction library according to the format of the document" refers to a function in which the server automatically identifies the file format of the uploaded document and extracts text using a library appropriate for each format, such as PDF or PowerPoint.

[0476] "Means for analyzing extracted text using a natural language processing engine" refers to a function in which the server uses natural language processing technology to perform semantic analysis and keyword extraction on the extracted text.

[0477] "Means for sending API requests to obtain relevant external data" refers to the function by which the server periodically or as needed creates and sends API requests to external databases or information sources to obtain the latest information.

[0478] "Means for comparing texts using document similarity calculations or machine learning models" refers to a function in which the server uses machine learning models or numerical algorithms to compare the text of a document with the text of external data and evaluate the similarities and differences between them.

[0479] MODE FOR CARRYING OUT THE INVENTION

[0480] Overall system configuration

[0481] This invention is a system that analyzes the content of materials uploaded by users, compares them with the latest external data, and then provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. The specific components of the system and their operation are described below.

[0482] Uploading materials

[0483] Users log in to the system via a browser or a dedicated application and upload documents. This process is carried out through the user interface, and the files specified by the user are sent to the server. Supported file formats include PDF and PowerPoint, and the sent files are temporarily stored on the server.

[0484] Text Extraction and Analysis

[0485] The server determines the format of the uploaded material and extracts the text using the appropriate text extraction library: for PDF materials, it uses the Apache PDFBox library, for PowerPoint materials it uses the Apache POI library, and this extracted text is sent to a natural language processing engine (e.g., SpaCy, NLTK) to extract key keywords and topics.

[0486] Retrieving External Data

[0487] The server retrieves the latest relevant external data based on the keywords extracted from the extracted text. External data sources include news databases and research report databases. The server sends a RESTful API request to retrieve the latest relevant information. An API request uses a format such as requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}).

[0488] Data comparison and evaluation

[0489] The server uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) or machine learning models such as TF-IDF and BERT to compare the text of the document with the acquired external data. For example, when using Cosine Similarity, the calculation is done as follows: cosine_similarity(vectorized_textA, vectorized_textB). This allows the server to evaluate whether the information in the document is up-to-date or if it is old and needs to be updated.

[0490] Generating and Providing Feedback

[0491] Based on the evaluation results, the server generates feedback to provide to the user. This feedback includes specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface. For example, a message such as "The latest information on autonomous driving technology for 2023 is available. Please check the link below." is generated and displayed as feedback.

[0492] Specific examples

[0493] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the process will proceed as follows:

[0494] 1. Uploading materials

[0495] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0496] 2. Text Extraction and Analysis

[0497] The server uses Apache PDFBox to extract text from the PDF and a natural language processing engine (e.g., SpaCy) to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0498] 3. Acquiring external data

[0499] The server sends a RESTful API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0500] 4. Data comparison and evaluation

[0501] The server compares the retrieved news with the extracted text and uses a document similarity algorithm (e.g., Cosine Similarity) to determine that the "2021" information in the document is outdated.

[0502] 5. Generating and Providing Feedback

[0503] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0504] In this way, the system helps users to efficiently update materials and create high-quality materials that always reflect the latest information.

[0505] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0506] Step 1:

[0507] A user logs into the system using a browser or a dedicated application, clicks the upload button, and selects a document. The input is a file selected by the user (e.g., "Autonomous Driving Technology 2021.pdf"). This file is sent to the server via the Internet. Specifically, the user selects the file using a standard file search window and clicks the upload button. The server receives the file and temporarily stores it in storage.

[0508] Step 2:

[0509] The server determines the format of the uploaded file and extracts the text using the appropriate text extraction library. For example, it uses the Apache PDFBox library for PDF format documents and the Apache POI library for PowerPoint format documents. The input contains the uploaded file. Specifically, it calls the ApachePDFBox.load(file) or ApachePOI.load(file) method to extract text data from the file. The extracted text data is returned as the output.

[0510] Step 3:

[0511] The server sends the extracted text to a natural language processing engine to extract key keywords and topics. The extracted text data is the input. The text is analyzed using a natural language processing engine (e.g., SpaCy, NLTK). Specifically, the model is loaded with nlp = spacy.load('en_core_web_sm') and the text is analyzed with doc = nlp(extracted_text). The output is a list of key keywords and topics.

[0512] Step 4:

[0513] The server retrieves the latest related external data based on the extracted keywords. The input is a list of extracted keywords. A RESTful API request is used to retrieve the external data. Specifically, a request of requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}) is sent to retrieve the latest data. The output is the retrieved external data in text format.

[0514] Step 5:

[0515] The server compares the text of the document with the acquired external data. The inputs include the text of the document and the acquired external data. It uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) and machine learning models such as TF-IDF and BERT. Specifically, it evaluates the similarity using cosine_similarity(vectorized_textA, vectorized_textB). The output is a score indicating the age of the information.

[0516] Step 6:

[0517] The server generates feedback based on the age of the information and provides it to the user. The inputs are the evaluation score and the acquired external data. The server generates a specific feedback message based on the evaluation results. Specifically, it creates a message such as "The latest information on autonomous driving technology as of 2023 is available. Please check the link below." and displays it with user_interface.display(feedback_message). The output is a feedback message to the user.

[0518] Through each step, the system assists users in updating materials efficiently and accurately.

[0519] (Application example 1)

[0520] 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."

[0521] In current factory operations, work procedures and manuals need to be updated regularly, but this process is time-consuming and it is difficult to ensure that they reflect the latest technical standards and regulations. This can also reduce work efficiency and affect quality and safety. To solve this problem, a system is needed that automatically compares the contents of procedure manuals with the latest information and makes any necessary updates quickly and accurately.

[0522] 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.

[0523] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the text to extract key keywords and topics, means for acquiring the latest related external data, means for evaluating the age of the information by comparing the acquired external data with the extracted text, means for generating feedback based on the evaluation results and providing it to the user, means for comparing the extracted text with the latest external data and using a generative AI model to indicate parts of the information that need updating, and means for generating prompts for the generative AI model and analyzing the results. This allows work procedures and manuals to be updated automatically and efficiently, ensuring that work reflects the latest technical standards and regulations.

[0524] The "material uploading means" is a mechanism by which a user can send materials in electronic data format to a server.

[0525] "Text extraction means" refers to a technique for extracting text data from uploaded materials.

[0526] "Keyword and topic extraction" is a technique that analyzes extracted text data to find key words and themes.

[0527] "Means for acquiring the latest external data" refers to a mechanism for collecting information on the latest technical standards and regulations from external data sources.

[0528] "Data comparison and evaluation means" refers to a technique for comparing extracted text with acquired external data to determine the freshness and accuracy of the information.

[0529] A "generative AI model" is a type of artificial intelligence that can understand and generate natural language, and is primarily used for generating and analyzing text.

[0530] A "prompt sentence generation means" is a technology that creates instruction sentences to be input into a generative AI model.

[0531] The "feedback generation means" is a mechanism for presenting to the user areas that require updating or improvement based on the results of data comparison and evaluation.

[0532] Overall system configuration

[0533] This invention is a system that uploads factory work procedures and manuals, extracts text, analyzes it, compares it with the latest technical standards and regulations, and generates and provides feedback. The system consists of a server and terminals, and users access the system via the Internet. This system helps users efficiently update documents and perform work that reflects the latest information.

[0534] Uploading materials

[0535] Users upload factory work procedures and manuals in PDF format through the user interface on their devices, and the uploaded materials are sent to the server and temporarily stored.

[0536] Text Extraction and Analysis

[0537] The server extracts text from the uploaded PDF documents, for example using a text extraction library such as pdfminer.six. The extracted text is then analyzed using a natural language processing (NLP) engine such as dslim / bert-base-NER to extract key keywords and topics.

[0538] Retrieving External Data

[0539] The server sends API requests to news databases and research report databases to obtain relevant and up-to-date external data. External data acquisition involves using news APIs. The acquired data is stored as text data on the server.

[0540] Data comparison and evaluation

[0541] The server compares the extracted text with the latest external data. This process involves using a generative AI model, such as GPT-3.5-Turbo, to input a prompt and obtain a result.

[0542] Generating and Providing Feedback

[0543] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and summaries of the latest information. The generated feedback is provided to the user through a user interface.

[0544] Specific examples

[0545] For example, if a user uploads "Factory Equipment Maintenance Manual 2021.pdf", the steps are as follows: First, the document is uploaded, then text extraction and analysis are performed. During the analysis, keywords such as "equipment maintenance" and "2021" are extracted. The server then retrieves the latest data related to "equipment maintenance 2023" from the news database. The retrieved data is compared with the extracted text, and a prompt sentence is generated using a generative AI model to indicate the parts of the information that need to be updated. A specific example of a prompt sentence is:

[0546] "Compare the contents of the following text: Factory Equipment Maintenance Manual 2021.pdf with the latest data for 2023 to indicate which information is current and which parts need to be updated."

[0547] Finally, feedback is generated and provided to the user in the form of "The information in the 2021 Equipment Maintenance Manual is outdated, so please update the following to reflect the latest information: ..."

[0548] In this way, the system can assist users in quickly implementing accurate work procedures based on the latest technical standards and regulations.

[0549] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0550] Step 1: Upload your materials

[0551] Users upload factory work procedures and manuals in PDF format to the server via their terminal. The input is a PDF file, and the server temporarily stores this PDF file in its storage. The file upload process is performed via the user interface.

[0552] Step 2: Text extraction

[0553] The server extracts text from the uploaded PDF file. Here, the pdfminer.six library is used. The input is a PDF file and the output is text data. In the text extraction process, the content of the PDF file is obtained as character data.

[0554] Step 3: Keyword and topic analysis

[0555] The server analyzes the extracted text and extracts key keywords and topics. The dslim / bert-base-NER model is used. The input is the extracted text, and the output is a list of keywords and topics. The analysis process uses natural language processing to identify important words and phrases.

[0556] Step 4: Retrieving External Data

[0557] The server sends API requests to the news database and research report database to obtain the latest external data. The input is a list of keywords and topics, and the output is text data as external data. The API request process obtains the latest information based on the specified keywords.

[0558] Step 5: Data comparison and evaluation

[0559] The server compares the extracted text with the latest external data obtained and evaluates the age of the information. A generative AI model is used here. The input is the extracted text and the latest external data, and the output is the evaluation result. In the comparison and evaluation process, a prompt sentence is input to the generative AI model and the model's output is analyzed.

[0560] Step 6: Prompt generation

[0561] The server generates prompt sentences to be input to the generative AI model. The input is the extracted text and external data, and the output is the prompt sentence. The prompt sentence generation process creates the instruction sentences necessary for comparison and evaluation.

[0562] Step 7: Analyze the results

[0563] The server analyzes the output of the generative AI model and identifies areas that need updating or improvement. The input is the output of the generative AI model, and the output is specific findings. The analysis process analyzes the model output and summarizes specific corrections.

[0564] Step 8: Generate and provide feedback

[0565] The server generates feedback based on the evaluation results and provides it to the user. The input is the findings obtained from the analysis, and the output is the feedback information. In the feedback generation process, corrections and suggestions are notified to the user through a user interface.

[0566] 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.

[0567] MODE FOR CARRYING OUT THE INVENTION

[0568] Overall system configuration

[0569] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest relevant external data, and then provides feedback to the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to adjust the content of the feedback and the interface according to the user's emotions. The system is primarily composed of a server, a terminal, and an emotion engine, and users access the system via the Internet. Each component of the system and its role are described below.

[0570] Uploading materials

[0571] Users upload presentation materials and document files to the system by selecting the materials through the user interface and clicking the upload button, which sends the materials to the server and temporarily stores them in storage.

[0572] Text Extraction and Analysis

[0573] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library. The extracted text is passed to a natural language processing (NLP) engine to parse and extract key keywords and topics.

[0574] Retrieving External Data

[0575] The server sends API requests to news databases and research report databases to retrieve relevant and up-to-date external data, which is then stored on the server in text format.

[0576] Data comparison and evaluation

[0577] The server compares the text extracted from the document with the latest information obtained from external sources, assessing whether the information in the document is up-to-date or outdated and therefore in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[0578] Recognizing user emotions with an emotion engine

[0579] The emotion engine analyzes the user's text and voice input to recognize their emotions, allowing the system to understand their emotional state in real time, such as whether they are stressed, excited, or relaxed.

[0580] Generating and Providing Feedback

[0581] The server generates feedback for the user based on the results of the comparative evaluation and the emotion recognition results of the emotion engine. For example, if the user is feeling stressed, the server will express the feedback content in a gentler manner, and if the user is relaxed, it will provide detailed information, and generate feedback that corresponds to the user's emotions. The generated feedback is notified to the user through the user interface.

[0582] Interface customization

[0583] The layout and color of the user interface can be customized based on the emotions recognized by the emotion engine, for example, changing to calming colors when the user is stressed and using bright colors when relaxed.

[0584] Specific examples

[0585] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[0586] 1. Uploading materials

[0587] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0588] 2. Text Extraction and Analysis

[0589] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0590] 3. Acquiring external data

[0591] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0592] 4. Data comparison and evaluation

[0593] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0594] 5. Emotion Recognition by Emotion Engine

[0595] If the user is feeling stressed, the emotion engine will recognize this state.

[0596] 6. Generating and Providing Feedback

[0597] The server generates feedback such as, "We have the latest information on autonomous driving technology for 2023. Check out the link below.", providing gentler language in consideration of the user's stress.

[0598] 7. Interface Customization

[0599] If the user is stressed, change the interface color to a calming color such as blue or green.

[0600] Users can revise their documents based on the feedback they receive, ensuring they always create high-quality documents that reflect the latest information. In addition, the emotion engine allows users to work in a comfortable environment. In this way, the system helps users update and create documents efficiently and accurately, improving the quality of the user experience.

[0601] The processing flow will be explained below.

[0602] Step 1:

[0603] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[0604] Step 2:

[0605] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[0606] Step 3:

[0607] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[0608] Step 4:

[0609] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[0610] Step 5:

[0611] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[0612] Step 6:

[0613] The emotion engine recognizes user emotions, for example by analyzing the user's text and voice inputs to identify emotions such as stress or relaxation, using natural language processing algorithms and machine learning models.

[0614] Step 7:

[0615] The server generates feedback for the user based on the results of the comparative evaluation and the recognition results of the emotion engine. For example, if the user is feeling stressed, the server will soften the feedback.

[0616] Step 8:

[0617] The server notifies the user of the generated feedback through a user interface, including suggestions for updating outdated information and links to the latest information.

[0618] Step 9:

[0619] The emotion engine customizes the layout and color of the user interface based on the emotions it recognizes. For example, if the user is feeling stressed, the interface color will change to calming colors such as blue or green.

[0620] Step 10:

[0621] The user modifies the material based on the provided feedback, making the modifications through the user interface, and then saving the updated material back to the system.

[0622] Example 2

[0623] 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."

[0624] Conventional document management systems often have issues with uploaded documents becoming outdated, making it difficult for users to keep documents up to date. Furthermore, the user interface is fixed and cannot be flexibly changed according to the user's emotional state, potentially resulting in a poor user experience. Furthermore, feedback is generated mechanically and is not tailored to the user's emotions or needs, resulting in a lack of familiarity for users.

[0625] 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.

[0626] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract major keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for recognizing the user's emotions, means for adjusting the content of the feedback based on the recognized emotions, and means for customizing the user interface based on the recognized emotions. This makes it possible to keep the content of the materials up to date and to flexibly adjust the feedback and interface according to the user's emotional state.

[0627] "Means for uploading materials" refers to the method and process by which a user transmits document files and presentation materials to the system via the Internet and stores them on the server.

[0628] "Means for extracting text from uploaded materials" refers to the techniques and processes for analyzing the content of received document files and extracting text data.

[0629] "Means for analyzing extracted text to extract key keywords and topics" refers to the process of analyzing extracted text data using natural language processing techniques to identify important keywords and topics within the document.

[0630] "Means for obtaining relevant and up-to-date external data" means methods and processes for obtaining up-to-date data from external databases and sources based on specified keywords and topics.

[0631] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to methods and techniques for comparing internal text with external data to determine the freshness of the information or whether it needs to be updated.

[0632] The "means for generating and providing feedback to the user based on the evaluation results" is a process for preparing appropriate feedback information for the user based on the results of the comparison and evaluation, and communicating it to the user via the interface.

[0633] "Means for recognizing user emotions" refers to technologies and processes that analyze data such as text and voice input by a user and identify the user's emotional state in real time.

[0634] The "means for adjusting the content of feedback based on the recognized emotion" refers to a method and process for appropriately changing the content and expression of feedback based on the result of the user's emotion recognition.

[0635] "Means for customizing user interfaces based on recognized emotions" refers to techniques and processes for adjusting interface layout, color, and user experience based on the user's emotional state.

[0636] Overall system configuration

[0637] This invention is a system that allows users to upload materials, analyzes the text extracted from the materials, compares it with the latest relevant external data, and provides feedback to the user. The system is combined with an emotion engine that can recognize the user's emotions and adjust the feedback and interface accordingly. The main components are a server, a terminal, and the emotion engine, and users access the system via the Internet.

[0638] Uploading materials

[0639] Users upload document files and presentation materials through the system's web interface. Specifically, users click the "Upload File" button, select the materials to upload from their local environment, and click the "Send" button. The files sent from the device are received by the server and temporarily saved in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed on the user interface.

[0640] Text Extraction and Analysis

[0641] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[0642] Retrieving External Data

[0643] The server issues an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored on the server in text format.

[0644] Data comparison and evaluation

[0645] The server compares the text extracted from the document with external data using a document comparison algorithm (e.g., Cosine Similarity). This comparison determines, for example, that information in the document referring to "2021" is out of date. The results of the comparison and evaluation are scored and stored.

[0646] Recognizing user emotions with an emotion engine

[0647] Users can input messages or voice messages into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[0648] Generating and Providing Feedback

[0649] The server generates appropriate feedback for the user based on the results of the comparative evaluation and emotion recognition. For example, if the user is feeling stressed, it will provide soft feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[0650] Interface customization

[0651] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[0652] Specific examples

[0653] For example, if a user wants to upload a "2021 Report on Autonomous Driving Technology," the process would look like this:

[0654] 1. Uploading materials

[0655] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0656] 2. Text Extraction and Analysis

[0657] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0658] 3. Acquiring external data

[0659] The server sends an API request to the news database using the keyword "autonomous driving technology 2023" to retrieve the latest related news.

[0660] 4. Data comparison and evaluation

[0661] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0662] 5. Emotion Recognition by Emotion Engine

[0663] If the user is feeling stressed, the emotion engine will recognize this state.

[0664] 6. Generating and Providing Feedback

[0665] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0666] 7. Interface Customization

[0667] The user is feeling stressed, so the interface color is changed to blue or green.

[0668] In this way, the system can help users update and create materials efficiently and accurately, improving the quality of the user experience.

[0669] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0670] Step 1:

[0671] Uploading materials

[0672] The user uploads document files or presentation materials from the system's web interface. Specifically, the user clicks the "Upload File" button, selects the material to upload from the local environment (e.g., "Autonomous Driving Technology 2021.pdf"), and clicks the "Send" button. The server receives the file sent from the terminal and temporarily saves it in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed in the user interface.

[0673] Input: A file selected by the user

[0674] Output: Upload successful message

[0675] The server saves the received file in storage and displays a save success message on the user interface.

[0676] Step 2:

[0677] Text Extraction and Analysis

[0678] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[0679] Input: Saved file

[0680] Output: Extracted text and analyzed keywords and topics

[0681] The server inputs the extracted text into a natural language processing engine to analyze and extract key keywords and topics.

[0682] Step 3:

[0683] Retrieving External Data

[0684] The server sends an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored in text format on the server.

[0685] Input: Extracted keywords

[0686] Output: Retrieved external data

[0687] The server sends API requests using keywords to news databases and research report databases to retrieve and store the latest data.

[0688] Step 4:

[0689] Data comparison and evaluation

[0690] The server compares the text extracted from the document with the external data. This comparison uses a document comparison algorithm (e.g., Cosine Similarity). For example, the comparison may determine that the information in the document about "2021" is outdated. The results of the comparison and evaluation are scored and stored on the server.

[0691] Input: Extracted text and retrieved external data

[0692] Output: Information freshness evaluation result

[0693] The server uses a document comparison algorithm to compare the internal text with the external data, assess the age of the information, and store the results.

[0694] Step 5:

[0695] Recognizing user emotions with an emotion engine

[0696] The user inputs a message or voice message into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[0697] Input: User text and voice input

[0698] Output: User emotion recognition results

[0699] The server sends the input user data to the emotion engine and stores the recognized emotional state.

[0700] Step 6:

[0701] Generating and Providing Feedback

[0702] The server generates feedback for the user based on the results of the comparative evaluation of the data and the recognition results of the emotion engine. For example, if the user is feeling stressed, it generates soft-spoken feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[0703] Input: Information freshness evaluation results and emotion recognition results

[0704] Output: Feedback provided to the user

[0705] The server generates appropriate feedback based on the evaluation results and emotion recognition results and provides it to the user.

[0706] Step 7:

[0707] Interface customization

[0708] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[0709] Input: Recognition results of emotion engine

[0710] Output: Customized user interface

[0711] The server adjusts the interface based on the emotion recognition results, providing a comfortable working environment for the user.

[0712] ---

[0713] Through these steps, the system helps users update and create documents efficiently and accurately, while improving the quality of the user experience.

[0714] (Application example 2)

[0715] 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."

[0716] When autonomous vehicles continue to operate, they are required to constantly update the latest traffic and road regulation information. However, if the driver feels fatigued or stressed, it may become difficult for them to accurately and quickly grasp this information. Therefore, in addition to updating the information, it is necessary to provide feedback and adjust the interface according to the driver's emotional state.

[0717] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract main keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, and means for recognizing the user's emotions using an emotion engine and adjusting the content of the feedback and the interface according to the user's emotions. This allows the driver to appropriately receive the latest traffic information and maintain a comfortable driving environment through appropriate feedback according to the user's emotional state.

[0718] "Documents" are documents or files that detail information.

[0719] An "uploading means" is a system or function that allows a user to send data from their device to a remote server.

[0720] "Text extraction methods" are techniques and algorithms used to extract textual information from documents and files.

[0721] "Means for analyzing and extracting key keywords and topics" refers to a technique for analyzing extracted text information and identifying important terms and topics from it.

[0722] "Means for obtaining the latest external data" are systems and processes for collecting current information from the Internet or databases.

[0723] The "means for comparing and assessing the age of information" is a function for comparing the collected external data with the extracted text information to determine how recent the information is.

[0724] "Means for generating feedback and providing it to users" refers to a system or function that creates information or advice based on the evaluation results and presents it to users.

[0725] An "emotion engine" is a technology or algorithm that analyzes and recognizes a user's emotional state from their input (voice, text, etc.).

[0726] "Means for recognizing emotions and adjusting the content of feedback and interface" refers to a system or function for changing the content and display format of feedback to the user based on the recognized emotional state.

[0727] Overall system configuration

[0728] This invention is a system that provides feedback based on the latest traffic information and the driver's emotional state during the operation of an autonomous vehicle, helping the driver continue driving comfortably and efficiently. The system mainly consists of a server, an in-vehicle computer, and an emotion recognition engine.

[0729] Uploading materials

[0730] The driver uploads a document, such as "New Traffic Regulation Information 2023.pdf," through the autonomous vehicle's navigation system. By clicking the upload button, the document file is sent to the server and temporarily stored.

[0731] Text Extraction and Analysis

[0732] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The extracted text is passed to a natural language processing (NLP) engine, which parses and extracts key keywords and topics.

[0733] Retrieving External Data

[0734] The server sends API requests to traffic information systems and news databases to obtain the latest traffic information. The obtained data is stored on the server in text format. The API library used is, for example, "requests".

[0735] Data comparison and evaluation

[0736] The server compares the text extracted from the document with the latest information obtained from external sources, and evaluates whether the information in the document is up-to-date or needs to be updated. The evaluation is performed automatically using comparison algorithms and scoring methods (e.g., similarity calculations).

[0737] Driver emotion recognition using emotion engine

[0738] The vehicle's computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state, allowing the system to understand in real time whether the driver is stressed, tired, or relaxed.

[0739] Generating and Providing Feedback

[0740] The server generates feedback for the driver based on the comparison of the document with external data and the results of the emotion recognition engine. For example, if the driver is feeling stressed, the server generates feedback that corresponds to the driver's emotions, such as softening the content of the feedback and providing more detailed information. The generated feedback is notified to the driver through the navigation system.

[0741] Interface customization

[0742] The emotion engine can customize the layout and color of the in-vehicle navigation system based on the driver's emotions, for example, changing to calming colors like blue and green if the driver is stressed, and using brighter colors if the driver is relaxed.

[0743] Specific examples

[0744] If a driver uploads "New Traffic Regulation Information 2023.pdf", the steps are as follows:

[0745] 1. Uploading materials

[0746] "New Traffic Regulation Information 2023.pdf" has been uploaded.

[0747] Example prompt: "Please upload New Traffic Regulation Information 2023.pdf."

[0748] 2. Text Extraction and Analysis

[0749] The server extracts text from the PDF and uses an NLP engine to extract keywords such as "2023," "traffic regulations," and "new regulations."

[0750] 3. Acquiring external data

[0751] The server sends an API request to the traffic information system to obtain the latest traffic information.

[0752] API request example: "requests.get("https: / / api.trafficinfo.com / data?year=2023")"

[0753] 4. Data comparison and evaluation

[0754] The server compares the extracted text with external data and evaluates whether it needs to be updated to reflect the latest information.

[0755] 5. Emotion Recognition by Emotion Engine

[0756] The emotion engine recognizes the driver's stress level and fatigue.

[0757] Example prompt: "Analyze the driver's emotional state and adjust feedback."

[0758] 6. Generating and Providing Feedback

[0759] The server generates soft feedback saying, "We have the latest 2023 traffic regulation information. Check the link below."

[0760] Example feedback: "Please check the latest traffic regulations and drive safely."

[0761] 7. Interface Customization

[0762] If the driver is feeling stressed, the navigation system changes the background color to blue or green.

[0763] Example prompt: "Due to high stress levels, we are changing the color tone of the navigation system."

[0764] In this way, the system helps drivers receive optimal information and provides a driving environment that takes their emotional state into consideration, supporting comfortable and safe driving.

[0765] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0766] Step 1:

[0767] The user uploads a document file (e.g., "New Traffic Regulation Information 2023.pdf") through the navigation system of the autonomous vehicle. When the upload button is clicked, the document file is sent to the server. At this stage, the input is the document file from the user, and the output is the document file saved on the server.

[0768] Step 2:

[0769] The server determines the format of the saved material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The input is the material file, and the output is the extracted text data.

[0770] Step 3:

[0771] The server passes the extracted text to a natural language processing (NLP) engine to analyze it for key keywords and topics. At this point, the input is the extracted text, and the output is a list of key keywords and topics. Specifically, keyword extraction and topic modeling are performed.

[0772] Step 4:

[0773] The server sends API requests to traffic information systems and news databases to get the latest traffic information. The input is the API query, and the output is the retrieved latest traffic information data. The data is collected using an API library (e.g., "requests").

[0774] Step 5:

[0775] The server compares the retrieved external data with the extracted text to assess the age of the information. The input is the external data and the extracted text, and the output is an assessment of the age of the information and whether it needs to be updated. A comparison algorithm or scoring method (e.g., similarity calculation) is used.

[0776] Step 6:

[0777] The in-vehicle computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state. At this point, the input is voice or text input from the driver, and the output is an evaluation of the driver's emotional state.

[0778] Step 7:

[0779] The server generates feedback for the driver based on the comparative evaluation results and emotion recognition results. The input is the information evaluation results and the driver's emotional state, and the output is the generated feedback message. The server provides softer expressions and detailed information according to the driver's emotional state.

[0780] Step 8:

[0781] The server notifies the driver of the generated feedback through the navigation system. The input is the generated feedback message, and the output is the notification provided to the driver. Specific operations include displaying the feedback message and an audio notification.

[0782] Step 9:

[0783] The in-vehicle computer customizes the navigation system interface based on the emotional state recognized by the emotion recognition engine. The input is the driver's emotional state, and the output is an adjusted interface layout and color tone. Specific actions include changing the background color and adjusting the layout.

[0784] 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.

[0785] 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.

[0786] 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.

[0787] [Third embodiment]

[0788] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0789] 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.

[0790] 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).

[0791] 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.

[0792] 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.

[0793] 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).

[0794] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0795] 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.

[0796] 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.

[0797] 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.

[0798] 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.

[0799] 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."

[0800] MODE FOR CARRYING OUT THE INVENTION

[0801] Overall system configuration

[0802] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest related external data, and provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. Each component of the system and its role are described below.

[0803] Uploading materials

[0804] Users upload presentation materials and document files to the system through a user interface, and the uploaded materials are sent to the server and temporarily stored.

[0805] Text Extraction and Analysis

[0806] The server extracts text from the uploaded material (using an appropriate text extraction library for PDF documents, another for PowerPoint documents, for example), and then analyzes the extracted text using a natural language processing (NLP) engine to extract key keywords and topics.

[0807] Retrieving External Data

[0808] The server sends API requests to news databases and research report databases to obtain the latest relevant external data, which is then stored on the server as text data.

[0809] Data comparison and evaluation

[0810] The server compares the extracted text with the latest external data it has retrieved, assessing whether the information in the document is up-to-date or outdated and in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[0811] Generating and Providing Feedback

[0812] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface.

[0813] Specific examples

[0814] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[0815] 1. Uploading materials

[0816] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0817] 2. Text Extraction and Analysis

[0818] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0819] 3. Acquiring external data

[0820] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0821] 4. Data comparison and evaluation

[0822] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0823] 5. Generating and Providing Feedback

[0824] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0825] Users can revise their materials based on the feedback they receive, ensuring that they always reflect the latest information and are of high quality. In this way, the system helps users update and create materials efficiently and accurately.

[0826] The processing flow will be explained below.

[0827] Step 1:

[0828] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[0829] Step 2:

[0830] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[0831] Step 3:

[0832] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[0833] Step 4:

[0834] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[0835] Step 5:

[0836] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[0837] Step 6:

[0838] The server generates feedback for the user based on the results of the comparative evaluation, such as making specific suggestions like, "You're using information from 2021, but here's the latest information for 2023."

[0839] Step 7:

[0840] The server notifies the user of the generated feedback through a user interface, and the user is provided with an interface to review the feedback and update the material.

[0841] Step 8:

[0842] The user modifies the material based on the provided feedback, performs the update through the user interface, and then saves the updated material back to the system.

[0843] In this way, the system helps users create and update materials based on the latest information, improving the quality of presentations and reports.

[0844] Example 1

[0845] 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."

[0846] In conventional document creation systems, manual confirmation was required to determine whether the content of documents uploaded by users was based on the latest information, making update work cumbersome. It was also difficult to effectively obtain the latest external data and provide appropriate feedback to reflect that information in documents.

[0847] 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.

[0848] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract key keywords and topics, means for acquiring the latest related external data, means for comparing the extracted text with the acquired external data to evaluate the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for applying an appropriate text extraction library depending on the format of the materials, means for analyzing the extracted text using a natural language processing engine, means for acquiring related external data by sending an API request, and means for comparing text using document similarity calculations and machine learning models. This allows users to significantly improve the efficiency of updating materials and always create high-quality materials that reflect the latest information.

[0849] "Means for uploading materials" refers to a function that provides an interface for users to send materials to the system via the Internet.

[0850] "Means for extracting text from uploaded materials" refers to the libraries or software used by the server to analyze the contents of uploaded files and extract text data.

[0851] "Means for analyzing extracted text to extract key keywords and topics" refers to the function by which the server uses a natural language processing engine to find important keywords and topics from the extracted text.

[0852] The "means for obtaining the latest relevant external data" refers to a function in which the server sends an API request to an external database or information source to obtain the latest relevant information.

[0853] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to the algorithms or models that the server uses to compare the content of the material with the external data to determine whether the information is up-to-date or out-of-date.

[0854] The "means of generating feedback based on the evaluation results and providing it to the user" is a function in which the server provides the user with specific improvement suggestions and the latest information based on the evaluation results of the age of the information.

[0855] "Means for applying an appropriate text extraction library according to the format of the document" refers to a function in which the server automatically identifies the file format of the uploaded document and extracts text using a library appropriate for each format, such as PDF or PowerPoint.

[0856] "Means for analyzing extracted text using a natural language processing engine" refers to a function in which the server uses natural language processing technology to perform semantic analysis and keyword extraction on the extracted text.

[0857] "Means for sending API requests to obtain relevant external data" refers to the function by which the server periodically or as needed creates and sends API requests to external databases or information sources to obtain the latest information.

[0858] "Means for comparing texts using document similarity calculations or machine learning models" refers to a function in which the server uses machine learning models or numerical algorithms to compare the text of a document with the text of external data and evaluate the similarities and differences between them.

[0859] MODE FOR CARRYING OUT THE INVENTION

[0860] Overall system configuration

[0861] This invention is a system that analyzes the content of materials uploaded by users, compares them with the latest external data, and then provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. The specific components of the system and their operation are described below.

[0862] Uploading materials

[0863] Users log in to the system via a browser or a dedicated application and upload documents. This process is carried out through the user interface, and the files specified by the user are sent to the server. Supported file formats include PDF and PowerPoint, and the sent files are temporarily stored on the server.

[0864] Text Extraction and Analysis

[0865] The server determines the format of the uploaded material and extracts the text using the appropriate text extraction library: for PDF materials, it uses the Apache PDFBox library, for PowerPoint materials it uses the Apache POI library, and this extracted text is sent to a natural language processing engine (e.g., SpaCy, NLTK) to extract key keywords and topics.

[0866] Retrieving External Data

[0867] The server retrieves the latest relevant external data based on the keywords extracted from the extracted text. External data sources include news databases and research report databases. The server sends a RESTful API request to retrieve the latest relevant information. An API request uses a format such as requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}).

[0868] Data comparison and evaluation

[0869] The server uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) or machine learning models such as TF-IDF and BERT to compare the text of the document with the acquired external data. For example, when using Cosine Similarity, the calculation is done as follows: cosine_similarity(vectorized_textA, vectorized_textB). This allows the server to evaluate whether the information in the document is up-to-date or if it is old and needs to be updated.

[0870] Generating and Providing Feedback

[0871] Based on the evaluation results, the server generates feedback to provide to the user. This feedback includes specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface. For example, a message such as "The latest information on autonomous driving technology for 2023 is available. Please check the link below." is generated and displayed as feedback.

[0872] Specific examples

[0873] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the process will proceed as follows:

[0874] 1. Uploading materials

[0875] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0876] 2. Text Extraction and Analysis

[0877] The server uses Apache PDFBox to extract text from the PDF and a natural language processing engine (e.g., SpaCy) to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0878] 3. Acquiring external data

[0879] The server sends a RESTful API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0880] 4. Data comparison and evaluation

[0881] The server compares the retrieved news with the extracted text and uses a document similarity algorithm (e.g., Cosine Similarity) to determine that the "2021" information in the document is outdated.

[0882] 5. Generating and Providing Feedback

[0883] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[0884] In this way, the system helps users to efficiently update materials and create high-quality materials that always reflect the latest information.

[0885] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0886] Step 1:

[0887] A user logs into the system using a browser or a dedicated application, clicks the upload button, and selects a document. The input is a file selected by the user (e.g., "Autonomous Driving Technology 2021.pdf"). This file is sent to the server via the Internet. Specifically, the user selects the file using a standard file search window and clicks the upload button. The server receives the file and temporarily stores it in storage.

[0888] Step 2:

[0889] The server determines the format of the uploaded file and extracts the text using the appropriate text extraction library. For example, it uses the Apache PDFBox library for PDF format documents and the Apache POI library for PowerPoint format documents. The input contains the uploaded file. Specifically, it calls the ApachePDFBox.load(file) or ApachePOI.load(file) method to extract text data from the file. The extracted text data is returned as the output.

[0890] Step 3:

[0891] The server sends the extracted text to a natural language processing engine to extract key keywords and topics. The extracted text data is the input. The text is analyzed using a natural language processing engine (e.g., SpaCy, NLTK). Specifically, the model is loaded with nlp = spacy.load('en_core_web_sm') and the text is analyzed with doc = nlp(extracted_text). The output is a list of key keywords and topics.

[0892] Step 4:

[0893] The server retrieves the latest related external data based on the extracted keywords. The input is a list of extracted keywords. A RESTful API request is used to retrieve the external data. Specifically, a request of requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}) is sent to retrieve the latest data. The output is the retrieved external data in text format.

[0894] Step 5:

[0895] The server compares the text of the document with the acquired external data. The inputs include the text of the document and the acquired external data. It uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) and machine learning models such as TF-IDF and BERT. Specifically, it evaluates the similarity using cosine_similarity(vectorized_textA, vectorized_textB). The output is a score indicating the age of the information.

[0896] Step 6:

[0897] The server generates feedback based on the age of the information and provides it to the user. The inputs are the evaluation score and the acquired external data. The server generates a specific feedback message based on the evaluation results. Specifically, it creates a message such as "The latest information on autonomous driving technology as of 2023 is available. Please check the link below." and displays it with user_interface.display(feedback_message). The output is a feedback message to the user.

[0898] Through each step, the system assists users in updating materials efficiently and accurately.

[0899] (Application example 1)

[0900] 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."

[0901] In current factory operations, work procedures and manuals need to be updated regularly, but this process is time-consuming and it is difficult to ensure that they reflect the latest technical standards and regulations. This can also reduce work efficiency and affect quality and safety. To solve this problem, a system is needed that automatically compares the contents of procedure manuals with the latest information and makes any necessary updates quickly and accurately.

[0902] 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.

[0903] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the text to extract key keywords and topics, means for acquiring the latest related external data, means for evaluating the age of the information by comparing the acquired external data with the extracted text, means for generating feedback based on the evaluation results and providing it to the user, means for comparing the extracted text with the latest external data and using a generative AI model to indicate parts of the information that need updating, and means for generating prompts for the generative AI model and analyzing the results. This allows work procedures and manuals to be updated automatically and efficiently, ensuring that work reflects the latest technical standards and regulations.

[0904] The "material uploading means" is a mechanism by which a user can send materials in electronic data format to a server.

[0905] "Text extraction means" refers to a technique for extracting text data from uploaded materials.

[0906] "Keyword and topic extraction" is a technique that analyzes extracted text data to find key words and themes.

[0907] "Means for acquiring the latest external data" refers to a mechanism for collecting information on the latest technical standards and regulations from external data sources.

[0908] "Data comparison and evaluation means" refers to a technique for comparing extracted text with acquired external data to determine the freshness and accuracy of the information.

[0909] A "generative AI model" is a type of artificial intelligence that can understand and generate natural language, and is primarily used for generating and analyzing text.

[0910] A "prompt sentence generation means" is a technology that creates instruction sentences to be input into a generative AI model.

[0911] The "feedback generation means" is a mechanism for presenting to the user areas that require updating or improvement based on the results of data comparison and evaluation.

[0912] Overall system configuration

[0913] This invention is a system that uploads factory work procedures and manuals, extracts text, analyzes it, compares it with the latest technical standards and regulations, and generates and provides feedback. The system consists of a server and terminals, and users access the system via the Internet. This system helps users efficiently update documents and perform work that reflects the latest information.

[0914] Uploading materials

[0915] Users upload factory work procedures and manuals in PDF format through the user interface on their devices, and the uploaded materials are sent to the server and temporarily stored.

[0916] Text Extraction and Analysis

[0917] The server extracts text from the uploaded PDF documents, for example using a text extraction library such as pdfminer.six. The extracted text is then analyzed using a natural language processing (NLP) engine such as dslim / bert-base-NER to extract key keywords and topics.

[0918] Retrieving External Data

[0919] The server sends API requests to news databases and research report databases to obtain relevant and up-to-date external data. External data acquisition involves using news APIs. The acquired data is stored as text data on the server.

[0920] Data comparison and evaluation

[0921] The server compares the extracted text with the latest external data. This process involves using a generative AI model, such as GPT-3.5-Turbo, to input a prompt and obtain a result.

[0922] Generating and Providing Feedback

[0923] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and summaries of the latest information. The generated feedback is provided to the user through a user interface.

[0924] Specific examples

[0925] For example, if a user uploads "Factory Equipment Maintenance Manual 2021.pdf", the steps are as follows: First, the document is uploaded, then text extraction and analysis are performed. During the analysis, keywords such as "equipment maintenance" and "2021" are extracted. The server then retrieves the latest data related to "equipment maintenance 2023" from the news database. The retrieved data is compared with the extracted text, and a prompt sentence is generated using a generative AI model to indicate the parts of the information that need to be updated. A specific example of a prompt sentence is:

[0926] "Compare the contents of the following text: Factory Equipment Maintenance Manual 2021.pdf with the latest data for 2023 to indicate which information is current and which parts need to be updated."

[0927] Finally, feedback is generated and provided to the user in the form of "The information in the 2021 Equipment Maintenance Manual is outdated, so please update the following to reflect the latest information: ..."

[0928] In this way, the system can assist users in quickly implementing accurate work procedures based on the latest technical standards and regulations.

[0929] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0930] Step 1: Upload your materials

[0931] Users upload factory work procedures and manuals in PDF format to the server via their terminal. The input is a PDF file, and the server temporarily stores this PDF file in its storage. The file upload process is performed via the user interface.

[0932] Step 2: Text extraction

[0933] The server extracts text from the uploaded PDF file. Here, the pdfminer.six library is used. The input is a PDF file and the output is text data. In the text extraction process, the content of the PDF file is obtained as character data.

[0934] Step 3: Keyword and topic analysis

[0935] The server analyzes the extracted text and extracts key keywords and topics. The dslim / bert-base-NER model is used. The input is the extracted text, and the output is a list of keywords and topics. The analysis process uses natural language processing to identify important words and phrases.

[0936] Step 4: Retrieving External Data

[0937] The server sends API requests to the news database and research report database to obtain the latest external data. The input is a list of keywords and topics, and the output is text data as external data. The API request process obtains the latest information based on the specified keywords.

[0938] Step 5: Data comparison and evaluation

[0939] The server compares the extracted text with the latest external data obtained and evaluates the age of the information. A generative AI model is used here. The input is the extracted text and the latest external data, and the output is the evaluation result. In the comparison and evaluation process, a prompt sentence is input to the generative AI model and the model's output is analyzed.

[0940] Step 6: Prompt generation

[0941] The server generates prompt sentences to be input to the generative AI model. The input is the extracted text and external data, and the output is the prompt sentence. The prompt sentence generation process creates the instruction sentences necessary for comparison and evaluation.

[0942] Step 7: Analyze the results

[0943] The server analyzes the output of the generative AI model and identifies areas that need updating or improvement. The input is the output of the generative AI model, and the output is specific findings. The analysis process analyzes the model output and summarizes specific corrections.

[0944] Step 8: Generate and provide feedback

[0945] The server generates feedback based on the evaluation results and provides it to the user. The input is the findings obtained from the analysis, and the output is the feedback information. In the feedback generation process, corrections and suggestions are notified to the user through a user interface.

[0946] 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.

[0947] MODE FOR CARRYING OUT THE INVENTION

[0948] Overall system configuration

[0949] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest relevant external data, and then provides feedback to the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to adjust the content of the feedback and the interface according to the user's emotions. The system is primarily composed of a server, a terminal, and an emotion engine, and users access the system via the Internet. Each component of the system and its role are described below.

[0950] Uploading materials

[0951] Users upload presentation materials and document files to the system by selecting the materials through the user interface and clicking the upload button, which sends the materials to the server and temporarily stores them in storage.

[0952] Text Extraction and Analysis

[0953] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library. The extracted text is passed to a natural language processing (NLP) engine to parse and extract key keywords and topics.

[0954] Retrieving External Data

[0955] The server sends API requests to news databases and research report databases to retrieve relevant and up-to-date external data, which is then stored on the server in text format.

[0956] Data comparison and evaluation

[0957] The server compares the text extracted from the document with the latest information obtained from external sources, assessing whether the information in the document is up-to-date or outdated and therefore in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[0958] Recognizing user emotions with an emotion engine

[0959] The emotion engine analyzes the user's text and voice input to recognize their emotions, allowing the system to understand their emotional state in real time, such as whether they are stressed, excited, or relaxed.

[0960] Generating and Providing Feedback

[0961] The server generates feedback for the user based on the results of the comparative evaluation and the emotion recognition results of the emotion engine. For example, if the user is feeling stressed, the server will express the feedback content in a gentler manner, and if the user is relaxed, it will provide detailed information, and generate feedback that corresponds to the user's emotions. The generated feedback is notified to the user through the user interface.

[0962] Interface customization

[0963] The layout and color of the user interface can be customized based on the emotions recognized by the emotion engine, for example, changing to calming colors when the user is stressed and using bright colors when relaxed.

[0964] Specific examples

[0965] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[0966] 1. Uploading materials

[0967] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[0968] 2. Text Extraction and Analysis

[0969] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[0970] 3. Acquiring external data

[0971] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[0972] 4. Data comparison and evaluation

[0973] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[0974] 5. Emotion Recognition by Emotion Engine

[0975] If the user is feeling stressed, the emotion engine will recognize this state.

[0976] 6. Generating and Providing Feedback

[0977] The server generates feedback such as, "We have the latest information on autonomous driving technology for 2023. Check out the link below.", providing gentler language in consideration of the user's stress.

[0978] 7. Interface Customization

[0979] If the user is stressed, change the interface color to a calming color such as blue or green.

[0980] Users can revise their documents based on the feedback they receive, ensuring they always create high-quality documents that reflect the latest information. In addition, the emotion engine allows users to work in a comfortable environment. In this way, the system helps users update and create documents efficiently and accurately, improving the quality of the user experience.

[0981] The processing flow will be explained below.

[0982] Step 1:

[0983] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[0984] Step 2:

[0985] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[0986] Step 3:

[0987] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[0988] Step 4:

[0989] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[0990] Step 5:

[0991] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[0992] Step 6:

[0993] The emotion engine recognizes user emotions, for example by analyzing the user's text and voice inputs to identify emotions such as stress or relaxation, using natural language processing algorithms and machine learning models.

[0994] Step 7:

[0995] The server generates feedback for the user based on the results of the comparative evaluation and the recognition results of the emotion engine. For example, if the user is feeling stressed, the server will soften the feedback.

[0996] Step 8:

[0997] The server notifies the user of the generated feedback through a user interface, including suggestions for updating outdated information and links to the latest information.

[0998] Step 9:

[0999] The emotion engine customizes the layout and color of the user interface based on the emotions it recognizes. For example, if the user is feeling stressed, the interface color will change to calming colors such as blue or green.

[1000] Step 10:

[1001] The user modifies the material based on the provided feedback, making the modifications through the user interface, and then saving the updated material back to the system.

[1002] Example 2

[1003] 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."

[1004] Conventional document management systems often have issues with uploaded documents becoming outdated, making it difficult for users to keep documents up to date. Furthermore, the user interface is fixed and cannot be flexibly changed according to the user's emotional state, potentially resulting in a poor user experience. Furthermore, feedback is generated mechanically and is not tailored to the user's emotions or needs, resulting in a lack of familiarity for users.

[1005] 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.

[1006] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract major keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for recognizing the user's emotions, means for adjusting the content of the feedback based on the recognized emotions, and means for customizing the user interface based on the recognized emotions. This makes it possible to keep the content of the materials up to date and to flexibly adjust the feedback and interface according to the user's emotional state.

[1007] "Means for uploading materials" refers to the method and process by which a user transmits document files and presentation materials to the system via the Internet and stores them on the server.

[1008] "Means for extracting text from uploaded materials" refers to the techniques and processes for analyzing the content of received document files and extracting text data.

[1009] "Means for analyzing extracted text to extract key keywords and topics" refers to the process of analyzing extracted text data using natural language processing techniques to identify important keywords and topics within the document.

[1010] "Means for obtaining relevant and up-to-date external data" means methods and processes for obtaining up-to-date data from external databases and sources based on specified keywords and topics.

[1011] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to methods and techniques for comparing internal text with external data to determine the freshness of the information or whether it needs to be updated.

[1012] The "means for generating and providing feedback to the user based on the evaluation results" is a process for preparing appropriate feedback information for the user based on the results of the comparison and evaluation, and communicating it to the user via the interface.

[1013] "Means for recognizing user emotions" refers to technologies and processes that analyze data such as text and voice input by a user and identify the user's emotional state in real time.

[1014] The "means for adjusting the content of feedback based on the recognized emotion" refers to a method and process for appropriately changing the content and expression of feedback based on the result of the user's emotion recognition.

[1015] "Means for customizing user interfaces based on recognized emotions" refers to techniques and processes for adjusting interface layout, color, and user experience based on the user's emotional state.

[1016] Overall system configuration

[1017] This invention is a system that allows users to upload materials, analyzes the text extracted from the materials, compares it with the latest relevant external data, and provides feedback to the user. The system is combined with an emotion engine that can recognize the user's emotions and adjust the feedback and interface accordingly. The main components are a server, a terminal, and the emotion engine, and users access the system via the Internet.

[1018] Uploading materials

[1019] Users upload document files and presentation materials through the system's web interface. Specifically, users click the "Upload File" button, select the materials to upload from their local environment, and click the "Send" button. The files sent from the device are received by the server and temporarily saved in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed on the user interface.

[1020] Text Extraction and Analysis

[1021] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[1022] Retrieving External Data

[1023] The server issues an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored on the server in text format.

[1024] Data comparison and evaluation

[1025] The server compares the text extracted from the document with external data using a document comparison algorithm (e.g., Cosine Similarity). This comparison determines, for example, that information in the document referring to "2021" is out of date. The results of the comparison and evaluation are scored and stored.

[1026] Recognizing user emotions with an emotion engine

[1027] Users can input messages or voice messages into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[1028] Generating and Providing Feedback

[1029] The server generates appropriate feedback for the user based on the results of the comparative evaluation and emotion recognition. For example, if the user is feeling stressed, it will provide soft feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[1030] Interface customization

[1031] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[1032] Specific examples

[1033] For example, if a user wants to upload a "2021 Report on Autonomous Driving Technology," the process would look like this:

[1034] 1. Uploading materials

[1035] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[1036] 2. Text Extraction and Analysis

[1037] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[1038] 3. Acquiring external data

[1039] The server sends an API request to the news database using the keyword "autonomous driving technology 2023" to retrieve the latest related news.

[1040] 4. Data comparison and evaluation

[1041] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[1042] 5. Emotion Recognition by Emotion Engine

[1043] If the user is feeling stressed, the emotion engine will recognize this state.

[1044] 6. Generating and Providing Feedback

[1045] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[1046] 7. Interface Customization

[1047] The user is feeling stressed, so the interface color is changed to blue or green.

[1048] In this way, the system can help users update and create materials efficiently and accurately, improving the quality of the user experience.

[1049] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1050] Step 1:

[1051] Uploading materials

[1052] The user uploads document files or presentation materials from the system's web interface. Specifically, the user clicks the "Upload File" button, selects the material to upload from the local environment (e.g., "Autonomous Driving Technology 2021.pdf"), and clicks the "Send" button. The server receives the file sent from the terminal and temporarily saves it in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed in the user interface.

[1053] Input: A file selected by the user

[1054] Output: Upload successful message

[1055] The server saves the received file in storage and displays a save success message on the user interface.

[1056] Step 2:

[1057] Text Extraction and Analysis

[1058] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[1059] Input: Saved file

[1060] Output: Extracted text and analyzed keywords and topics

[1061] The server inputs the extracted text into a natural language processing engine to analyze and extract key keywords and topics.

[1062] Step 3:

[1063] Retrieving External Data

[1064] The server sends an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored in text format on the server.

[1065] Input: Extracted keywords

[1066] Output: Retrieved external data

[1067] The server sends API requests using keywords to news databases and research report databases to retrieve and store the latest data.

[1068] Step 4:

[1069] Data comparison and evaluation

[1070] The server compares the text extracted from the document with the external data. This comparison uses a document comparison algorithm (e.g., Cosine Similarity). For example, the comparison may determine that the information in the document about "2021" is outdated. The results of the comparison and evaluation are scored and stored on the server.

[1071] Input: Extracted text and retrieved external data

[1072] Output: Information freshness evaluation result

[1073] The server uses a document comparison algorithm to compare the internal text with the external data, assess the age of the information, and store the results.

[1074] Step 5:

[1075] Recognizing user emotions with an emotion engine

[1076] The user inputs a message or voice message into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[1077] Input: User text and voice input

[1078] Output: User emotion recognition results

[1079] The server sends the input user data to the emotion engine and stores the recognized emotional state.

[1080] Step 6:

[1081] Generating and Providing Feedback

[1082] The server generates feedback for the user based on the results of the comparative evaluation of the data and the recognition results of the emotion engine. For example, if the user is feeling stressed, it generates soft-spoken feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[1083] Input: Information freshness evaluation results and emotion recognition results

[1084] Output: Feedback provided to the user

[1085] The server generates appropriate feedback based on the evaluation results and emotion recognition results and provides it to the user.

[1086] Step 7:

[1087] Interface customization

[1088] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[1089] Input: Recognition results of emotion engine

[1090] Output: Customized user interface

[1091] The server adjusts the interface based on the emotion recognition results, providing a comfortable working environment for the user.

[1092] ---

[1093] Through these steps, the system helps users update and create documents efficiently and accurately, while improving the quality of the user experience.

[1094] (Application example 2)

[1095] 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."

[1096] When autonomous vehicles continue to operate, they are required to constantly update the latest traffic and road regulation information. However, if the driver feels fatigued or stressed, it may become difficult for them to accurately and quickly grasp this information. Therefore, in addition to updating the information, it is necessary to provide feedback and adjust the interface according to the driver's emotional state.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract main keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, and means for recognizing the user's emotions using an emotion engine and adjusting the content of the feedback and the interface according to the user's emotions. This allows the driver to appropriately receive the latest traffic information and maintain a comfortable driving environment through appropriate feedback according to the user's emotional state.

[1098] "Documents" are documents or files that detail information.

[1099] An "uploading means" is a system or function that allows a user to send data from their device to a remote server.

[1100] "Text extraction methods" are techniques and algorithms used to extract textual information from documents and files.

[1101] "Means for analyzing and extracting key keywords and topics" refers to a technique for analyzing extracted text information and identifying important terms and topics from it.

[1102] "Means for obtaining the latest external data" are systems and processes for collecting current information from the Internet or databases.

[1103] The "means for comparing and assessing the age of information" is a function for comparing the collected external data with the extracted text information to determine how recent the information is.

[1104] "Means for generating feedback and providing it to users" refers to a system or function that creates information or advice based on the evaluation results and presents it to users.

[1105] An "emotion engine" is a technology or algorithm that analyzes and recognizes a user's emotional state from their input (voice, text, etc.).

[1106] "Means for recognizing emotions and adjusting the content of feedback and interface" refers to a system or function for changing the content and display format of feedback to the user based on the recognized emotional state.

[1107] Overall system configuration

[1108] This invention is a system that provides feedback based on the latest traffic information and the driver's emotional state during the operation of an autonomous vehicle, helping the driver continue driving comfortably and efficiently. The system mainly consists of a server, an in-vehicle computer, and an emotion recognition engine.

[1109] Uploading materials

[1110] The driver uploads a document, such as "New Traffic Regulation Information 2023.pdf," through the autonomous vehicle's navigation system. By clicking the upload button, the document file is sent to the server and temporarily stored.

[1111] Text Extraction and Analysis

[1112] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The extracted text is passed to a natural language processing (NLP) engine, which parses and extracts key keywords and topics.

[1113] Retrieving External Data

[1114] The server sends API requests to traffic information systems and news databases to obtain the latest traffic information. The obtained data is stored on the server in text format. The API library used is, for example, "requests".

[1115] Data comparison and evaluation

[1116] The server compares the text extracted from the document with the latest information obtained from external sources, and evaluates whether the information in the document is up-to-date or needs to be updated. The evaluation is performed automatically using comparison algorithms and scoring methods (e.g., similarity calculations).

[1117] Driver emotion recognition using emotion engine

[1118] The vehicle's computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state, allowing the system to understand in real time whether the driver is stressed, tired, or relaxed.

[1119] Generating and Providing Feedback

[1120] The server generates feedback for the driver based on the comparison of the document with external data and the results of the emotion recognition engine. For example, if the driver is feeling stressed, the server generates feedback that corresponds to the driver's emotions, such as softening the content of the feedback and providing more detailed information. The generated feedback is notified to the driver through the navigation system.

[1121] Interface customization

[1122] The emotion engine can customize the layout and color of the in-vehicle navigation system based on the driver's emotions, for example, changing to calming colors like blue and green if the driver is stressed, and using brighter colors if the driver is relaxed.

[1123] Specific examples

[1124] If a driver uploads "New Traffic Regulation Information 2023.pdf", the steps are as follows:

[1125] 1. Uploading materials

[1126] "New Traffic Regulation Information 2023.pdf" has been uploaded.

[1127] Example prompt: "Please upload New Traffic Regulation Information 2023.pdf."

[1128] 2. Text Extraction and Analysis

[1129] The server extracts text from the PDF and uses an NLP engine to extract keywords such as "2023," "traffic regulations," and "new regulations."

[1130] 3. Acquiring external data

[1131] The server sends an API request to the traffic information system to obtain the latest traffic information.

[1132] API request example: "requests.get("https: / / api.trafficinfo.com / data?year=2023")"

[1133] 4. Data comparison and evaluation

[1134] The server compares the extracted text with external data and evaluates whether it needs to be updated to reflect the latest information.

[1135] 5. Emotion Recognition by Emotion Engine

[1136] The emotion engine recognizes the driver's stress level and fatigue.

[1137] Example prompt: "Analyze the driver's emotional state and adjust feedback."

[1138] 6. Generating and Providing Feedback

[1139] The server generates soft feedback saying, "We have the latest 2023 traffic regulation information. Check the link below."

[1140] Example feedback: "Please check the latest traffic regulations and drive safely."

[1141] 7. Interface Customization

[1142] If the driver is feeling stressed, the navigation system changes the background color to blue or green.

[1143] Example prompt: "Due to high stress levels, we are changing the color tone of the navigation system."

[1144] In this way, the system helps drivers receive optimal information and provides a driving environment that takes their emotional state into consideration, supporting comfortable and safe driving.

[1145] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1146] Step 1:

[1147] The user uploads a document file (e.g., "New Traffic Regulation Information 2023.pdf") through the navigation system of the autonomous vehicle. When the upload button is clicked, the document file is sent to the server. At this stage, the input is the document file from the user, and the output is the document file saved on the server.

[1148] Step 2:

[1149] The server determines the format of the saved material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The input is the material file, and the output is the extracted text data.

[1150] Step 3:

[1151] The server passes the extracted text to a natural language processing (NLP) engine to analyze it for key keywords and topics. At this point, the input is the extracted text, and the output is a list of key keywords and topics. Specifically, keyword extraction and topic modeling are performed.

[1152] Step 4:

[1153] The server sends API requests to traffic information systems and news databases to get the latest traffic information. The input is the API query, and the output is the retrieved latest traffic information data. The data is collected using an API library (e.g., "requests").

[1154] Step 5:

[1155] The server compares the retrieved external data with the extracted text to assess the age of the information. The input is the external data and the extracted text, and the output is an assessment of the age of the information and whether it needs to be updated. A comparison algorithm or scoring method (e.g., similarity calculation) is used.

[1156] Step 6:

[1157] The in-vehicle computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state. At this point, the input is voice or text input from the driver, and the output is an evaluation of the driver's emotional state.

[1158] Step 7:

[1159] The server generates feedback for the driver based on the comparative evaluation results and emotion recognition results. The input is the information evaluation results and the driver's emotional state, and the output is the generated feedback message. The server provides softer expressions and detailed information according to the driver's emotional state.

[1160] Step 8:

[1161] The server notifies the driver of the generated feedback through the navigation system. The input is the generated feedback message, and the output is the notification provided to the driver. Specific operations include displaying the feedback message and an audio notification.

[1162] Step 9:

[1163] The in-vehicle computer customizes the navigation system interface based on the emotional state recognized by the emotion recognition engine. The input is the driver's emotional state, and the output is an adjusted interface layout and color tone. Specific actions include changing the background color and adjusting the layout.

[1164] 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.

[1165] 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.

[1166] 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.

[1167] [Fourth embodiment]

[1168] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1169] 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.

[1170] 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).

[1171] 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.

[1172] 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.

[1173] 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).

[1174] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1175] 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.

[1176] 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.

[1177] 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.

[1178] 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.

[1179] 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.

[1180] 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."

[1181] MODE FOR CARRYING OUT THE INVENTION

[1182] Overall system configuration

[1183] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest related external data, and provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. Each component of the system and its role are described below.

[1184] Uploading materials

[1185] Users upload presentation materials and document files to the system through a user interface, and the uploaded materials are sent to the server and temporarily stored.

[1186] Text Extraction and Analysis

[1187] The server extracts text from the uploaded material (using an appropriate text extraction library for PDF documents, another for PowerPoint documents, for example), and then analyzes the extracted text using a natural language processing (NLP) engine to extract key keywords and topics.

[1188] Retrieving External Data

[1189] The server sends API requests to news databases and research report databases to obtain the latest relevant external data, which is then stored on the server as text data.

[1190] Data comparison and evaluation

[1191] The server compares the extracted text with the latest external data it has retrieved, assessing whether the information in the document is up-to-date or outdated and in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[1192] Generating and Providing Feedback

[1193] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface.

[1194] Specific examples

[1195] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[1196] 1. Uploading materials

[1197] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[1198] 2. Text Extraction and Analysis

[1199] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[1200] 3. Acquiring external data

[1201] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[1202] 4. Data comparison and evaluation

[1203] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[1204] 5. Generating and Providing Feedback

[1205] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[1206] Users can revise their materials based on the feedback they receive, ensuring that they always reflect the latest information and are of high quality. In this way, the system helps users update and create materials efficiently and accurately.

[1207] The processing flow will be explained below.

[1208] Step 1:

[1209] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[1210] Step 2:

[1211] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[1212] Step 3:

[1213] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[1214] Step 4:

[1215] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[1216] Step 5:

[1217] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[1218] Step 6:

[1219] The server generates feedback for the user based on the results of the comparative evaluation, such as making specific suggestions like, "You're using information from 2021, but here's the latest information for 2023."

[1220] Step 7:

[1221] The server notifies the user of the generated feedback through a user interface, and the user is provided with an interface to review the feedback and update the material.

[1222] Step 8:

[1223] The user modifies the material based on the provided feedback, performs the update through the user interface, and then saves the updated material back to the system.

[1224] In this way, the system helps users create and update materials based on the latest information, improving the quality of presentations and reports.

[1225] Example 1

[1226] 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."

[1227] In conventional document creation systems, manual confirmation was required to determine whether the content of documents uploaded by users was based on the latest information, making update work cumbersome. It was also difficult to effectively obtain the latest external data and provide appropriate feedback to reflect that information in documents.

[1228] 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.

[1229] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract key keywords and topics, means for acquiring the latest related external data, means for comparing the extracted text with the acquired external data to evaluate the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for applying an appropriate text extraction library depending on the format of the materials, means for analyzing the extracted text using a natural language processing engine, means for acquiring related external data by sending an API request, and means for comparing text using document similarity calculations and machine learning models. This allows users to significantly improve the efficiency of updating materials and always create high-quality materials that reflect the latest information.

[1230] "Means for uploading materials" refers to a function that provides an interface for users to send materials to the system via the Internet.

[1231] "Means for extracting text from uploaded materials" refers to the libraries or software used by the server to analyze the contents of uploaded files and extract text data.

[1232] "Means for analyzing extracted text to extract key keywords and topics" refers to the function by which the server uses a natural language processing engine to find important keywords and topics from the extracted text.

[1233] The "means for obtaining the latest relevant external data" refers to a function in which the server sends an API request to an external database or information source to obtain the latest relevant information.

[1234] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to the algorithms or models that the server uses to compare the content of the material with the external data to determine whether the information is up-to-date or out-of-date.

[1235] The "means of generating feedback based on the evaluation results and providing it to the user" is a function in which the server provides the user with specific improvement suggestions and the latest information based on the evaluation results of the age of the information.

[1236] "Means for applying an appropriate text extraction library according to the format of the document" refers to a function in which the server automatically identifies the file format of the uploaded document and extracts text using a library appropriate for each format, such as PDF or PowerPoint.

[1237] "Means for analyzing extracted text using a natural language processing engine" refers to a function in which the server uses natural language processing technology to perform semantic analysis and keyword extraction on the extracted text.

[1238] "Means for sending API requests to obtain relevant external data" refers to the function by which the server periodically or as needed creates and sends API requests to external databases or information sources to obtain the latest information.

[1239] "Means for comparing texts using document similarity calculations or machine learning models" refers to a function in which the server uses machine learning models or numerical algorithms to compare the text of a document with the text of external data and evaluate the similarities and differences between them.

[1240] MODE FOR CARRYING OUT THE INVENTION

[1241] Overall system configuration

[1242] This invention is a system that analyzes the content of materials uploaded by users, compares them with the latest external data, and then provides feedback to the users. The system is mainly composed of a server and a terminal, and users access the system via the Internet. The specific components of the system and their operation are described below.

[1243] Uploading materials

[1244] Users log in to the system via a browser or a dedicated application and upload documents. This process is carried out through the user interface, and the files specified by the user are sent to the server. Supported file formats include PDF and PowerPoint, and the sent files are temporarily stored on the server.

[1245] Text Extraction and Analysis

[1246] The server determines the format of the uploaded material and extracts the text using the appropriate text extraction library: for PDF materials, it uses the Apache PDFBox library, for PowerPoint materials it uses the Apache POI library, and this extracted text is sent to a natural language processing engine (e.g., SpaCy, NLTK) to extract key keywords and topics.

[1247] Retrieving External Data

[1248] The server retrieves the latest relevant external data based on the keywords extracted from the extracted text. External data sources include news databases and research report databases. The server sends a RESTful API request to retrieve the latest relevant information. An API request uses a format such as requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}).

[1249] Data comparison and evaluation

[1250] The server uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) or machine learning models such as TF-IDF and BERT to compare the text of the document with the acquired external data. For example, when using Cosine Similarity, the calculation is done as follows: cosine_similarity(vectorized_textA, vectorized_textB). This allows the server to evaluate whether the information in the document is up-to-date or if it is old and needs to be updated.

[1251] Generating and Providing Feedback

[1252] Based on the evaluation results, the server generates feedback to provide to the user. This feedback includes specific suggestions for updating outdated information and links to the latest information. The generated feedback is provided to the user through a user interface. For example, a message such as "The latest information on autonomous driving technology for 2023 is available. Please check the link below." is generated and displayed as feedback.

[1253] Specific examples

[1254] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the process will proceed as follows:

[1255] 1. Uploading materials

[1256] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[1257] 2. Text Extraction and Analysis

[1258] The server uses Apache PDFBox to extract text from the PDF and a natural language processing engine (e.g., SpaCy) to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[1259] 3. Acquiring external data

[1260] The server sends a RESTful API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[1261] 4. Data comparison and evaluation

[1262] The server compares the retrieved news with the extracted text and uses a document similarity algorithm (e.g., Cosine Similarity) to determine that the "2021" information in the document is outdated.

[1263] 5. Generating and Providing Feedback

[1264] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[1265] In this way, the system helps users to efficiently update materials and create high-quality materials that always reflect the latest information.

[1266] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1267] Step 1:

[1268] A user logs into the system using a browser or a dedicated application, clicks the upload button, and selects a document. The input is a file selected by the user (e.g., "Autonomous Driving Technology 2021.pdf"). This file is sent to the server via the Internet. Specifically, the user selects the file using a standard file search window and clicks the upload button. The server receives the file and temporarily stores it in storage.

[1269] Step 2:

[1270] The server determines the format of the uploaded file and extracts the text using the appropriate text extraction library. For example, it uses the Apache PDFBox library for PDF format documents and the Apache POI library for PowerPoint format documents. The input contains the uploaded file. Specifically, it calls the ApachePDFBox.load(file) or ApachePOI.load(file) method to extract text data from the file. The extracted text data is returned as the output.

[1271] Step 3:

[1272] The server sends the extracted text to a natural language processing engine to extract key keywords and topics. The extracted text data is the input. The text is analyzed using a natural language processing engine (e.g., SpaCy, NLTK). Specifically, the model is loaded with nlp = spacy.load('en_core_web_sm') and the text is analyzed with doc = nlp(extracted_text). The output is a list of key keywords and topics.

[1273] Step 4:

[1274] The server retrieves the latest related external data based on the extracted keywords. The input is a list of extracted keywords. A RESTful API request is used to retrieve the external data. Specifically, a request of requests.get(api_endpoint, params={'query': 'Autonomous Driving Technology 2023'}) is sent to retrieve the latest data. The output is the retrieved external data in text format.

[1275] Step 5:

[1276] The server compares the text of the document with the acquired external data. The inputs include the text of the document and the acquired external data. It uses document similarity calculations (e.g., Cosine Similarity, Jaccard Index) and machine learning models such as TF-IDF and BERT. Specifically, it evaluates the similarity using cosine_similarity(vectorized_textA, vectorized_textB). The output is a score indicating the age of the information.

[1277] Step 6:

[1278] The server generates feedback based on the age of the information and provides it to the user. The inputs are the evaluation score and the acquired external data. The server generates a specific feedback message based on the evaluation results. Specifically, it creates a message such as "The latest information on autonomous driving technology as of 2023 is available. Please check the link below." and displays it with user_interface.display(feedback_message). The output is a feedback message to the user.

[1279] Through each step, the system assists users in updating materials efficiently and accurately.

[1280] (Application example 1)

[1281] 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."

[1282] In current factory operations, work procedures and manuals need to be updated regularly, but this process is time-consuming and it is difficult to ensure that they reflect the latest technical standards and regulations. This can also reduce work efficiency and affect quality and safety. To solve this problem, a system is needed that automatically compares the contents of procedure manuals with the latest information and makes any necessary updates quickly and accurately.

[1283] 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.

[1284] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the text to extract key keywords and topics, means for acquiring the latest related external data, means for evaluating the age of the information by comparing the acquired external data with the extracted text, means for generating feedback based on the evaluation results and providing it to the user, means for comparing the extracted text with the latest external data and using a generative AI model to indicate parts of the information that need updating, and means for generating prompts for the generative AI model and analyzing the results. This allows work procedures and manuals to be updated automatically and efficiently, ensuring that work reflects the latest technical standards and regulations.

[1285] The "material uploading means" is a mechanism by which a user can send materials in electronic data format to a server.

[1286] "Text extraction means" refers to a technique for extracting text data from uploaded materials.

[1287] "Keyword and topic extraction" is a technique that analyzes extracted text data to find key words and themes.

[1288] "Means for acquiring the latest external data" refers to a mechanism for collecting information on the latest technical standards and regulations from external data sources.

[1289] "Data comparison and evaluation means" refers to a technique for comparing extracted text with acquired external data to determine the freshness and accuracy of the information.

[1290] A "generative AI model" is a type of artificial intelligence that can understand and generate natural language, and is primarily used for generating and analyzing text.

[1291] A "prompt sentence generation means" is a technology that creates instruction sentences to be input into a generative AI model.

[1292] The "feedback generation means" is a mechanism for presenting to the user areas that require updating or improvement based on the results of data comparison and evaluation.

[1293] Overall system configuration

[1294] This invention is a system that uploads factory work procedures and manuals, extracts text, analyzes it, compares it with the latest technical standards and regulations, and generates and provides feedback. The system consists of a server and terminals, and users access the system via the Internet. This system helps users efficiently update documents and perform work that reflects the latest information.

[1295] Uploading materials

[1296] Users upload factory work procedures and manuals in PDF format through the user interface on their devices, and the uploaded materials are sent to the server and temporarily stored.

[1297] Text Extraction and Analysis

[1298] The server extracts text from the uploaded PDF documents, for example using a text extraction library such as pdfminer.six. The extracted text is then analyzed using a natural language processing (NLP) engine such as dslim / bert-base-NER to extract key keywords and topics.

[1299] Retrieving External Data

[1300] The server sends API requests to news databases and research report databases to obtain relevant and up-to-date external data. External data acquisition involves using news APIs. The acquired data is stored as text data on the server.

[1301] Data comparison and evaluation

[1302] The server compares the extracted text with the latest external data. This process involves using a generative AI model, such as GPT-3.5-Turbo, to input a prompt and obtain a result.

[1303] Generating and Providing Feedback

[1304] Based on the evaluation results, the server generates feedback for the user, including specific suggestions for updating outdated information and summaries of the latest information. The generated feedback is provided to the user through a user interface.

[1305] Specific examples

[1306] For example, if a user uploads "Factory Equipment Maintenance Manual 2021.pdf", the steps are as follows: First, the document is uploaded, then text extraction and analysis are performed. During the analysis, keywords such as "equipment maintenance" and "2021" are extracted. The server then retrieves the latest data related to "equipment maintenance 2023" from the news database. The retrieved data is compared with the extracted text, and a prompt sentence is generated using a generative AI model to indicate the parts of the information that need to be updated. A specific example of a prompt sentence is:

[1307] "Compare the contents of the following text: Factory Equipment Maintenance Manual 2021.pdf with the latest data for 2023 to indicate which information is current and which parts need to be updated."

[1308] Finally, feedback is generated and provided to the user in the form of "The information in the 2021 Equipment Maintenance Manual is outdated, so please update the following to reflect the latest information: ..."

[1309] In this way, the system can assist users in quickly implementing accurate work procedures based on the latest technical standards and regulations.

[1310] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1311] Step 1: Upload your materials

[1312] Users upload factory work procedures and manuals in PDF format to the server via their terminal. The input is a PDF file, and the server temporarily stores this PDF file in its storage. The file upload process is performed via the user interface.

[1313] Step 2: Text extraction

[1314] The server extracts text from the uploaded PDF file. Here, the pdfminer.six library is used. The input is a PDF file and the output is text data. In the text extraction process, the content of the PDF file is obtained as character data.

[1315] Step 3: Keyword and topic analysis

[1316] The server analyzes the extracted text and extracts key keywords and topics. The dslim / bert-base-NER model is used. The input is the extracted text, and the output is a list of keywords and topics. The analysis process uses natural language processing to identify important words and phrases.

[1317] Step 4: Retrieving External Data

[1318] The server sends API requests to the news database and research report database to obtain the latest external data. The input is a list of keywords and topics, and the output is text data as external data. The API request process obtains the latest information based on the specified keywords.

[1319] Step 5: Data comparison and evaluation

[1320] The server compares the extracted text with the latest external data obtained and evaluates the age of the information. A generative AI model is used here. The input is the extracted text and the latest external data, and the output is the evaluation result. In the comparison and evaluation process, a prompt sentence is input to the generative AI model and the model's output is analyzed.

[1321] Step 6: Prompt generation

[1322] The server generates prompt sentences to be input to the generative AI model. The input is the extracted text and external data, and the output is the prompt sentence. The prompt sentence generation process creates the instruction sentences necessary for comparison and evaluation.

[1323] Step 7: Analyze the results

[1324] The server analyzes the output of the generative AI model and identifies areas that need updating or improvement. The input is the output of the generative AI model, and the output is specific findings. The analysis process analyzes the model output and summarizes specific corrections.

[1325] Step 8: Generate and provide feedback

[1326] The server generates feedback based on the evaluation results and provides it to the user. The input is the findings obtained from the analysis, and the output is the feedback information. In the feedback generation process, corrections and suggestions are notified to the user through a user interface.

[1327] 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.

[1328] MODE FOR CARRYING OUT THE INVENTION

[1329] Overall system configuration

[1330] This invention is a system that allows users to upload documents, analyzes the text extracted from the documents, compares it with the latest relevant external data, and then provides feedback to the user. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it becomes possible to adjust the content of the feedback and the interface according to the user's emotions. The system is primarily composed of a server, a terminal, and an emotion engine, and users access the system via the Internet. Each component of the system and its role are described below.

[1331] Uploading materials

[1332] Users upload presentation materials and document files to the system by selecting the materials through the user interface and clicking the upload button, which sends the materials to the server and temporarily stores them in storage.

[1333] Text Extraction and Analysis

[1334] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library. The extracted text is passed to a natural language processing (NLP) engine to parse and extract key keywords and topics.

[1335] Retrieving External Data

[1336] The server sends API requests to news databases and research report databases to retrieve relevant and up-to-date external data, which is then stored on the server in text format.

[1337] Data comparison and evaluation

[1338] The server compares the text extracted from the document with the latest information obtained from external sources, assessing whether the information in the document is up-to-date or outdated and therefore in need of updating. The assessment is done automatically, using comparison algorithms and scoring methods.

[1339] Recognizing user emotions with an emotion engine

[1340] The emotion engine analyzes the user's text and voice input to recognize their emotions, allowing the system to understand their emotional state in real time, such as whether they are stressed, excited, or relaxed.

[1341] Generating and Providing Feedback

[1342] The server generates feedback for the user based on the results of the comparative evaluation and the emotion recognition results of the emotion engine. For example, if the user is feeling stressed, the server will express the feedback content in a gentler manner, and if the user is relaxed, it will provide detailed information, and generate feedback that corresponds to the user's emotions. The generated feedback is notified to the user through the user interface.

[1343] Interface customization

[1344] The layout and color of the user interface can be customized based on the emotions recognized by the emotion engine, for example, changing to calming colors when the user is stressed and using bright colors when relaxed.

[1345] Specific examples

[1346] For example, if a user uploads a "Report on Autonomous Driving Technology in 2021," the steps are as follows:

[1347] 1. Uploading materials

[1348] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[1349] 2. Text Extraction and Analysis

[1350] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[1351] 3. Acquiring external data

[1352] The server sends an API request to the news database with keywords such as "autonomous driving technology 2023" to retrieve the latest related news.

[1353] 4. Data comparison and evaluation

[1354] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[1355] 5. Emotion Recognition by Emotion Engine

[1356] If the user is feeling stressed, the emotion engine will recognize this state.

[1357] 6. Generating and Providing Feedback

[1358] The server generates feedback such as, "We have the latest information on autonomous driving technology for 2023. Check out the link below.", providing gentler language in consideration of the user's stress.

[1359] 7. Interface Customization

[1360] If the user is stressed, change the interface color to a calming color such as blue or green.

[1361] Users can revise their documents based on the feedback they receive, ensuring they always create high-quality documents that reflect the latest information. In addition, the emotion engine allows users to work in a comfortable environment. In this way, the system helps users update and create documents efficiently and accurately, improving the quality of the user experience.

[1362] The processing flow will be explained below.

[1363] Step 1:

[1364] The user selects a presentation or document file using the system's user interface and clicks the upload button. The server receives the file and stores it in temporary storage.

[1365] Step 2:

[1366] The server determines the format of the saved document file, for example, if it is PDF format, it uses the PyMuPDF library, and if it is PowerPoint format, it uses the python-pptx library to extract the text from the document.

[1367] Step 3:

[1368] The server passes the extracted text to a natural language processing (NLP) engine, specifically using a library such as spaCy, which parses and extracts key keywords and topics from the text.

[1369] Step 4:

[1370] The server sends API requests to the news database and research report database to retrieve the latest external data based on the extracted keywords. For example, it sends an HTTP request to collect related news using keywords such as "autonomous driving technology 2023."

[1371] Step 5:

[1372] The server compares the extracted text with the latest information from external sources, using custom algorithms and libraries (e.g., difflib) to assess the consistency and age of the information.

[1373] Step 6:

[1374] The emotion engine recognizes user emotions, for example by analyzing the user's text and voice inputs to identify emotions such as stress or relaxation, using natural language processing algorithms and machine learning models.

[1375] Step 7:

[1376] The server generates feedback for the user based on the results of the comparative evaluation and the recognition results of the emotion engine. For example, if the user is feeling stressed, the server will soften the feedback.

[1377] Step 8:

[1378] The server notifies the user of the generated feedback through a user interface, including suggestions for updating outdated information and links to the latest information.

[1379] Step 9:

[1380] The emotion engine customizes the layout and color of the user interface based on the emotions it recognizes. For example, if the user is feeling stressed, the interface color will change to calming colors such as blue or green.

[1381] Step 10:

[1382] The user modifies the material based on the provided feedback, making the modifications through the user interface, and then saving the updated material back to the system.

[1383] Example 2

[1384] 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."

[1385] Conventional document management systems often have issues with uploaded documents becoming outdated, making it difficult for users to keep documents up to date. Furthermore, the user interface is fixed and cannot be flexibly changed according to the user's emotional state, potentially resulting in a poor user experience. Furthermore, feedback is generated mechanically and is not tailored to the user's emotions or needs, resulting in a lack of familiarity for users.

[1386] 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.

[1387] In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract major keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, means for recognizing the user's emotions, means for adjusting the content of the feedback based on the recognized emotions, and means for customizing the user interface based on the recognized emotions. This makes it possible to keep the content of the materials up to date and to flexibly adjust the feedback and interface according to the user's emotional state.

[1388] "Means for uploading materials" refers to the method and process by which a user transmits document files and presentation materials to the system via the Internet and stores them on the server.

[1389] "Means for extracting text from uploaded materials" refers to the techniques and processes for analyzing the content of received document files and extracting text data.

[1390] "Means for analyzing extracted text to extract key keywords and topics" refers to the process of analyzing extracted text data using natural language processing techniques to identify important keywords and topics within the document.

[1391] "Means for obtaining relevant and up-to-date external data" means methods and processes for obtaining up-to-date data from external databases and sources based on specified keywords and topics.

[1392] "Means for comparing retrieved external data with extracted text to assess the age of the information" refers to methods and techniques for comparing internal text with external data to determine the freshness of the information or whether it needs to be updated.

[1393] The "means for generating and providing feedback to the user based on the evaluation results" is a process for preparing appropriate feedback information for the user based on the results of the comparison and evaluation, and communicating it to the user via the interface.

[1394] "Means for recognizing user emotions" refers to technologies and processes that analyze data such as text and voice input by a user and identify the user's emotional state in real time.

[1395] The "means for adjusting the content of feedback based on the recognized emotion" refers to a method and process for appropriately changing the content and expression of feedback based on the result of the user's emotion recognition.

[1396] "Means for customizing user interfaces based on recognized emotions" refers to techniques and processes for adjusting interface layout, color, and user experience based on the user's emotional state.

[1397] Overall system configuration

[1398] This invention is a system that allows users to upload materials, analyzes the text extracted from the materials, compares it with the latest relevant external data, and provides feedback to the user. The system is combined with an emotion engine that can recognize the user's emotions and adjust the feedback and interface accordingly. The main components are a server, a terminal, and the emotion engine, and users access the system via the Internet.

[1399] Uploading materials

[1400] Users upload document files and presentation materials through the system's web interface. Specifically, users click the "Upload File" button, select the materials to upload from their local environment, and click the "Send" button. The files sent from the device are received by the server and temporarily saved in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed on the user interface.

[1401] Text Extraction and Analysis

[1402] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[1403] Retrieving External Data

[1404] The server issues an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored on the server in text format.

[1405] Data comparison and evaluation

[1406] The server compares the text extracted from the document with external data using a document comparison algorithm (e.g., Cosine Similarity). This comparison determines, for example, that information in the document referring to "2021" is out of date. The results of the comparison and evaluation are scored and stored.

[1407] Recognizing user emotions with an emotion engine

[1408] Users can input messages or voice messages into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[1409] Generating and Providing Feedback

[1410] The server generates appropriate feedback for the user based on the results of the comparative evaluation and emotion recognition. For example, if the user is feeling stressed, it will provide soft feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[1411] Interface customization

[1412] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[1413] Specific examples

[1414] For example, if a user wants to upload a "2021 Report on Autonomous Driving Technology," the process would look like this:

[1415] 1. Uploading materials

[1416] The user uploads "Autonomous Driving Technology 2021.pdf" to the system.

[1417] 2. Text Extraction and Analysis

[1418] The server extracts text from the PDF and uses a natural language processing engine to extract keywords such as "autonomous driving technology," "2021," and "key technologies."

[1419] 3. Acquiring external data

[1420] The server sends an API request to the news database using the keyword "autonomous driving technology 2023" to retrieve the latest related news.

[1421] 4. Data comparison and evaluation

[1422] The server compares the retrieved news with the extracted text and determines that the "2021" information in the document is outdated.

[1423] 5. Emotion Recognition by Emotion Engine

[1424] If the user is feeling stressed, the emotion engine will recognize this state.

[1425] 6. Generating and Providing Feedback

[1426] The server generates feedback to the user saying, "We have the latest information on autonomous driving technology for 2023. Check the link below."

[1427] 7. Interface Customization

[1428] The user is feeling stressed, so the interface color is changed to blue or green.

[1429] In this way, the system can help users update and create materials efficiently and accurately, improving the quality of the user experience.

[1430] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1431] Step 1:

[1432] Uploading materials

[1433] The user uploads document files or presentation materials from the system's web interface. Specifically, the user clicks the "Upload File" button, selects the material to upload from the local environment (e.g., "Autonomous Driving Technology 2021.pdf"), and clicks the "Send" button. The server receives the file sent from the terminal and temporarily saves it in storage (e.g., Amazon S3). After saving is complete, a message indicating successful upload is displayed in the user interface.

[1434] Input: A file selected by the user

[1435] Output: Upload successful message

[1436] The server saves the received file in storage and displays a save success message on the user interface.

[1437] Step 2:

[1438] Text Extraction and Analysis

[1439] The server determines the format of the stored document file. For example, if the file is in PDF format, it uses a PDF text extraction library (e.g., Apache PDFBox) to extract the text data. The extracted text is input into a natural language processing engine (e.g., SpaCy). The engine parses the text data to extract key keywords and topics.

[1440] Input: Saved file

[1441] Output: Extracted text and analyzed keywords and topics

[1442] The server inputs the extracted text into a natural language processing engine to analyze and extract key keywords and topics.

[1443] Step 3:

[1444] Retrieving External Data

[1445] The server sends an API request to an external database (e.g., Google News API) based on the extracted keywords. For example, a search query such as "Autonomous Driving Technology 2023" is used to retrieve the latest relevant data from the news database. The retrieved data is stored in text format on the server.

[1446] Input: Extracted keywords

[1447] Output: Retrieved external data

[1448] The server sends API requests using keywords to news databases and research report databases to retrieve and store the latest data.

[1449] Step 4:

[1450] Data comparison and evaluation

[1451] The server compares the text extracted from the document with the external data. This comparison uses a document comparison algorithm (e.g., Cosine Similarity). For example, the comparison may determine that the information in the document about "2021" is outdated. The results of the comparison and evaluation are scored and stored on the server.

[1452] Input: Extracted text and retrieved external data

[1453] Output: Information freshness evaluation result

[1454] The server uses a document comparison algorithm to compare the internal text with the external data, assess the age of the information, and store the results.

[1455] Step 5:

[1456] Recognizing user emotions with an emotion engine

[1457] The user inputs a message or voice message into the system. The server sends the input data to an emotion engine (e.g., Microsoft Azure Cognitive Services). The emotion engine determines the user's emotional state in real time and returns the results to the server. The emotion recognition results are stored on the server.

[1458] Input: User text and voice input

[1459] Output: User emotion recognition results

[1460] The server sends the input user data to the emotion engine and stores the recognized emotional state.

[1461] Step 6:

[1462] Generating and Providing Feedback

[1463] The server generates feedback for the user based on the results of the comparative evaluation of the data and the recognition results of the emotion engine. For example, if the user is feeling stressed, it generates soft-spoken feedback such as, "We have the latest information on autonomous driving technology for 2023. Please check the link below." The generated feedback is notified to the user through the user interface.

[1464] Input: Information freshness evaluation results and emotion recognition results

[1465] Output: Feedback provided to the user

[1466] The server generates appropriate feedback based on the evaluation results and emotion recognition results and provides it to the user.

[1467] Step 7:

[1468] Interface customization

[1469] The server customizes the layout and color of the user interface based on the recognition results of the emotion engine. For example, if the user is feeling stressed, the color of the interface will be changed to blue or green, allowing the user to work in a comfortable environment.

[1470] Input: Recognition results of emotion engine

[1471] Output: Customized user interface

[1472] The server adjusts the interface based on the emotion recognition results, providing a comfortable working environment for the user.

[1473] ---

[1474] Through these steps, the system helps users update and create documents efficiently and accurately, while improving the quality of the user experience.

[1475] (Application example 2)

[1476] 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."

[1477] When autonomous vehicles continue to operate, they are required to constantly update the latest traffic and road regulation information. However, if the driver feels fatigued or stressed, it may become difficult for them to accurately and quickly grasp this information. Therefore, in addition to updating the information, it is necessary to provide feedback and adjust the interface according to the driver's emotional state.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for uploading materials, means for extracting text from the uploaded materials, means for analyzing the extracted text to extract main keywords and topics, means for acquiring the latest related external data, means for comparing the acquired external data with the extracted text and evaluating the age of the information, means for generating feedback based on the evaluation results and providing it to the user, and means for recognizing the user's emotions using an emotion engine and adjusting the content of the feedback and the interface according to the user's emotions. This allows the driver to appropriately receive the latest traffic information and maintain a comfortable driving environment through appropriate feedback according to the user's emotional state.

[1479] "Documents" are documents or files that detail information.

[1480] An "uploading means" is a system or function that allows a user to send data from their device to a remote server.

[1481] "Text extraction methods" are techniques and algorithms used to extract textual information from documents and files.

[1482] "Means for analyzing and extracting key keywords and topics" refers to a technique for analyzing extracted text information and identifying important terms and topics from it.

[1483] "Means for obtaining the latest external data" are systems and processes for collecting current information from the Internet or databases.

[1484] The "means for comparing and assessing the age of information" is a function for comparing the collected external data with the extracted text information to determine how recent the information is.

[1485] "Means for generating feedback and providing it to users" refers to a system or function that creates information or advice based on the evaluation results and presents it to users.

[1486] An "emotion engine" is a technology or algorithm that analyzes and recognizes a user's emotional state from their input (voice, text, etc.).

[1487] "Means for recognizing emotions and adjusting the content of feedback and interface" refers to a system or function for changing the content and display format of feedback to the user based on the recognized emotional state.

[1488] Overall system configuration

[1489] This invention is a system that provides feedback based on the latest traffic information and the driver's emotional state during the operation of an autonomous vehicle, helping the driver continue driving comfortably and efficiently. The system mainly consists of a server, an in-vehicle computer, and an emotion recognition engine.

[1490] Uploading materials

[1491] The driver uploads a document, such as "New Traffic Regulation Information 2023.pdf," through the autonomous vehicle's navigation system. By clicking the upload button, the document file is sent to the server and temporarily stored.

[1492] Text Extraction and Analysis

[1493] The server determines the format of the stored material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The extracted text is passed to a natural language processing (NLP) engine, which parses and extracts key keywords and topics.

[1494] Retrieving External Data

[1495] The server sends API requests to traffic information systems and news databases to obtain the latest traffic information. The obtained data is stored on the server in text format. The API library used is, for example, "requests".

[1496] Data comparison and evaluation

[1497] The server compares the text extracted from the document with the latest information obtained from external sources, and evaluates whether the information in the document is up-to-date or needs to be updated. The evaluation is performed automatically using comparison algorithms and scoring methods (e.g., similarity calculations).

[1498] Driver emotion recognition using emotion engine

[1499] The vehicle's computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state, allowing the system to understand in real time whether the driver is stressed, tired, or relaxed.

[1500] Generating and Providing Feedback

[1501] The server generates feedback for the driver based on the comparison of the document with external data and the results of the emotion recognition engine. For example, if the driver is feeling stressed, the server generates feedback that corresponds to the driver's emotions, such as softening the content of the feedback and providing more detailed information. The generated feedback is notified to the driver through the navigation system.

[1502] Interface customization

[1503] The emotion engine can customize the layout and color of the in-vehicle navigation system based on the driver's emotions, for example, changing to calming colors like blue and green if the driver is stressed, and using brighter colors if the driver is relaxed.

[1504] Specific examples

[1505] If a driver uploads "New Traffic Regulation Information 2023.pdf", the steps are as follows:

[1506] 1. Uploading materials

[1507] "New Traffic Regulation Information 2023.pdf" has been uploaded.

[1508] Example prompt: "Please upload New Traffic Regulation Information 2023.pdf."

[1509] 2. Text Extraction and Analysis

[1510] The server extracts text from the PDF and uses an NLP engine to extract keywords such as "2023," "traffic regulations," and "new regulations."

[1511] 3. Acquiring external data

[1512] The server sends an API request to the traffic information system to obtain the latest traffic information.

[1513] API request example: "requests.get("https: / / api.trafficinfo.com / data?year=2023")"

[1514] 4. Data comparison and evaluation

[1515] The server compares the extracted text with external data and evaluates whether it needs to be updated to reflect the latest information.

[1516] 5. Emotion Recognition by Emotion Engine

[1517] The emotion engine recognizes the driver's stress level and fatigue.

[1518] Example prompt: "Analyze the driver's emotional state and adjust feedback."

[1519] 6. Generating and Providing Feedback

[1520] The server generates soft feedback saying, "We have the latest 2023 traffic regulation information. Check the link below."

[1521] Example feedback: "Please check the latest traffic regulations and drive safely."

[1522] 7. Interface Customization

[1523] If the driver is feeling stressed, the navigation system changes the background color to blue or green.

[1524] Example prompt: "Due to high stress levels, we are changing the color tone of the navigation system."

[1525] In this way, the system helps drivers receive optimal information and provides a driving environment that takes their emotional state into consideration, supporting comfortable and safe driving.

[1526] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1527] Step 1:

[1528] The user uploads a document file (e.g., "New Traffic Regulation Information 2023.pdf") through the navigation system of the autonomous vehicle. When the upload button is clicked, the document file is sent to the server. At this stage, the input is the document file from the user, and the output is the document file saved on the server.

[1529] Step 2:

[1530] The server determines the format of the saved material file and extracts text from the material using an appropriate text extraction library (e.g., the Python NLP library "spaCy"). The input is the material file, and the output is the extracted text data.

[1531] Step 3:

[1532] The server passes the extracted text to a natural language processing (NLP) engine to analyze it for key keywords and topics. At this point, the input is the extracted text, and the output is a list of key keywords and topics. Specifically, keyword extraction and topic modeling are performed.

[1533] Step 4:

[1534] The server sends API requests to traffic information systems and news databases to get the latest traffic information. The input is the API query, and the output is the retrieved latest traffic information data. The data is collected using an API library (e.g., "requests").

[1535] Step 5:

[1536] The server compares the retrieved external data with the extracted text to assess the age of the information. The input is the external data and the extracted text, and the output is an assessment of the age of the information and whether it needs to be updated. A comparison algorithm or scoring method (e.g., similarity calculation) is used.

[1537] Step 6:

[1538] The in-vehicle computer uses an emotion recognition engine (e.g., "DeepAffects") to analyze the driver's emotional state. At this point, the input is voice or text input from the driver, and the output is an evaluation of the driver's emotional state.

[1539] Step 7:

[1540] The server generates feedback for the driver based on the comparative evaluation results and emotion recognition results. The input is the information evaluation results and the driver's emotional state, and the output is the generated feedback message. The server provides softer expressions and detailed information according to the driver's emotional state.

[1541] Step 8:

[1542] The server notifies the driver of the generated feedback through the navigation system. The input is the generated feedback message, and the output is the notification provided to the driver. Specific operations include displaying the feedback message and an audio notification.

[1543] Step 9:

[1544] The in-vehicle computer customizes the navigation system interface based on the emotional state recognized by the emotion recognition engine. The input is the driver's emotional state, and the output is an adjusted interface layout and color tone. Specific actions include changing the background color and adjusting the layout.

[1545] 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.

[1546] 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.

[1547] 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.

[1548] 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.

[1549] 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.

[1550] 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.

[1551] 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).

[1552] 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.

[1553] 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."

[1554] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1555] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1556] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1557] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1558] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1559] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1560] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1561] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1562] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1563] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1564] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1565] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1566] The following is further disclosed regarding the above embodiment.

[1567] (Claim 1)

[1568] a means for uploading materials;

[1569] means for extracting text from the uploaded material;

[1570] a means for analyzing the extracted text to extract key keywords and topics;

[1571] a means for obtaining relevant and up-to-date external data;

[1572] a means for comparing the retrieved external data with the extracted text to assess the age of the information;

[1573] means for generating and providing feedback to the user based on the evaluation results;

[1574] A system including:

[1575] (Claim 2)

[1576] 2. The system of claim 1, wherein the external data acquisition means acquires data from a news database and a research report database.

[1577] (Claim 3)

[1578] 10. The system of claim 1, wherein the means for generating feedback provides an interface for modifying the material based on the provided feedback.

[1579] "Example 1"

[1580] (Claim 1)

[1581] a means for uploading materials;

[1582] means for extracting text from the uploaded material;

[1583] a means for analyzing the extracted text to extract key keywords and topics;

[1584] a means for obtaining relevant and up-to-date external data;

[1585] a means for comparing the retrieved external data with the extracted text to assess the age of the information;

[1586] means for generating and providing feedback to the user based on the evaluation results;

[1587] a means for applying an appropriate text extraction library depending on the format of the material;

[1588] means for analyzing the extracted text using a natural language processing engine;

[1589] A means of submitting API requests to retrieve relevant external data;

[1590] A means of comparing texts using document similarity calculations and machine learning models;

[1591] A system including:

[1592] (Claim 2)

[1593] 2. The system of claim 1, wherein the external data acquisition means acquires data from a news database and a research report database.

[1594] (Claim 3)

[1595] 10. The system of claim 1, wherein the means for generating feedback provides an interface for modifying the material based on the provided feedback.

[1596] "Application Example 1"

[1597] (Claim 1)

[1598] a means for uploading materials;

[1599] means for extracting text from the uploaded material;

[1600] a means for analyzing the extracted text to extract key keywords and topics;

[1601] a means for obtaining relevant and up-to-date external data;

[1602] a means for comparing the retrieved external data with the extracted text to assess the age of the information;

[1603] means for generating and providing feedback to the user based on the evaluation results;

[1604] using a generative AI model to compare the extracted text with current external data to indicate where information needs updating;

[1605] a means for generating prompts for the generative AI model and analyzing the results;

[1606] A system including:

[1607] (Claim 2)

[1608] 2. The system of claim 1, wherein the external data acquisition means acquires data from a news database and a research report database.

[1609] (Claim 3)

[1610] 10. The system of claim 1, wherein the means for generating feedback provides an interface for modifying the material based on the provided feedback.

[1611] "Example 2: Combining Emotion Engines"

[1612] (Claim 1)

[1613] a means for uploading materials;

[1614] means for extracting text from the uploaded material;

[1615] a means for analyzing the extracted text to extract key keywords and topics;

[1616] a means for obtaining relevant and up-to-date external data;

[1617] a means for comparing the retrieved external data with the extracted text to assess the age of the information;

[1618] means for generating and providing feedback to the user based on the evaluation results;

[1619] means for recognizing a user's emotion;

[1620] a means of tailoring the content of the feedback based on the perceived emotions;

[1621] means for customizing a user interface based on the recognized emotion;

[1622] A system including:

[1623] (Claim 2)

[1624] 2. The system of claim 1, wherein the external data acquisition means acquires data from a news database and a research report database.

[1625] (Claim 3)

[1626] 10. The system of claim 1, wherein the means for generating feedback provides an interface for modifying the material based on the provided feedback.

[1627] "Application example 2 when combining emotion engines"

[1628] (Claim 1)

[1629] a means for uploading materials;

[1630] means for extracting text from the uploaded material;

[1631] a means for analyzing the extracted text to extract key keywords and topics;

[1632] a means for obtaining relevant and up-to-date external data;

[1633] a means for comparing the retrieved external data with the extracted text to assess the age of the information;

[1634] means for generating and providing feedback to the user based on the evaluation results;

[1635] means for recognizing a user's emotion using an emotion engine and adjusting the feedback content and interface in accordance with the user's emotion;

[1636] A system including:

[1637] (Claim 2)

[1638] 2. The system of claim 1, wherein said external data acquisition means acquires data from an information database and a report database.

[1639] (Claim 3)

[1640] 2. The system of claim 1, wherein the means for generating feedback provides an interface for modifying the material based on the provided feedback and further adjusts the layout and color tone of the interface depending on the user's emotional state. [Explanation of symbols]

[1641] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for uploading materials; means for extracting text from the uploaded material; a means for analyzing the extracted text to extract key keywords and topics; a means for obtaining relevant and up-to-date external data; a means for comparing the retrieved external data with the extracted text to assess the age of the information; means for generating and providing feedback to the user based on the evaluation results; A system including:

2. 2. The system of claim 1, wherein said external data acquisition means acquires data from a news database and a research report database.

3. 10. The system of claim 1, wherein the means for generating feedback provides an interface for modifying the material based on the provided feedback.

Images