system

Abstract

We provide the system. [Solution] A means of accessing the latest academic literature databases and searching for and collecting literature related to a specified topic, A means for automatically extracting abstracts, conclusions, and experimental results from collected literature and generating summaries, An artificial intelligence tool that automatically generates application methods for business based on the generated summary, A means of displaying the generated application methods on a terminal and providing a user-accessible dashboard, A means of collecting feedback from users and continuously improving the artificial intelligence model, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern enterprises, incorporating the latest academic research into business operations has many advantages. However, due to the vast amount of academic papers and their high level of specialization, it is difficult for ordinary employees to properly understand and apply this knowledge in their work. Moreover, even for newly recruited employees with a university degree, they lack the experience and know-how to effectively utilize the latest research results in their work, and thus the system for linking academic knowledge to work is not well-established. Furthermore, the mechanism for evaluating the usefulness of an idea once proposed and reflecting the results as feedback is also insufficient, making continuous improvement difficult.

Means for Solving the Problems

[0005] To solve this problem, the present invention provides the following means. Specifically, it provides means for accessing the latest academic literature databases and searching for and collecting literature related to a specified topic. Next, it provides means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries. Based on these summaries, it provides artificial intelligence means for automatically generating methods for applying them to business operations. Furthermore, it provides means for displaying the generated application methods on a terminal and providing a dashboard accessible to the user. It also provides means for collecting feedback from users and continuously improving the artificial intelligence model. As a result, companies can efficiently apply academic knowledge to their operations and improve employee skills and work efficiency.

[0006] A "latest academic literature database" is an electronic database containing the latest research findings in a specialized field, such as academic papers, research reports, and technical documents.

[0007] A "specified topic" refers to a specific theme or keyword related to a task that has been pre-configured by the user or system.

[0008] "Literature" refers to written documents and electronic data that are publicly available in the form of academic papers, research reports, technical documents, etc.

[0009] An "abstract" is a section in an academic paper or research report that concisely summarizes the purpose, methods, results, and conclusions of the research.

[0010] The "conclusion" in an academic paper or research report is the section that presents the final details and discussion derived from the research results.

[0011] "Experimental results" refer to specific data obtained through experiments or surveys and the results of their analysis, as described in academic papers and research reports.

[0012] A "summary" is a concise overview of the entire document, designed to present the key points of the research in an easily understandable format.

[0013] "Application methods to business operations" refer to specific methods of how to apply the content of academic papers and research reports to actual business processes and business improvement.

[0014] "Artificial intelligence tools" refer to systems and algorithms that use technologies such as machine learning and natural language processing to automatically perform tasks such as data analysis, summary generation, and suggestion of application methods.

[0015] A "device" refers to a computer, tablet, smartphone, or other device used by a user to view and interact with information.

[0016] A "dashboard" is an interface that displays data and information in a way that is easy for users to understand visually.

[0017] "Feedback" refers to information that allows users to evaluate system suggestions and results, and provide opinions and suggestions for improvement.

[0018] An "artificial intelligence model" is a set of machine learning or deep learning algorithms designed to analyze data and perform specific tasks. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

[0020] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0022] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0023] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0024] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0025] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0027] [First Embodiment]

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

[0029] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0032] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0034] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0036] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0039] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0040] The system of the present invention is realized through the interaction of a server, terminals, and users. The embodiments for carrying out the present invention are described in detail below.

[0041] 1. Server Role

[0042] Data collection

[0043] The server accesses academic literature databases and collects the latest literature related to the specified topic. This includes scheduled searches and real-time searches based on user requests. The collected literature data is stored in a database on the server.

[0044] Information extraction and summary generation

[0045] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[0046] Generating business application proposals

[0047] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[0048] Providing a user interface (UI)

[0049] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. The dashboard displays the latest suggestions and a feedback form.

[0050] Gathering feedback and learning

[0051] The server collects user feedback and stores it in a database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0052] 2. The role of the terminal

[0053] Dashboard display

[0054] The terminal displays an enterprise dashboard for user access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface.

[0055] Submitting feedback

[0056] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the proposed solutions. This feedback is sent to the server in real time.

[0057] 3. User Roles

[0058] Information verification and evaluation

[0059] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[0060] Provide feedback

[0061] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[0062] Specific example

[0063] Example 1: Application in the development of medical devices

[0064] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates proposals on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[0065] Example 2: Application in improving marketing strategies

[0066] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. The terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[0067] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system can be continuously improved through continuous feedback.

[0068] The following describes the processing flow.

[0069] Step 1:

[0070] The server accesses the academic literature database and searches for the latest literature based on the specified topic. The query is executed according to business-related keywords and filtering conditions.

[0071] Step 2:

[0072] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[0073] Step 3:

[0074] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[0075] Step 4:

[0076] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[0077] Step 5:

[0078] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[0079] Step 6:

[0080] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[0081] Step 7:

[0082] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[0083] Step 8:

[0084] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[0085] Step 9:

[0086] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time.

[0087] Step 10:

[0088] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[0089] Step 11:

[0090] The server retrains the artificial intelligence model based on the feedback data. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[0091] Step 12:

[0092] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[0093] (Example 1)

[0094] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0095] Currently, for companies to apply academic literature to their operations, they need to manually collect, analyze, and devise application methods for vast amounts of information. This process consumes a great deal of time and effort, and the accuracy and usefulness of the analysis results and application methods are inconsistent because they depend on human resources. Furthermore, even when feedback is collected, there is a lack of mechanisms to effectively utilize it and reflect it in future proposals, making continuous improvement difficult. As a result, it is difficult for companies to quickly and efficiently incorporate the latest academic knowledge into their operations and innovate their business processes.

[0096] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0097] This invention includes a server that includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a user-accessible dashboard, means for collecting feedback from users and storing it in an evaluation database, and means for retraining the artificial intelligence model based on the collected feedback data to successively improve the accuracy and usefulness of future suggestions. This enables companies to efficiently carry out everything from collecting academic literature to generating application suggestions and even continuous improvement through feedback, allowing for rapid and highly accurate innovation of business processes.

[0098] A "server" is a computer system that provides specific services to other computers (clients) on a network.

[0099] A "scholarly literature database" is a database system that collects and makes searchable and accessible literature information such as academic papers and research results.

[0100] An "abstract" is a concise summary of the content of an academic paper or report, providing an overview of the research's objectives, methods, results, and conclusions.

[0101] The "Conclusion" section is the part of the document that summarizes the main findings and conclusions derived from the results of research or experiments.

[0102] "Experimental results" refer to data and observations obtained in research or experiments, and include the results of their analysis.

[0103] A "Natural Language Processing (NLP) module" is a software module for analyzing and understanding text data, and in particular, it processes human language using machine learning and generative AI models.

[0104] "Artificial intelligence tools" refer to systems or modules that analyze data using machine learning algorithms or generative AI models and make judgments and suggestions like humans.

[0105] A "dashboard" is an interface that allows users to visually view and manipulate information, and it is a screen that displays specific data or analysis results.

[0106] "Feedback" refers to evaluations and opinions provided by users, and is information collected to improve the system and inform future suggestions.

[0107] An "evaluation database" is a database system that stores collected feedback information and uses it for analysis and model retraining.

[0108] "Retraining" is the process of training an existing machine learning model again using new data and feedback information to improve the model's accuracy and usefulness.

[0109] The system of the present invention is realized through the mutual cooperation of a server, terminal, and user. The embodiments for carrying out the present invention will be described in detail below.

[0110] The server accesses the latest academic literature databases to search for and collect literature related to the specified topic. Specifically, it utilizes databases such as PubMed and IEEE Xplore. The collected literature data is stored in the server's database in JSON format or similar.

[0111] The server is equipped with a natural language processing (NLP) module, which utilizes generative AI models such as BERT and GPT-3®. This NLP module analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. This analysis process extracts important information and generates a summary. The summary generation algorithm picks out important keywords and sentences from the extracted text and creates a concise summary.

[0112] Next, the server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary. This AI module uses a business proposal template to suggest how the new algorithm or method can contribute to business processes. The generated application methods and summary are created in HTML format and sent to the terminal via WebSocket or REST API.

[0113] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface. The dashboard also displays a feedback form, allowing users to input and submit their opinions on the effectiveness and areas for improvement of the suggested content.

[0114] User feedback is sent to the server in real time and stored in an evaluation database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0115] As a concrete example, the server collects the latest literature related to the topic of "medical devices" from PubMed and analyzes it using an NLP module. Then, based on the summary generated by the AI ​​module, it proposes applications for medical device development. The terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[0116] A similar process can be applied to improving marketing strategies. A server collects the latest marketing-related literature and generates summaries. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. A terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[0117] An example of a prompt might be: "Collect the latest marketing-related literature, generate summaries, and create marketing strategy proposals based on new consumer behavior analysis methods."

[0118] As described above, the system of the present invention enables the rapid and accurate application of academic knowledge to business operations through the collaboration of a server, terminal, and user, via data collection, summary generation, business application proposals, feedback collection, and retraining.

[0119] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0120] Step 1:

[0121] The server accesses academic literature databases to search for and collect literature related to the specified topic.

[0122] Specific operation: The server sends queries to databases such as PubMed and IEEE Xplore based on a regular schedule or user requests. The retrieved bibliographic data is stored in JSON format. The input for this step is the search query, and the output is the collected bibliographic data.

[0123] Step 2:

[0124] A natural language processing (NLP) module on the server analyzes the collected literature data, extracts abstracts, conclusions, and experimental results, and generates a summary.

[0125] Specific operation: The NLP module analyzes sections of literature using generative AI models such as BERT and GPT-3, and extracts important information.

[0126] The input for this step is collected literature data, and the output is the analyzed information and summary.

[0127] Step 3:

[0128] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary.

[0129] Specific operation: The AI ​​module utilizes business templates to suggest how new algorithms and methods can contribute to business processes.

[0130] The input for this step is the generated summary, and the output is a proposed application method.

[0131] Step 4:

[0132] The server displays the generated application methods on the terminal and provides a user-accessible dashboard.

[0133] Specific operation: Generates proposal content and summary in HTML format and sends it to the terminal via WebSocket or REST API.

[0134] The input for this step is a proposed application method, and the output is a dashboard displayed on the terminal.

[0135] Step 5:

[0136] The dashboard on the device displays information to the user and collects feedback.

[0137] Specific operation: The device uses a web browser to render HTML data provided by the server, retrieves user-entered feedback information using JavaScript (registered trademark), and sends it to the server in real time.

[0138] The input for this step is the information from the dashboard, and the output is the collected feedback.

[0139] Step 6:

[0140] The server collects feedback provided by users and stores it in an evaluation database.

[0141] Specific operation: Feedback data is stored in an SQL database and used for subsequent natural language processing and AI model training.

[0142] The input for this step is the collected feedback, and the output is the feedback data stored in the evaluation database.

[0143] Step 7:

[0144] The server retrains its artificial intelligence model based on the collected feedback data, continuously improving the accuracy and usefulness of subsequent suggestions.

[0145] Specific action: Adjust the parameters of the generated AI model using the new feedback data and retrain it.

[0146] The input for this step is feedback data stored in an evaluation database, and the output is an improved generative AI model.

[0147] (Application Example 1)

[0148] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0149] Conventional systems for collecting and analyzing academic literature have made it difficult to quickly and accurately analyze the latest information and propose concrete ways to apply it to business operations. In particular, there has been a lack of systems that effectively utilize information visualization and user feedback, resulting in problems in streamlining business processes and improving the accuracy of proposals.

[0150] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0151] In this invention, the server includes means for accessing the latest academic literature databases, searching for and collecting literature related to a specified topic; means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries; artificial intelligence means for automatically generating application methods for business based on the generated summaries; means for displaying the generated application methods on a mobile communication terminal and providing a user-accessible visualized operation screen; means for collecting feedback from users and continuously improving the artificial intelligence model; and means for efficiently organizing the collected and generated information and generating proposals adaptable to various business processes. This makes it possible to quickly analyze the latest information, present it to users in a visually easy-to-understand format, and continuously improve the proposals through user feedback.

[0152] A "scholarly literature database" is an information aggregation system that collects and stores academic information such as research papers, academic books, and technical reports in a searchable format.

[0153] "Specified topics" refer to keywords or theme settings used to identify research areas or themes that the user is interested in.

[0154] "Collection methods" refer to technologies for accessing academic literature databases, automatically searching for literature related to a specified topic, and obtaining data.

[0155] An "abstract" is a concise summary of the research objectives, methods, and main findings in a document.

[0156] The "conclusion" is the section that outlines the overall judgment and future research direction derived from the research results.

[0157] "Experimental results" refers to the section that shows the specific results and data from experiments and surveys conducted in a study.

[0158] A "summary generation method" is a technique for extracting important information from collected literature and organizing it into a concise and easy-to-understand format.

[0159] "Artificial intelligence methods" refer to artificial intelligence technologies that analyze large amounts of data, recognize patterns, and generate new information and application methods.

[0160] A "mobile communication terminal" refers to a mobile device, such as a smartphone or tablet, that can connect to the internet and receive and display information.

[0161] A "visualized user interface" is a screen designed to graphically display collected information and generated suggestions, allowing users to operate it intuitively.

[0162] It refers to "feedback."

[0163] "Retraining" is the process by which an artificial intelligence model improves its prediction accuracy and suggestions based on newly collected data and user feedback.

[0164] A "business process" refers to a series of tasks or procedures performed in business or research to achieve a specific objective.

[0165] "Means for generating suggestions" refers to technologies that present users with useful action plans and areas for improvement based on collected data and generated summaries.

[0166] The system for implementing this invention collects the latest literature from a scholarly literature database, analyzes it, generates suggestions for its application to business operations, and continuously improves the system through feedback. This system is realized through the interaction of a server, terminals, and users.

[0167] Server Role

[0168] The server plays the following main roles:

[0169] 1. Data collection:

[0170] The server accesses academic literature databases on the internet to search for and collect the latest literature related to a specified topic. Specifically, it uses APIs to retrieve bibliographic information. Here, the requests library is used to access the APIs of academic literature databases.

[0171] 2. Information extraction and summarization using natural language processing:

[0172] Natural language processing (NLP) techniques are used to automatically extract abstracts, conclusions, and experimental results from collected literature and generate summaries. Here, the OpenAI® API is used to generate the summaries. This process involves analyzing the main parts of the literature and concisely summarizing the key information.

[0173] 3. Generating business application proposals:

[0174] Artificial intelligence (AI) technology is used to generate application methods for business operations based on summarized information. The generated summaries are used as prompts, and business suggestions are generated via the OpenAI API. For example, the following prompts are used:

[0175] Based on the following summary, please propose an application:

[0176] (Summary text)

[0177] 4. Providing a user interface:

[0178] The generated suggestions are displayed on the device, providing a visualized, user-accessible interface. This uses a dashboard built with HTML and JavaScript. The dashboard displays the suggestions and a feedback form.

[0179] 5. Gathering feedback and relearning:

[0180] We collect user feedback and use it to retrain the AI ​​model. This retraining improves the accuracy of future suggestions. The feedback is sent to and collected on the server in real time.

[0181] Terminal role

[0182] The terminal primarily serves the following roles:

[0183] 1. Display the dashboard:

[0184] The terminal displays a visualized interface (dashboard) for the user to access. This includes the latest business application proposals and summarized academic research information sent from the server.

[0185] 2. Submitting feedback:

[0186] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the suggestions. This feedback is sent to the server and used for retraining.

[0187] User roles

[0188] The user will have the following roles:

[0189] 1. Information verification and evaluation:

[0190] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[0191] 2. Providing feedback:

[0192] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[0193] Specific application examples

[0194] For example, if a user specifies "artificial intelligence" as their topic, the server will collect the latest relevant literature and generate summaries from it. Based on these summaries, it will then suggest how they can be applied to content delivery services. Specifically, a possible suggestion might be, "Using this new AI algorithm will improve the accuracy of the recommendation system." Users can view these suggestions on a dashboard and contribute to improving the system's accuracy by providing feedback.

[0195] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0196] Step 1: Data Collection

[0197] The server receives a topic specified by the user. The server accesses academic literature databases on the internet and searches for literature related to the specified topic. Specifically, the server uses the requests library to send requests to the literature database API and retrieve relevant literature information. The input is the topic specified by the user, and the output is a list of retrieved literature.

[0198] Step 2: Information Extraction and Summary Generation

[0199] Based on the collected list of literature, the server extracts the abstract, conclusions, and experimental results for each document. Next, the server's natural language processing (NLP) module analyzes this information and generates a summary. This NLP processing utilizes the OpenAI API. The input is the text data of the literature, and the output is the extracted summary.

[0200] Step 3: Generating Business Application Proposals

[0201] Based on the generated summary, the server's artificial intelligence (AI) module proposes ways to apply it to the business. At this stage, the summary is used as a prompt, and specific business proposals are generated using the OpenAI API. The input is the summarized text, and the output is a proposal for application methods. Specifically, the server generates prompts such as the following:

[0202] Based on the following summary, please propose an application:

[0203] (Summary text)

[0204] Step 4: Provide the user interface

[0205] The generated business proposals are sent to the terminal, and a visualized operation screen (dashboard) accessible to the user is provided. The terminal displays these proposals using HTML and JavaScript. The input is the business proposal data, and the output is the visualized operation screen. Users can check the information through this dashboard.

[0206] Step 5: Gathering Feedback

[0207] After the user reviews and evaluates the proposal, they submit their feedback to the server via a feedback form. The server collects this feedback and stores it in a database. The input is the user's feedback information, and the output is the result of saving the feedback to the database.

[0208] Step 6: Relearning

[0209] Based on the collected feedback, the server's artificial intelligence model undergoes retraining. This retraining improves the accuracy of subsequent suggestions. In this process, the server analyzes the feedback data and generates new model parameters. The input is the feedback data, and the output is the updated AI model. As a result of retraining, the suggestions improve, and the overall accuracy of the system increases.

[0210] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0211] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and emotion engine. The embodiments for carrying out the present invention are described in detail below.

[0212] 1. Server Role

[0213] Data collection

[0214] The server accesses a scholarly literature database and collects the latest literature related to the specified topic. Queries are performed according to business-related keywords and filtering conditions. The collected literature data is stored in a database on the server.

[0215] Information extraction and summary generation

[0216] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[0217] Generating business application proposals

[0218] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[0219] Analysis of the Emotion Engine

[0220] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[0221] Providing a user interface (UI)

[0222] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[0223] Gathering feedback and learning

[0224] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0225] 2. The role of the terminal

[0226] Dashboard display

[0227] The terminal displays an enterprise dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[0228] Submitting feedback

[0229] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[0230] 3. User Roles

[0231] Information verification and evaluation

[0232] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they decide whether to apply it to their actual marketing strategy.

[0233] Provide feedback

[0234] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. In addition, an emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[0235] Specific example

[0236] Example 1: Application in the development of medical devices

[0237] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates suggestions on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these suggestions to employees in the medical device development department, who review the suggestions and provide feedback. An emotion engine analyzes the emotions expressed by the employees during the feedback process and sends this information back to the server.

[0238] Example 2: Application in improving marketing strategies

[0239] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies. A terminal presents these proposals to sales representatives, who then try out the suggestions and provide feedback. An emotion engine analyzes the user's emotions during feedback and sends the results to the server.

[0240] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system is continuously improved based on feedback that takes user emotions into consideration.

[0241] The following describes the processing flow.

[0242] Step 1:

[0243] The server accesses the academic literature database and searches for the latest literature related to the specified topic. The query is executed according to business-related keywords and filtering conditions.

[0244] Step 2:

[0245] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[0246] Step 3:

[0247] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[0248] Step 4:

[0249] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[0250] Step 5:

[0251] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[0252] Step 6:

[0253] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[0254] Step 7:

[0255] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[0256] Step 8:

[0257] The emotion engine analyzes the user's emotional state when providing feedback. The device acquires the user's text input and voice data and sends the emotion data to the server.

[0258] Step 9:

[0259] The server's emotion engine analyzes the transmitted emotion data to detect the user's emotional state. The analysis results are stored along with the feedback data.

[0260] Step 10:

[0261] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[0262] Step 11:

[0263] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time, and sentiment analysis data is also attached.

[0264] Step 12:

[0265] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[0266] Step 13:

[0267] The server retrains the artificial intelligence model based on feedback data and sentiment analysis results. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[0268] Step 14:

[0269] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[0270] (Example 2)

[0271] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0272] Conventional technologies made the process of efficiently collecting the latest academic literature, extracting its summaries and conclusions, and applying them to actual work time-consuming and limited in accuracy. Furthermore, there was insufficient method for quickly incorporating user feedback to improve the system. Therefore, challenges existed in improving work efficiency and the quality of proposed solutions.

[0273] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0274] In this invention, the server includes means for accessing the latest information resource database and searching for and collecting information related to a specified field; means for automatically extracting summaries, conclusions, and results from the collected information and generating a summary; intelligent means for automatically generating application methods for business based on the generated summary; means for analyzing the user's emotional state using a cognitive analysis engine; means for displaying the generated application methods on an information terminal and providing a user-accessible interface; and means for collecting feedback from the user and continuously improving the intelligent model. This enables the rapid application of the latest academic knowledge to business operations, the realization of efficient business processes, and the continuous improvement of the system.

[0275] An "information resource database" is a database that collects, stores, and provides information related to various fields in a searchable format.

[0276] An "abstract" is a concise summary of the content of a document or report.

[0277] The "conclusion" is the final judgment or assertion derived from the results of literature and research.

[0278] "Results" refer to data and outcomes obtained based on literature and research.

[0279] A "summary" is a short piece of text that concisely summarizes the content of a document or report, extracting the most important points.

[0280] An "intelligent tool" is a system that uses artificial intelligence technology to automatically perform specific tasks.

[0281] A "cognitive analysis engine" is a system that analyzes a user's text input and voice data to detect their emotional state.

[0282] An "information terminal" is a device that allows users to access information through an interface. Examples include personal computers and smartphones.

[0283] "Interface" refers to the operation screen and input tools for users to interact with the system.

[0284] "Feedback" refers to the evaluations and opinions provided by users, which are information used for system improvement and enhancing proposal accuracy.

[0285] "Intelligent model" refers to the structure and patterns of artificial intelligence generated by learning algorithms and used to perform specific tasks.

[0286] The system of the present invention automates the process of collecting the latest information, generating application proposals for business, and continuously improving based on user feedback. The following will explain in detail the embodiments for implementing the present invention.

[0287] Role of the server

[0288] Data collection

[0289] First, the server accesses the information resource database. For this access, APIs (e.g., PubMed API, IEEE Xplore API) are used to search for and effectively collect information related to the specified field. For example, queries are executed with keywords such as "artificial intelligence" and "medical device development", and the obtained data is saved in a database (e.g., MySQL (registered trademark), MongoDB).

[0290] Information extraction and summary generation

[0291] The server analyzes the collected information using an NLP module (e.g., spaCy, BERT). Through this analysis, important information such as the summary, conclusion, and results of the information is extracted. Next, a summary generation algorithm (e.g., TF-IDF, topic modeling) is utilized to convert the extracted information into a summary in a concise and understandable form.

[0292] Generating business application proposals

[0293] Furthermore, the server's intelligent model (e.g., GPT-3, Transformers) generates business application suggestions based on the generated summary. This process uses specific templates (e.g., SWOT analysis framework) to suggest how the new insights can help improve business processes.

[0294] Emotion analysis

[0295] The server is equipped with a cognitive analysis engine (e.g., IBM Watson®, sentimentr) that analyzes user feedback to understand their emotional state. This allows for the acquisition of information useful for assessing the usefulness of suggestions and for future improvements.

[0296] Terminal role

[0297] Dashboard display

[0298] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. This interface is built using, for example, React.js. Through this dashboard, users can review the information and evaluate the suggestions. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[0299] Submitting feedback

[0300] A form is installed on the device to easily collect user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The server analyzes the submitted feedback data and stores it in a database along with the user's emotional state.

[0301] User roles

[0302] Information verification and evaluation

[0303] The user checks the proposed content provided through the dashboard on the terminal and evaluates the proposals useful for the business. For example, when receiving a proposal for a new marketing method, determine whether it can be applied to one's own marketing strategy.

[0304] Providing Feedback

[0305] The user tries the provided proposal and provides feedback on the results. The feedback is given through an evaluation form, and the sentiment engine analyzes the user's input data, and the sentiment state is also saved as feedback.

[0306] Specific Examples

[0307] Example 1: Application in the Development of Medical Devices

[0308] 1. The server collects the latest literature in the medical field and generates a summary using natural language processing.

[0309] 2. The intelligent model generates proposals on how the research results of this literature can be applied to the company's medical devices.

[0310] 3. The terminal presents this proposal to the employees in the medical device development department, and the employees check the content of the proposal and provide feedback.

[0311] 4. The cognitive analysis engine analyzes the sentiment during the employees' feedback and also sends it to the server.

[0312] Example 2: Application in the Improvement of Marketing Strategies

[0313] 1. The server collects the latest literature related to marketing and generates a summary by natural language processing.

[0314] 2. The intelligent model extracts a new consumer behavior analysis method from the literature and proposes how this method can be applied to the marketing strategy.

[0315] 3. The terminal presents this proposal to the sales representative, who then tries out the proposal and provides feedback on the results.

[0316] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback and sends the results to the server.

[0317] Example of a prompt

[0318] "Summarize the latest academic literature on medical devices and propose how to apply it to our company's product development."

[0319] "Collect the latest literature on new marketing techniques, generate summaries, and propose how these techniques can be applied to consumer behavior analysis."

[0320] As described above, through the system of the present invention, companies can apply academic knowledge to their operations quickly and efficiently, thereby achieving innovation in business processes and continuous improvement of systems.

[0321] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0322] Step 1:

[0323] Data collection

[0324] The server accesses an information resource database (e.g., PubMed, IEEE Xplore). The input is a query related to a specified topic (e.g., "artificial intelligence," "medical device development"). Based on this query, the server searches the database for relevant information. The search results (bibliographic data) are output. The server saves this bibliographic data to a database (e.g., MySQL, MongoDB).

[0325] Step 2:

[0326] Information Extraction

[0327] The server analyzes collected literature data using an NLP module (e.g., spaCy, BERT). The input is literature data stored in a database. The NLP module automatically extracts the abstract, conclusion, and results of the literature. This extracted information is then generated as output. This information is passed on to the next step in summary generation.

[0328] Step 3:

[0329] Summary generation

[0330] The server uses a summarization algorithm (e.g., TF-IDF, topic modeling) to generate a concise and easy-to-understand summary from the extracted information. The input is the extracted information. The algorithm selects key points and formats them into a summary. The generated summary is output and used to generate business application proposals.

[0331] Step 4:

[0332] Generating business application proposals

[0333] The server's intelligent model (e.g., GPT-3, Transformers) automatically generates business application proposals based on the generated summary. The input is the generated summary. The intelligent model constructs the proposals using a specific template (e.g., SWOT analysis framework). The proposed content is output and formatted for display.

[0334] Step 5:

[0335] Emotion analysis

[0336] A cognitive analysis engine (e.g., IBM Watson, sentimentr) installed on the server analyzes user feedback. The input is feedback text or audio data sent by the user. The analysis engine detects the emotional state (e.g., positive, negative) and generates the result as output. This analysis result is also stored in a database.

[0337] Step 6:

[0338] Dashboard display

[0339] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. Input consists of suggestions and summary information sent from the server. The terminal builds the dashboard using React.js and displays it to the user. The user can access the information through this dashboard. The displayed content may also be dynamically adjusted based on the user's emotional state.

[0340] Step 7:

[0341] Submitting feedback

[0342] Users evaluate the proposals through a dashboard and submit the feedback form with the necessary information. This feedback consists of user opinions regarding the evaluation and potential improvements to the proposals. The feedback data is sent from the device to the server, where it is analyzed by a cognitive analysis engine, including the user's emotional state.

[0343] Step 8:

[0344] Storing and learning from feedback

[0345] The server stores user feedback data and sentiment analysis results in a database. The input consists of user-provided feedback and analysis results of emotional states. This data is used in the next model retraining process. The output is an improvement to the AI ​​model and increased suggestion accuracy.

[0346] The above outlines the specific processing steps of this system. Through the specific actions of the server, terminal, and user in each step, it becomes possible to quickly collect the latest academic knowledge and apply it to work. Furthermore, the system is continuously improved based on user feedback.

[0347] (Application Example 2)

[0348] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0349] Traditional advertising strategies faced the challenge of quickly gathering information on the latest marketing techniques and consumer behavior analysis, and then formulating effective strategies based on that information. Furthermore, there was a lack of systems capable of evaluating the effectiveness of advertising strategies and providing real-time feedback and sentiment analysis for continuous improvement.

[0350] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a dashboard accessible to the user, means for collecting feedback from the user and continuously improving the artificial intelligence model, and means for providing advertising-related information via a display device that allows the user to visually confirm it. This enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[0351] A "scholarly literature database" is a database that contains academic research results and papers.

[0352] An "abstract" is a short, concise summary of the content of a document, highlighting its main points and conclusions.

[0353] A "conclusion" refers to the final judgment or opinion that the author has arrived at as a result of their research in a given document.

[0354] "Experimental results" refer to data and observations obtained during the course of research or experiments.

[0355] A "summary" is a concise document that summarizes the main points of a text, and is used to aid in understanding the overall content.

[0356] "Artificial intelligence" is a general term for software and systems that can perform information processing and decision-making by mimicking human intelligence.

[0357] A "terminal" is an electronic device used by a user to access and operate information.

[0358] A "dashboard" is a visual interface that allows users to see multiple pieces of information at a glance.

[0359] "Feedback" refers to the opinions and evaluations that users provide to a system or service.

[0360] A "display device" is a device used to visually display information, and includes screens and displays.

[0361] "Advertising-related information" refers to useful data, knowledge, and analytical methods within the advertising industry.

[0362] "Visual inspection" refers to the act of directly seeing something with the human eye.

[0363] "Collection" refers to a series of activities that involve gathering specific information or data.

[0364] "Extraction" refers to the operation of taking out specific elements or information from a whole.

[0365] "Generation" refers to the process of creating new information or data.

[0366] "Provision" refers to the act of a system or service delivering information to a user.

[0367] "Most suitable" means being judged to be the best for a particular purpose.

[0368] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and display device as a means for displaying advertising-related information. This system enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[0369] 1. Server Role

[0370] Data collection

[0371] The server accesses academic literature databases and collects the latest literature related to the specified topic. The collection process uses work-related keywords and filtering criteria. The literature data is stored in a database on the server.

[0372] Information extraction and summary generation

[0373] Using a natural language processing (NLP) module installed on the server, abstracts, conclusions, and experimental results are automatically extracted from collected literature to generate summaries. Generative AI models such as Hugging Face's transformers library are used for summary generation.

[0374] Generating business application proposals

[0375] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates that present application methods tailored to predefined business contexts and business processes.

[0376] Analysis of the Emotion Engine

[0377] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[0378] Providing a user interface (UI)

[0379] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[0380] Gathering feedback and learning

[0381] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This improves the accuracy and usefulness of future suggestions.

[0382] 2. The role of the terminal

[0383] Dashboard display

[0384] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[0385] Submitting feedback

[0386] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[0387] 3. User Roles

[0388] Information verification and evaluation

[0389] Users who are advertising industry professionals review the suggestions provided through the dashboard on their devices and evaluate those that are useful for their work. For example, if a new marketing method is suggested, they decide whether to apply it to their actual advertising strategy.

[0390] Provide feedback

[0391] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form and sent to the server. An emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[0392] Specific example

[0393] Sample generation AI prompt text

[0394] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[0395] Abstract: {Abstract of the literature}

[0396] Conclusion: {Conclusion of the literature}

[0397] for example:

[0398] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[0399] Abstract: This study focuses on the latest trends in consumer behavior analysis...

[0400] Conclusion: The findings suggest that integrating AI models with traditional marketing strategies...

[0401] This system enables advertising professionals to quickly develop effective advertising strategies based on the latest marketing techniques and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The server accesses an academic literature database and collects the latest literature related to the specified topic. The data used as input consists of business-related keywords and filtering conditions. This ensures that the latest marketing-related literature is stored in the database on the server.

[0405] Step 2:

[0406] A natural language processing (NLP) module installed on the server automatically extracts abstracts, conclusions, and experimental results from collected literature. The input is the literature data collected in step 1, and the output is the extracted abstracts, conclusions, and experimental results. Specifically, the analysis is performed using the Hugging Face transformers library.

[0407] Step 3:

[0408] The server processes the extracted information for summary generation, concisely summarizing the key points. The input is the information extracted in step 2, and the output is the generated summary. This step also utilizes the Hugging Face transformers library.

[0409] Step 4:

[0410] An artificial intelligence (AI) module installed on the server automatically generates application methods for business operations based on the generated summary. The input is the summary generated in step 3, and the output is a proposal for application methods. The AI ​​module generates proposals using predefined templates that correspond to the business context and business processes.

[0411] Step 5:

[0412] The server displays the generated application methods on the terminal. A user interface (UI) for this purpose is provided on the dashboard, making it accessible to the user. The input is the application method from step 4, and the output is the suggestion displayed on the user's terminal. The dashboard is implemented using web technologies such as HTML and JavaScript.

[0413] Step 6:

[0414] Users review application methods through a dashboard on their devices and apply them to their actual advertising strategies. Users review the suggestions and provide feedback. The input is the suggestions displayed by the server, and the output is the user's evaluation and feedback. User actions include entering opinions into a feedback form and submitting it.

[0415] Step 7:

[0416] The device collects user feedback and sends it to the server. The input is the user's feedback, and the output is the feedback data sent to the server. During this process, sentiment analysis is performed on the device, analyzing text input and voice data.

[0417] Step 8:

[0418] The server stores the collected feedback data in a database and uses it along with the sentiment analysis results in the next model retraining process. The input is the feedback data sent in step 7, and the output is the improved AI model. Specifically, the feedback data is analyzed and reused as training data for the AI ​​model.

[0419] These steps enable advertising professionals to quickly incorporate the latest marketing techniques and consumer behavior analysis to develop effective advertising strategies, and to continuously improve them through real-time feedback and sentiment analysis.

[0420] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0421] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0422] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0423] [Second Embodiment]

[0424] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0425] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0426] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0427] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0428] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0429] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0430] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0431] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0432] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0433] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0434] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0435] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0436] The system of the present invention is realized through the interaction of a server, terminals, and users. The embodiments for carrying out the present invention are described in detail below.

[0437] 1. Server Role

[0438] Data collection

[0439] The server accesses academic literature databases and collects the latest literature related to the specified topic. This includes scheduled searches and real-time searches based on user requests. The collected literature data is stored in a database on the server.

[0440] Information extraction and summary generation

[0441] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[0442] Generating business application proposals

[0443] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[0444] Providing a user interface (UI)

[0445] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. The dashboard displays the latest suggestions and a feedback form.

[0446] Gathering feedback and learning

[0447] The server collects user feedback and stores it in a database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0448] 2. The role of the terminal

[0449] Dashboard display

[0450] The terminal displays an enterprise dashboard for user access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface.

[0451] Submitting feedback

[0452] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the proposed solutions. This feedback is sent to the server in real time.

[0453] 3. User Roles

[0454] Information verification and evaluation

[0455] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[0456] Provide feedback

[0457] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[0458] Specific example

[0459] Example 1: Application in the development of medical devices

[0460] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates proposals on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[0461] Example 2: Application in improving marketing strategies

[0462] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. The terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[0463] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system can be continuously improved through continuous feedback.

[0464] The following describes the processing flow.

[0465] Step 1:

[0466] The server accesses the academic literature database and searches for the latest literature based on the specified topic. The query is executed according to business-related keywords and filtering conditions.

[0467] Step 2:

[0468] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[0469] Step 3:

[0470] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[0471] Step 4:

[0472] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[0473] Step 5:

[0474] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[0475] Step 6:

[0476] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[0477] Step 7:

[0478] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[0479] Step 8:

[0480] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[0481] Step 9:

[0482] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time.

[0483] Step 10:

[0484] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[0485] Step 11:

[0486] The server retrains the artificial intelligence model based on the feedback data. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[0487] Step 12:

[0488] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[0489] (Example 1)

[0490] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0491] Currently, for companies to apply academic literature to their operations, they need to manually collect, analyze, and devise application methods for vast amounts of information. This process consumes a great deal of time and effort, and the accuracy and usefulness of the analysis results and application methods are inconsistent because they depend on human resources. Furthermore, even when feedback is collected, there is a lack of mechanisms to effectively utilize it and reflect it in future proposals, making continuous improvement difficult. As a result, it is difficult for companies to quickly and efficiently incorporate the latest academic knowledge into their operations and innovate their business processes.

[0492] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0493] This invention includes a server that includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a user-accessible dashboard, means for collecting feedback from users and storing it in an evaluation database, and means for retraining the artificial intelligence model based on the collected feedback data to successively improve the accuracy and usefulness of future suggestions. This enables companies to efficiently carry out everything from collecting academic literature to generating application suggestions and even continuous improvement through feedback, allowing for rapid and highly accurate innovation of business processes.

[0494] A "server" is a computer system that provides specific services to other computers (clients) on a network.

[0495] A "scholarly literature database" is a database system that collects and makes searchable and accessible literature information such as academic papers and research results.

[0496] An "abstract" is a concise summary of the content of an academic paper or report, providing an overview of the research's objectives, methods, results, and conclusions.

[0497] The "Conclusion" section is the part of the document that summarizes the main findings and conclusions derived from the results of research or experiments.

[0498] "Experimental results" refer to data and observations obtained in research or experiments, and include the results of their analysis.

[0499] A "Natural Language Processing (NLP) module" is a software module for analyzing and understanding text data, and in particular, it processes human language using machine learning and generative AI models.

[0500] "Artificial intelligence tools" refer to systems or modules that analyze data using machine learning algorithms or generative AI models and make judgments and suggestions like humans.

[0501] A "dashboard" is an interface that allows users to visually view and manipulate information, and it is a screen that displays specific data or analysis results.

[0502] "Feedback" refers to evaluations and opinions provided by users, and is information collected to improve the system and inform future suggestions.

[0503] An "evaluation database" is a database system that stores collected feedback information and uses it for analysis and model retraining.

[0504] "Retraining" is the process of training an existing machine learning model again using new data and feedback information to improve the model's accuracy and usefulness.

[0505] The system of the present invention is realized through the mutual cooperation of a server, terminal, and user. The embodiments for carrying out the present invention will be described in detail below.

[0506] The server accesses the latest academic literature databases to search for and collect literature related to the specified topic. Specifically, it utilizes databases such as PubMed and IEEE Xplore. The collected literature data is stored in the server's database in JSON format or similar.

[0507] The server is equipped with a natural language processing (NLP) module, which utilizes generative AI models such as BERT and GPT-3. This NLP module analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. This analysis process extracts key information and generates a summary. The summary generation algorithm picks out important keywords and sentences from the extracted text and creates a concise summary.

[0508] Next, the server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary. This AI module uses a business proposal template to suggest how the new algorithm or method can contribute to business processes. The generated application methods and summary are created in HTML format and sent to the terminal via WebSocket or REST API.

[0509] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface. The dashboard also displays a feedback form, allowing users to input and submit their opinions on the effectiveness and areas for improvement of the suggested content.

[0510] User feedback is sent to the server in real time and stored in an evaluation database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0511] As a concrete example, the server collects the latest literature related to the topic of "medical devices" from PubMed and analyzes it using an NLP module. Then, based on the summary generated by the AI ​​module, it proposes applications for medical device development. The terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[0512] A similar process can be applied to improving marketing strategies. A server collects the latest marketing-related literature and generates summaries. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. A terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[0513] An example of a prompt might be: "Collect the latest marketing-related literature, generate summaries, and create marketing strategy proposals based on new consumer behavior analysis methods."

[0514] As described above, the system of the present invention enables the rapid and accurate application of academic knowledge to business operations through the collaboration of a server, terminal, and user, via data collection, summary generation, business application proposals, feedback collection, and retraining.

[0515] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0516] Step 1:

[0517] The server accesses academic literature databases to search for and collect literature related to the specified topic.

[0518] Specific operation: The server sends queries to databases such as PubMed and IEEE Xplore based on a regular schedule or user requests. The retrieved bibliographic data is stored in JSON format. The input for this step is the search query, and the output is the collected bibliographic data.

[0519] Step 2:

[0520] A natural language processing (NLP) module on the server analyzes the collected literature data, extracts abstracts, conclusions, and experimental results, and generates a summary.

[0521] Specific operation: The NLP module analyzes sections of literature using generative AI models such as BERT and GPT-3, and extracts important information.

[0522] The input for this step is collected literature data, and the output is the analyzed information and summary.

[0523] Step 3:

[0524] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary.

[0525] Specific operation: The AI ​​module utilizes business templates to suggest how new algorithms and methods can contribute to business processes.

[0526] The input for this step is the generated summary, and the output is a proposed application method.

[0527] Step 4:

[0528] The server displays the generated application methods on the terminal and provides a user-accessible dashboard.

[0529] Specific operation: Generates proposal content and summary in HTML format and sends it to the terminal via WebSocket or REST API.

[0530] The input for this step is a proposed application method, and the output is a dashboard displayed on the terminal.

[0531] Step 5:

[0532] The dashboard on the device displays information to the user and collects feedback.

[0533] Specific operation: The device uses a web browser to render HTML data provided by the server, retrieves user-entered feedback information using JavaScript, and sends it to the server in real time.

[0534] The input for this step is the information from the dashboard, and the output is the collected feedback.

[0535] Step 6:

[0536] The server collects feedback provided by users and stores it in an evaluation database.

[0537] Specific operation: Feedback data is stored in an SQL database and used for subsequent natural language processing and AI model training.

[0538] The input for this step is the collected feedback, and the output is the feedback data stored in the evaluation database.

[0539] Step 7:

[0540] The server retrains its artificial intelligence model based on the collected feedback data, continuously improving the accuracy and usefulness of subsequent suggestions.

[0541] Specific action: Adjust the parameters of the generated AI model using the new feedback data and retrain it.

[0542] The input for this step is feedback data stored in an evaluation database, and the output is an improved generative AI model.

[0543] (Application Example 1)

[0544] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0545] Conventional systems for collecting and analyzing academic literature have made it difficult to quickly and accurately analyze the latest information and propose concrete ways to apply it to business operations. In particular, there has been a lack of systems that effectively utilize information visualization and user feedback, resulting in problems in streamlining business processes and improving the accuracy of proposals.

[0546] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0547] In this invention, the server includes means for accessing the latest academic literature databases, searching for and collecting literature related to a specified topic; means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries; artificial intelligence means for automatically generating application methods for business based on the generated summaries; means for displaying the generated application methods on a mobile communication terminal and providing a user-accessible visualized operation screen; means for collecting feedback from users and continuously improving the artificial intelligence model; and means for efficiently organizing the collected and generated information and generating proposals adaptable to various business processes. This makes it possible to quickly analyze the latest information, present it to users in a visually easy-to-understand format, and continuously improve the proposals through user feedback.

[0548] A "scholarly literature database" is an information aggregation system that collects and stores academic information such as research papers, academic books, and technical reports in a searchable format.

[0549] "Specified topics" refer to keywords or theme settings used to identify research areas or themes that the user is interested in.

[0550] "Collection methods" refer to technologies for accessing academic literature databases, automatically searching for literature related to a specified topic, and obtaining data.

[0551] An "abstract" is a concise summary of the research objectives, methods, and main findings in a document.

[0552] The "conclusion" is the section that outlines the overall judgment and future research direction derived from the research results.

[0553] "Experimental results" refers to the section that shows the specific results and data from experiments and surveys conducted in a study.

[0554] A "summary generation method" is a technique for extracting important information from collected literature and organizing it into a concise and easy-to-understand format.

[0555] "Artificial intelligence methods" refer to artificial intelligence technologies that analyze large amounts of data, recognize patterns, and generate new information and application methods.

[0556] A "mobile communication terminal" refers to a mobile device, such as a smartphone or tablet, that can connect to the internet and receive and display information.

[0557] A "visualized user interface" is a screen designed to graphically display collected information and generated suggestions, allowing users to operate it intuitively.

[0558] It refers to "feedback."

[0559] "Retraining" is the process by which an artificial intelligence model improves its prediction accuracy and suggestions based on newly collected data and user feedback.

[0560] A "business process" refers to a series of tasks or procedures performed in business or research to achieve a specific objective.

[0561] "Means for generating suggestions" refers to technologies that present users with useful action plans and areas for improvement based on collected data and generated summaries.

[0562] The system for implementing this invention collects the latest literature from a scholarly literature database, analyzes it, generates suggestions for its application to business operations, and continuously improves the system through feedback. This system is realized through the interaction of a server, terminals, and users.

[0563] Server Role

[0564] The server plays the following main roles:

[0565] 1. Data collection:

[0566] The server accesses academic literature databases on the internet to search for and collect the latest literature related to a specified topic. Specifically, it uses APIs to retrieve bibliographic information. Here, the requests library is used to access the APIs of academic literature databases.

[0567] 2. Information extraction and summarization using natural language processing:

[0568] Natural language processing (NLP) techniques are used to automatically extract abstracts, conclusions, and experimental results from collected literature and generate summaries. Here, the OpenAI API is used to generate the summaries. This process involves analyzing the main parts of the literature and concisely summarizing the key information.

[0569] 3. Generating business application proposals:

[0570] Artificial intelligence (AI) technology is used to generate application methods for business operations based on summarized information. The generated summaries are used as prompts, and business suggestions are generated via the OpenAI API. For example, the following prompts are used:

[0571] Based on the following summary, please propose an application:

[0572] (Summary text)

[0573] 4. Providing a user interface:

[0574] The generated suggestions are displayed on the device, providing a visualized, user-accessible interface. This uses a dashboard built with HTML and JavaScript. The dashboard displays the suggestions and a feedback form.

[0575] 5. Gathering feedback and relearning:

[0576] We collect user feedback and use it to retrain the AI ​​model. This retraining improves the accuracy of future suggestions. The feedback is sent to and collected on the server in real time.

[0577] Terminal role

[0578] The terminal primarily serves the following roles:

[0579] 1. Display the dashboard:

[0580] The terminal displays a visualized interface (dashboard) for the user to access. This includes the latest business application proposals and summarized academic research information sent from the server.

[0581] 2. Submitting feedback:

[0582] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the suggestions. This feedback is sent to the server and used for retraining.

[0583] User roles

[0584] The user will have the following roles:

[0585] 1. Information verification and evaluation:

[0586] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[0587] 2. Providing feedback:

[0588] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[0589] Specific application examples

[0590] For example, if a user specifies "artificial intelligence" as their topic, the server will collect the latest relevant literature and generate summaries from it. Based on these summaries, it will then suggest how they can be applied to content delivery services. Specifically, a possible suggestion might be, "Using this new AI algorithm will improve the accuracy of the recommendation system." Users can view these suggestions on a dashboard and contribute to improving the system's accuracy by providing feedback.

[0591] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0592] Step 1: Data Collection

[0593] The server receives a topic specified by the user. The server accesses academic literature databases on the internet and searches for literature related to the specified topic. Specifically, the server uses the requests library to send requests to the literature database API and retrieve relevant literature information. The input is the topic specified by the user, and the output is a list of retrieved literature.

[0594] Step 2: Information Extraction and Summary Generation

[0595] Based on the collected list of literature, the server extracts the abstract, conclusions, and experimental results for each document. Next, the server's natural language processing (NLP) module analyzes this information and generates a summary. This NLP processing utilizes the OpenAI API. The input is the text data of the literature, and the output is the extracted summary.

[0596] Step 3: Generating Business Application Proposals

[0597] Based on the generated summary, the server's artificial intelligence (AI) module proposes ways to apply it to the business. At this stage, the summary is used as a prompt, and specific business proposals are generated using the OpenAI API. The input is the summarized text, and the output is a proposal for application methods. Specifically, the server generates prompts such as the following:

[0598] Based on the following summary, please propose an application:

[0599] (Summary text)

[0600] Step 4: Provide the user interface

[0601] The generated business proposals are sent to the terminal, and a visualized operation screen (dashboard) accessible to the user is provided. The terminal displays these proposals using HTML and JavaScript. The input is the business proposal data, and the output is the visualized operation screen. Users can check the information through this dashboard.

[0602] Step 5: Gathering Feedback

[0603] After the user reviews and evaluates the proposal, they submit their feedback to the server via a feedback form. The server collects this feedback and stores it in a database. The input is the user's feedback information, and the output is the result of saving the feedback to the database.

[0604] Step 6: Relearning

[0605] Based on the collected feedback, the server's artificial intelligence model undergoes retraining. This retraining improves the accuracy of subsequent suggestions. In this process, the server analyzes the feedback data and generates new model parameters. The input is the feedback data, and the output is the updated AI model. As a result of retraining, the suggestions improve, and the overall accuracy of the system increases.

[0606] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0607] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and emotion engine. The embodiments for carrying out the present invention are described in detail below.

[0608] 1. Server Role

[0609] Data collection

[0610] The server accesses a scholarly literature database and collects the latest literature related to the specified topic. Queries are performed according to business-related keywords and filtering conditions. The collected literature data is stored in a database on the server.

[0611] Information extraction and summary generation

[0612] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[0613] Generating business application proposals

[0614] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[0615] Analysis of the Emotion Engine

[0616] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[0617] Providing a user interface (UI)

[0618] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[0619] Gathering feedback and learning

[0620] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0621] 2. The role of the terminal

[0622] Dashboard display

[0623] The terminal displays an enterprise dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[0624] Submitting feedback

[0625] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[0626] 3. User Roles

[0627] Information verification and evaluation

[0628] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they decide whether to apply it to their actual marketing strategy.

[0629] Provide feedback

[0630] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. In addition, an emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[0631] Specific example

[0632] Example 1: Application in the development of medical devices

[0633] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates suggestions on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these suggestions to employees in the medical device development department, who review the suggestions and provide feedback. An emotion engine analyzes the emotions expressed by the employees during the feedback process and sends this information back to the server.

[0634] Example 2: Application in improving marketing strategies

[0635] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies. A terminal presents these proposals to sales representatives, who then try out the suggestions and provide feedback. An emotion engine analyzes the user's emotions during feedback and sends the results to the server.

[0636] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system is continuously improved based on feedback that takes user emotions into consideration.

[0637] The following describes the processing flow.

[0638] Step 1:

[0639] The server accesses the academic literature database and searches for the latest literature related to the specified topic. The query is executed according to business-related keywords and filtering conditions.

[0640] Step 2:

[0641] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[0642] Step 3:

[0643] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[0644] Step 4:

[0645] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[0646] Step 5:

[0647] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[0648] Step 6:

[0649] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[0650] Step 7:

[0651] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[0652] Step 8:

[0653] The emotion engine analyzes the user's emotional state when providing feedback. The device acquires the user's text input and voice data and sends the emotion data to the server.

[0654] Step 9:

[0655] The server's emotion engine analyzes the transmitted emotion data to detect the user's emotional state. The analysis results are stored along with the feedback data.

[0656] Step 10:

[0657] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[0658] Step 11:

[0659] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time, and sentiment analysis data is also attached.

[0660] Step 12:

[0661] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[0662] Step 13:

[0663] The server retrains the artificial intelligence model based on feedback data and sentiment analysis results. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[0664] Step 14:

[0665] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[0666] (Example 2)

[0667] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0668] Conventional technologies made the process of efficiently collecting the latest academic literature, extracting its summaries and conclusions, and applying them to actual work time-consuming and limited in accuracy. Furthermore, there was insufficient method for quickly incorporating user feedback to improve the system. Therefore, challenges existed in improving work efficiency and the quality of proposed solutions.

[0669] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0670] In this invention, the server includes means for accessing the latest information resource database and searching for and collecting information related to a specified field; means for automatically extracting summaries, conclusions, and results from the collected information and generating a summary; intelligent means for automatically generating application methods for business based on the generated summary; means for analyzing the user's emotional state using a cognitive analysis engine; means for displaying the generated application methods on an information terminal and providing a user-accessible interface; and means for collecting feedback from the user and continuously improving the intelligent model. This enables the rapid application of the latest academic knowledge to business operations, the realization of efficient business processes, and the continuous improvement of the system.

[0671] An "information resource database" is a database that collects, stores, and provides information related to various fields in a searchable format.

[0672] An "abstract" is a concise summary of the content of a document or report.

[0673] The "conclusion" is the final judgment or assertion derived from the results of literature and research.

[0674] "Results" refer to data and outcomes obtained based on literature and research.

[0675] A "summary" is a short piece of text that concisely summarizes the content of a document or report, extracting the most important points.

[0676] An "intelligent tool" is a system that uses artificial intelligence technology to automatically perform specific tasks.

[0677] A "cognitive analysis engine" is a system that analyzes a user's text input and voice data to detect their emotional state.

[0678] An "information terminal" is a device that allows users to access information through an interface. Examples include personal computers and smartphones.

[0679] An "interface" refers to the user interface or input tools that allow a user to interact with a system.

[0680] "Feedback" refers to evaluations and opinions provided by users, and is used to improve the system and enhance the accuracy of suggestions.

[0681] An "intelligent model" refers to the structure or pattern of artificial intelligence generated by a learning algorithm and used to perform a specific task.

[0682] The system of the present invention automates the process of collecting the latest information, generating application suggestions for business operations, and continuously improving it based on user feedback. The embodiments for carrying out the present invention are described in detail below.

[0683] Server Role

[0684] Data collection

[0685] First, the server accesses an information resource database. This access uses an API (e.g., PubMed API, IEEE Xplore API). It searches for and effectively collects information related to a specified field. For example, it executes queries using keywords such as "artificial intelligence" or "medical device development" and stores the retrieved data in a database (e.g., MySQL, MongoDB).

[0686] Information extraction and summary generation

[0687] The server analyzes the collected information using an NLP module (e.g., spaCy, BERT). This analysis extracts key information such as the summary, conclusions, and results. Next, a summarization algorithm (e.g., TF-IDF, topic modeling) is used to convert the extracted information into a concise and easy-to-understand summary.

[0688] Generating business application proposals

[0689] Furthermore, the server's intelligent model (e.g., GPT-3, Transformers) generates business application suggestions based on the generated summary. This process uses specific templates (e.g., SWOT analysis framework) to suggest how the new insights can help improve business processes.

[0690] Emotion analysis

[0691] The server is equipped with a cognitive analysis engine (e.g., IBM Watson, sentimentr) that analyzes user feedback to understand their emotional state. This allows for the acquisition of information that can be used to assess the usefulness of suggestions and improve future offerings.

[0692] Terminal role

[0693] Dashboard display

[0694] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. This interface is built using, for example, React.js. Through this dashboard, users can review the information and evaluate the suggestions. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[0695] Submitting feedback

[0696] A form is installed on the device to easily collect user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The server analyzes the submitted feedback data and stores it in a database along with the user's emotional state.

[0697] User roles

[0698] Information verification and evaluation

[0699] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they will determine whether it is applicable to their own marketing strategy.

[0700] Provide feedback

[0701] Users try out the suggested features and provide feedback on the results. Feedback is given through an evaluation form, and the emotion engine analyzes the user's input data, saving their emotional state as part of the feedback.

[0702] Specific example

[0703] Example 1: Application in the development of medical devices

[0704] 1. The server collects the latest medical literature and generates summaries using natural language processing.

[0705] 2. The intelligent model generates proposals on how the research findings in this document can be applied to the company's medical devices.

[0706] 3. The terminal presents this proposal to an employee in the medical device development department, who reviews the proposal and provides feedback.

[0707] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback, and this information is also sent to the server.

[0708] Example 2: Application in improving marketing strategies

[0709] 1. The server collects the latest marketing-related literature and generates summaries using natural language processing.

[0710] 2. The intelligent model extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies.

[0711] 3. The terminal presents this proposal to the sales representative, who then tries out the proposal and provides feedback on the results.

[0712] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback and sends the results to the server.

[0713] Example of a prompt

[0714] "Summarize the latest academic literature on medical devices and propose how to apply it to our company's product development."

[0715] "Collect the latest literature on new marketing techniques, generate summaries, and propose how these techniques can be applied to consumer behavior analysis."

[0716] As described above, through the system of the present invention, companies can apply academic knowledge to their operations quickly and efficiently, thereby achieving innovation in business processes and continuous improvement of systems.

[0717] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0718] Step 1:

[0719] Data collection

[0720] The server accesses an information resource database (e.g., PubMed, IEEE Xplore). The input is a query related to a specified topic (e.g., "artificial intelligence," "medical device development"). Based on this query, the server searches the database for relevant information. The search results (bibliographic data) are output. The server saves this bibliographic data to a database (e.g., MySQL, MongoDB).

[0721] Step 2:

[0722] Information Extraction

[0723] The server analyzes collected literature data using an NLP module (e.g., spaCy, BERT). The input is literature data stored in a database. The NLP module automatically extracts the abstract, conclusion, and results of the literature. This extracted information is then generated as output. This information is passed on to the next step in summary generation.

[0724] Step 3:

[0725] Summary generation

[0726] The server uses a summarization algorithm (e.g., TF-IDF, topic modeling) to generate a concise and easy-to-understand summary from the extracted information. The input is the extracted information. The algorithm selects key points and formats them into a summary. The generated summary is output and used to generate business application proposals.

[0727] Step 4:

[0728] Generating business application proposals

[0729] The server's intelligent model (e.g., GPT-3, Transformers) automatically generates business application proposals based on the generated summary. The input is the generated summary. The intelligent model constructs the proposals using a specific template (e.g., SWOT analysis framework). The proposed content is output and formatted for display.

[0730] Step 5:

[0731] Emotion analysis

[0732] A cognitive analysis engine (e.g., IBM Watson, sentimentr) installed on the server analyzes user feedback. The input is feedback text or audio data sent by the user. The analysis engine detects the emotional state (e.g., positive, negative) and generates the result as output. This analysis result is also stored in a database.

[0733] Step 6:

[0734] Dashboard display

[0735] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. Input consists of suggestions and summary information sent from the server. The terminal builds the dashboard using React.js and displays it to the user. The user can access the information through this dashboard. The displayed content may also be dynamically adjusted based on the user's emotional state.

[0736] Step 7:

[0737] Submitting feedback

[0738] Users evaluate the proposals through a dashboard and submit the feedback form with the necessary information. This feedback consists of user opinions regarding the evaluation and potential improvements to the proposals. The feedback data is sent from the device to the server, where it is analyzed by a cognitive analysis engine, including the user's emotional state.

[0739] Step 8:

[0740] Storing and learning from feedback

[0741] The server stores user feedback data and sentiment analysis results in a database. The input consists of user-provided feedback and analysis results of emotional states. This data is used in the next model retraining process. The output is an improvement to the AI ​​model and increased suggestion accuracy.

[0742] The above outlines the specific processing steps of this system. Through the specific actions of the server, terminal, and user in each step, it becomes possible to quickly collect the latest academic knowledge and apply it to work. Furthermore, the system is continuously improved based on user feedback.

[0743] (Application Example 2)

[0744] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0745] Traditional advertising strategies faced the challenge of quickly gathering information on the latest marketing techniques and consumer behavior analysis, and then formulating effective strategies based on that information. Furthermore, there was a lack of systems capable of evaluating the effectiveness of advertising strategies and providing real-time feedback and sentiment analysis for continuous improvement.

[0746] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a dashboard accessible to the user, means for collecting feedback from the user and continuously improving the artificial intelligence model, and means for providing advertising-related information via a display device that allows the user to visually confirm it. This enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[0747] A "scholarly literature database" is a database that contains academic research results and papers.

[0748] An "abstract" is a short, concise summary of the content of a document, highlighting its main points and conclusions.

[0749] A "conclusion" refers to the final judgment or opinion that the author has arrived at as a result of their research in a given document.

[0750] "Experimental results" refer to data and observations obtained during the course of research or experiments.

[0751] A "summary" is a concise document that summarizes the main points of a text, and is used to aid in understanding the overall content.

[0752] "Artificial intelligence" is a general term for software and systems that can perform information processing and decision-making by mimicking human intelligence.

[0753] A "terminal" is an electronic device used by a user to access and operate information.

[0754] A "dashboard" is a visual interface that allows users to see multiple pieces of information at a glance.

[0755] "Feedback" refers to the opinions and evaluations that users provide to a system or service.

[0756] A "display device" is a device used to visually display information, and includes screens and displays.

[0757] "Advertising-related information" refers to useful data, knowledge, and analytical methods within the advertising industry.

[0758] "Visual inspection" refers to the act of directly seeing something with the human eye.

[0759] "Collection" refers to a series of activities that involve gathering specific information or data.

[0760] "Extraction" refers to the operation of taking out specific elements or information from a whole.

[0761] "Generation" refers to the process of creating new information or data.

[0762] "Provision" refers to the act of a system or service delivering information to a user.

[0763] "Most suitable" means being judged to be the best for a particular purpose.

[0764] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and display device as a means for displaying advertising-related information. This system enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[0765] 1. Server Role

[0766] Data collection

[0767] The server accesses academic literature databases and collects the latest literature related to the specified topic. The collection process uses work-related keywords and filtering criteria. The literature data is stored in a database on the server.

[0768] Information extraction and summary generation

[0769] Using a natural language processing (NLP) module installed on the server, abstracts, conclusions, and experimental results are automatically extracted from collected literature to generate summaries. Generative AI models such as Hugging Face's transformers library are used for summary generation.

[0770] Generating business application proposals

[0771] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates that present application methods tailored to predefined business contexts and business processes.

[0772] Analysis of the Emotion Engine

[0773] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[0774] Providing a user interface (UI)

[0775] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[0776] Gathering feedback and learning

[0777] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This improves the accuracy and usefulness of future suggestions.

[0778] 2. The role of the terminal

[0779] Dashboard display

[0780] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[0781] Submitting feedback

[0782] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[0783] 3. User Roles

[0784] Information verification and evaluation

[0785] Users who are advertising industry professionals review the suggestions provided through the dashboard on their devices and evaluate those that are useful for their work. For example, if a new marketing method is suggested, they decide whether to apply it to their actual advertising strategy.

[0786] Provide feedback

[0787] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form and sent to the server. An emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[0788] Specific example

[0789] Sample generation AI prompt text

[0790] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[0791] Abstract: {Abstract of the literature}

[0792] Conclusion: {Conclusion of the literature}

[0793] for example:

[0794] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[0795] Abstract: This study focuses on the latest trends in consumer behavior analysis...

[0796] Conclusion: The findings suggest that integrating AI models with traditional marketing strategies...

[0797] This system enables advertising professionals to quickly develop effective advertising strategies based on the latest marketing techniques and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] The server accesses an academic literature database and collects the latest literature related to the specified topic. The data used as input consists of business-related keywords and filtering conditions. This ensures that the latest marketing-related literature is stored in the database on the server.

[0801] Step 2:

[0802] A natural language processing (NLP) module installed on the server automatically extracts abstracts, conclusions, and experimental results from collected literature. The input is the literature data collected in step 1, and the output is the extracted abstracts, conclusions, and experimental results. Specifically, the analysis is performed using the Hugging Face transformers library.

[0803] Step 3:

[0804] The server processes the extracted information for summary generation, concisely summarizing the key points. The input is the information extracted in step 2, and the output is the generated summary. This step also utilizes the Hugging Face transformers library.

[0805] Step 4:

[0806] An artificial intelligence (AI) module installed on the server automatically generates application methods for business operations based on the generated summary. The input is the summary generated in step 3, and the output is a proposal for application methods. The AI ​​module generates proposals using predefined templates that correspond to the business context and business processes.

[0807] Step 5:

[0808] The server displays the generated application methods on the terminal. A user interface (UI) for this purpose is provided on the dashboard, making it accessible to the user. The input is the application method from step 4, and the output is the suggestion displayed on the user's terminal. The dashboard is implemented using web technologies such as HTML and JavaScript.

[0809] Step 6:

[0810] Users review application methods through a dashboard on their devices and apply them to their actual advertising strategies. Users review the suggestions and provide feedback. The input is the suggestions displayed by the server, and the output is the user's evaluation and feedback. User actions include entering opinions into a feedback form and submitting it.

[0811] Step 7:

[0812] The device collects user feedback and sends it to the server. The input is the user's feedback, and the output is the feedback data sent to the server. During this process, sentiment analysis is performed on the device, analyzing text input and voice data.

[0813] Step 8:

[0814] The server stores the collected feedback data in a database and uses it along with the sentiment analysis results in the next model retraining process. The input is the feedback data sent in step 7, and the output is the improved AI model. Specifically, the feedback data is analyzed and reused as training data for the AI ​​model.

[0815] These steps enable advertising professionals to quickly incorporate the latest marketing techniques and consumer behavior analysis to develop effective advertising strategies, and to continuously improve them through real-time feedback and sentiment analysis.

[0816] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0817] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0818] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0819] [Third Embodiment]

[0820] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0821] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0822] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0823] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0824] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0825] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0826] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0827] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0828] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0829] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0830] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0831] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0832] The system of the present invention is realized through the interaction of a server, terminals, and users. The embodiments for carrying out the present invention are described in detail below.

[0833] 1. Server Role

[0834] Data collection

[0835] The server accesses academic literature databases and collects the latest literature related to the specified topic. This includes scheduled searches and real-time searches based on user requests. The collected literature data is stored in a database on the server.

[0836] Information extraction and summary generation

[0837] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[0838] Generating business application proposals

[0839] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[0840] Providing a user interface (UI)

[0841] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. The dashboard displays the latest suggestions and a feedback form.

[0842] Gathering feedback and learning

[0843] The server collects user feedback and stores it in a database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0844] 2. The role of the terminal

[0845] Dashboard display

[0846] The terminal displays an enterprise dashboard for user access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface.

[0847] Submitting feedback

[0848] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the proposed solutions. This feedback is sent to the server in real time.

[0849] 3. User Roles

[0850] Information verification and evaluation

[0851] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[0852] Provide feedback

[0853] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[0854] Specific example

[0855] Example 1: Application in the development of medical devices

[0856] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates proposals on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[0857] Example 2: Application in improving marketing strategies

[0858] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. The terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[0859] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system can be continuously improved through continuous feedback.

[0860] The following describes the processing flow.

[0861] Step 1:

[0862] The server accesses the academic literature database and searches for the latest literature based on the specified topic. The query is executed according to business-related keywords and filtering conditions.

[0863] Step 2:

[0864] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[0865] Step 3:

[0866] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[0867] Step 4:

[0868] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[0869] Step 5:

[0870] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[0871] Step 6:

[0872] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[0873] Step 7:

[0874] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[0875] Step 8:

[0876] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[0877] Step 9:

[0878] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time.

[0879] Step 10:

[0880] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[0881] Step 11:

[0882] The server retrains the artificial intelligence model based on the feedback data. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[0883] Step 12:

[0884] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[0885] (Example 1)

[0886] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0887] Currently, for companies to apply academic literature to their operations, they need to manually collect, analyze, and devise application methods for vast amounts of information. This process consumes a great deal of time and effort, and the accuracy and usefulness of the analysis results and application methods are inconsistent because they depend on human resources. Furthermore, even when feedback is collected, there is a lack of mechanisms to effectively utilize it and reflect it in future proposals, making continuous improvement difficult. As a result, it is difficult for companies to quickly and efficiently incorporate the latest academic knowledge into their operations and innovate their business processes.

[0888] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0889] This invention includes a server that includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a user-accessible dashboard, means for collecting feedback from users and storing it in an evaluation database, and means for retraining the artificial intelligence model based on the collected feedback data to successively improve the accuracy and usefulness of future suggestions. This enables companies to efficiently carry out everything from collecting academic literature to generating application suggestions and even continuous improvement through feedback, allowing for rapid and highly accurate innovation of business processes.

[0890] A "server" is a computer system that provides specific services to other computers (clients) on a network.

[0891] A "scholarly literature database" is a database system that collects and makes searchable and accessible literature information such as academic papers and research results.

[0892] An "abstract" is a concise summary of the content of an academic paper or report, providing an overview of the research's objectives, methods, results, and conclusions.

[0893] The "Conclusion" section is the part of the document that summarizes the main findings and conclusions derived from the results of research or experiments.

[0894] "Experimental results" refer to data and observations obtained in research or experiments, and include the results of their analysis.

[0895] A "Natural Language Processing (NLP) module" is a software module for analyzing and understanding text data, and in particular, it processes human language using machine learning and generative AI models.

[0896] "Artificial intelligence tools" refer to systems or modules that analyze data using machine learning algorithms or generative AI models and make judgments and suggestions like humans.

[0897] A "dashboard" is an interface that allows users to visually view and manipulate information, and it is a screen that displays specific data or analysis results.

[0898] "Feedback" refers to evaluations and opinions provided by users, and is information collected to improve the system and inform future suggestions.

[0899] An "evaluation database" is a database system that stores collected feedback information and uses it for analysis and model retraining.

[0900] "Retraining" is the process of training an existing machine learning model again using new data and feedback information to improve the model's accuracy and usefulness.

[0901] The system of the present invention is realized through the mutual cooperation of a server, terminal, and user. The embodiments for carrying out the present invention will be described in detail below.

[0902] The server accesses the latest academic literature databases to search for and collect literature related to the specified topic. Specifically, it utilizes databases such as PubMed and IEEE Xplore. The collected literature data is stored in the server's database in JSON format or similar.

[0903] The server is equipped with a natural language processing (NLP) module, which utilizes generative AI models such as BERT and GPT-3. This NLP module analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. This analysis process extracts key information and generates a summary. The summary generation algorithm picks out important keywords and sentences from the extracted text and creates a concise summary.

[0904] Next, the server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary. This AI module uses a business proposal template to suggest how the new algorithm or method can contribute to business processes. The generated application methods and summary are created in HTML format and sent to the terminal via WebSocket or REST API.

[0905] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface. The dashboard also displays a feedback form, allowing users to input and submit their opinions on the effectiveness and areas for improvement of the suggested content.

[0906] User feedback is sent to the server in real time and stored in an evaluation database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[0907] As a concrete example, the server collects the latest literature related to the topic of "medical devices" from PubMed and analyzes it using an NLP module. Then, based on the summary generated by the AI ​​module, it proposes applications for medical device development. The terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[0908] A similar process can be applied to improving marketing strategies. A server collects the latest marketing-related literature and generates summaries. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. A terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[0909] An example of a prompt might be: "Collect the latest marketing-related literature, generate summaries, and create marketing strategy proposals based on new consumer behavior analysis methods."

[0910] As described above, the system of the present invention enables the rapid and accurate application of academic knowledge to business operations through the collaboration of a server, terminal, and user, via data collection, summary generation, business application proposals, feedback collection, and retraining.

[0911] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0912] Step 1:

[0913] The server accesses academic literature databases to search for and collect literature related to the specified topic.

[0914] Specific operation: The server sends queries to databases such as PubMed and IEEE Xplore based on a regular schedule or user requests. The retrieved bibliographic data is stored in JSON format. The input for this step is the search query, and the output is the collected bibliographic data.

[0915] Step 2:

[0916] A natural language processing (NLP) module on the server analyzes the collected literature data, extracts abstracts, conclusions, and experimental results, and generates a summary.

[0917] Specific operation: The NLP module analyzes sections of literature using generative AI models such as BERT and GPT-3, and extracts important information.

[0918] The input for this step is collected literature data, and the output is the analyzed information and summary.

[0919] Step 3:

[0920] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary.

[0921] Specific operation: The AI ​​module utilizes business templates to suggest how new algorithms and methods can contribute to business processes.

[0922] The input for this step is the generated summary, and the output is a proposed application method.

[0923] Step 4:

[0924] The server displays the generated application methods on the terminal and provides a user-accessible dashboard.

[0925] Specific operation: Generates proposal content and summary in HTML format and sends it to the terminal via WebSocket or REST API.

[0926] The input for this step is a proposed application method, and the output is a dashboard displayed on the terminal.

[0927] Step 5:

[0928] The dashboard on the device displays information to the user and collects feedback.

[0929] Specific operation: The device uses a web browser to render HTML data provided by the server, retrieves user-entered feedback information using JavaScript, and sends it to the server in real time.

[0930] The input for this step is the information from the dashboard, and the output is the collected feedback.

[0931] Step 6:

[0932] The server collects feedback provided by users and stores it in an evaluation database.

[0933] Specific operation: Feedback data is stored in an SQL database and used for subsequent natural language processing and AI model training.

[0934] The input for this step is the collected feedback, and the output is the feedback data stored in the evaluation database.

[0935] Step 7:

[0936] The server retrains its artificial intelligence model based on the collected feedback data, continuously improving the accuracy and usefulness of subsequent suggestions.

[0937] Specific action: Adjust the parameters of the generated AI model using the new feedback data and retrain it.

[0938] The input for this step is feedback data stored in an evaluation database, and the output is an improved generative AI model.

[0939] (Application Example 1)

[0940] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0941] Conventional systems for collecting and analyzing academic literature have made it difficult to quickly and accurately analyze the latest information and propose concrete ways to apply it to business operations. In particular, there has been a lack of systems that effectively utilize information visualization and user feedback, resulting in problems in streamlining business processes and improving the accuracy of proposals.

[0942] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0943] In this invention, the server includes means for accessing the latest academic literature databases, searching for and collecting literature related to a specified topic; means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries; artificial intelligence means for automatically generating application methods for business based on the generated summaries; means for displaying the generated application methods on a mobile communication terminal and providing a user-accessible visualized operation screen; means for collecting feedback from users and continuously improving the artificial intelligence model; and means for efficiently organizing the collected and generated information and generating proposals adaptable to various business processes. This makes it possible to quickly analyze the latest information, present it to users in a visually easy-to-understand format, and continuously improve the proposals through user feedback.

[0944] A "scholarly literature database" is an information aggregation system that collects and stores academic information such as research papers, academic books, and technical reports in a searchable format.

[0945] "Specified topics" refer to keywords or theme settings used to identify research areas or themes that the user is interested in.

[0946] "Collection methods" refer to technologies for accessing academic literature databases, automatically searching for literature related to a specified topic, and obtaining data.

[0947] An "abstract" is a concise summary of the research objectives, methods, and main findings in a document.

[0948] The "conclusion" is the section that outlines the overall judgment and future research direction derived from the research results.

[0949] "Experimental results" refers to the section that shows the specific results and data from experiments and surveys conducted in a study.

[0950] A "summary generation method" is a technique for extracting important information from collected literature and organizing it into a concise and easy-to-understand format.

[0951] "Artificial intelligence methods" refer to artificial intelligence technologies that analyze large amounts of data, recognize patterns, and generate new information and application methods.

[0952] A "mobile communication terminal" refers to a mobile device, such as a smartphone or tablet, that can connect to the internet and receive and display information.

[0953] A "visualized user interface" is a screen designed to graphically display collected information and generated suggestions, allowing users to operate it intuitively.

[0954] It refers to "feedback."

[0955] "Retraining" is the process by which an artificial intelligence model improves its prediction accuracy and suggestions based on newly collected data and user feedback.

[0956] A "business process" refers to a series of tasks or procedures performed in business or research to achieve a specific objective.

[0957] "Means for generating suggestions" refers to technologies that present users with useful action plans and areas for improvement based on collected data and generated summaries.

[0958] The system for implementing this invention collects the latest literature from a scholarly literature database, analyzes it, generates suggestions for its application to business operations, and continuously improves the system through feedback. This system is realized through the interaction of a server, terminals, and users.

[0959] Server Role

[0960] The server plays the following main roles:

[0961] 1. Data collection:

[0962] The server accesses academic literature databases on the internet to search for and collect the latest literature related to a specified topic. Specifically, it uses APIs to retrieve bibliographic information. Here, the requests library is used to access the APIs of academic literature databases.

[0963] 2. Information extraction and summarization using natural language processing:

[0964] Natural language processing (NLP) techniques are used to automatically extract abstracts, conclusions, and experimental results from collected literature and generate summaries. Here, the OpenAI API is used to generate the summaries. This process involves analyzing the main parts of the literature and concisely summarizing the key information.

[0965] 3. Generating business application proposals:

[0966] Artificial intelligence (AI) technology is used to generate application methods for business operations based on summarized information. The generated summaries are used as prompts, and business suggestions are generated via the OpenAI API. For example, the following prompts are used:

[0967] Based on the following summary, please propose an application:

[0968] (Summary text)

[0969] 4. Providing a user interface:

[0970] The generated suggestions are displayed on the device, providing a visualized, user-accessible interface. This uses a dashboard built with HTML and JavaScript. The dashboard displays the suggestions and a feedback form.

[0971] 5. Gathering feedback and relearning:

[0972] We collect user feedback and use it to retrain the AI ​​model. This retraining improves the accuracy of future suggestions. The feedback is sent to and collected on the server in real time.

[0973] Terminal role

[0974] The terminal primarily serves the following roles:

[0975] 1. Display the dashboard:

[0976] The terminal displays a visualized interface (dashboard) for the user to access. This includes the latest business application proposals and summarized academic research information sent from the server.

[0977] 2. Submitting feedback:

[0978] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the suggestions. This feedback is sent to the server and used for retraining.

[0979] User roles

[0980] The user will have the following roles:

[0981] 1. Information verification and evaluation:

[0982] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[0983] 2. Providing feedback:

[0984] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[0985] Specific application examples

[0986] For example, if a user specifies "artificial intelligence" as their topic, the server will collect the latest relevant literature and generate summaries from it. Based on these summaries, it will then suggest how they can be applied to content delivery services. Specifically, a possible suggestion might be, "Using this new AI algorithm will improve the accuracy of the recommendation system." Users can view these suggestions on a dashboard and contribute to improving the system's accuracy by providing feedback.

[0987] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0988] Step 1: Data Collection

[0989] The server receives a topic specified by the user. The server accesses academic literature databases on the internet and searches for literature related to the specified topic. Specifically, the server uses the requests library to send requests to the literature database API and retrieve relevant literature information. The input is the topic specified by the user, and the output is a list of retrieved literature.

[0990] Step 2: Information Extraction and Summary Generation

[0991] Based on the collected list of literature, the server extracts the abstract, conclusions, and experimental results for each document. Next, the server's natural language processing (NLP) module analyzes this information and generates a summary. This NLP processing utilizes the OpenAI API. The input is the text data of the literature, and the output is the extracted summary.

[0992] Step 3: Generating Business Application Proposals

[0993] Based on the generated summary, the server's artificial intelligence (AI) module proposes ways to apply it to the business. At this stage, the summary is used as a prompt, and specific business proposals are generated using the OpenAI API. The input is the summarized text, and the output is a proposal for application methods. Specifically, the server generates prompts such as the following:

[0994] Based on the following summary, please propose an application:

[0995] (Summary text)

[0996] Step 4: Provide the user interface

[0997] The generated business proposals are sent to the terminal, and a visualized operation screen (dashboard) accessible to the user is provided. The terminal displays these proposals using HTML and JavaScript. The input is the business proposal data, and the output is the visualized operation screen. Users can check the information through this dashboard.

[0998] Step 5: Gathering Feedback

[0999] After the user reviews and evaluates the proposal, they submit their feedback to the server via a feedback form. The server collects this feedback and stores it in a database. The input is the user's feedback information, and the output is the result of saving the feedback to the database.

[1000] Step 6: Relearning

[1001] Based on the collected feedback, the server's artificial intelligence model undergoes retraining. This retraining improves the accuracy of subsequent suggestions. In this process, the server analyzes the feedback data and generates new model parameters. The input is the feedback data, and the output is the updated AI model. As a result of retraining, the suggestions improve, and the overall accuracy of the system increases.

[1002] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1003] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and emotion engine. The embodiments for carrying out the present invention are described in detail below.

[1004] 1. Server Role

[1005] Data collection

[1006] The server accesses a scholarly literature database and collects the latest literature related to the specified topic. Queries are performed according to business-related keywords and filtering conditions. The collected literature data is stored in a database on the server.

[1007] Information extraction and summary generation

[1008] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[1009] Generating business application proposals

[1010] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[1011] Analysis of the Emotion Engine

[1012] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[1013] Providing a user interface (UI)

[1014] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[1015] Gathering feedback and learning

[1016] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This continuously improves the accuracy and usefulness of subsequent suggestions.

[1017] 2. The role of the terminal

[1018] Dashboard display

[1019] The terminal displays an enterprise dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[1020] Submitting feedback

[1021] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[1022] 3. User Roles

[1023] Information verification and evaluation

[1024] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they decide whether to apply it to their actual marketing strategy.

[1025] Provide feedback

[1026] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. In addition, an emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[1027] Specific example

[1028] Example 1: Application in the development of medical devices

[1029] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates suggestions on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these suggestions to employees in the medical device development department, who review the suggestions and provide feedback. An emotion engine analyzes the emotions expressed by the employees during the feedback process and sends this information back to the server.

[1030] Example 2: Application in improving marketing strategies

[1031] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies. A terminal presents these proposals to sales representatives, who then try out the suggestions and provide feedback. An emotion engine analyzes the user's emotions during feedback and sends the results to the server.

[1032] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system is continuously improved based on feedback that takes user emotions into consideration.

[1033] The following describes the processing flow.

[1034] Step 1:

[1035] The server accesses the academic literature database and searches for the latest literature related to the specified topic. The query is executed according to business-related keywords and filtering conditions.

[1036] Step 2:

[1037] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[1038] Step 3:

[1039] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[1040] Step 4:

[1041] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[1042] Step 5:

[1043] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[1044] Step 6:

[1045] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[1046] Step 7:

[1047] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[1048] Step 8:

[1049] The emotion engine analyzes the user's emotional state when providing feedback. The device acquires the user's text input and voice data and sends the emotion data to the server.

[1050] Step 9:

[1051] The server's emotion engine analyzes the transmitted emotion data to detect the user's emotional state. The analysis results are stored along with the feedback data.

[1052] Step 10:

[1053] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[1054] Step 11:

[1055] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time, and sentiment analysis data is also attached.

[1056] Step 12:

[1057] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[1058] Step 13:

[1059] The server retrains the artificial intelligence model based on feedback data and sentiment analysis results. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[1060] Step 14:

[1061] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[1062] (Example 2)

[1063] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1064] Conventional technologies made the process of efficiently collecting the latest academic literature, extracting its summaries and conclusions, and applying them to actual work time-consuming and limited in accuracy. Furthermore, there was insufficient method for quickly incorporating user feedback to improve the system. Therefore, challenges existed in improving work efficiency and the quality of proposed solutions.

[1065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1066] In this invention, the server includes means for accessing the latest information resource database and searching for and collecting information related to a specified field; means for automatically extracting summaries, conclusions, and results from the collected information and generating a summary; intelligent means for automatically generating application methods for business based on the generated summary; means for analyzing the user's emotional state using a cognitive analysis engine; means for displaying the generated application methods on an information terminal and providing a user-accessible interface; and means for collecting feedback from the user and continuously improving the intelligent model. This enables the rapid application of the latest academic knowledge to business operations, the realization of efficient business processes, and the continuous improvement of the system.

[1067] An "information resource database" is a database that collects, stores, and provides information related to various fields in a searchable format.

[1068] An "abstract" is a concise summary of the content of a document or report.

[1069] The "conclusion" is the final judgment or assertion derived from the results of literature and research.

[1070] "Results" refer to data and outcomes obtained based on literature and research.

[1071] A "summary" is a short piece of text that concisely summarizes the content of a document or report, extracting the most important points.

[1072] An "intelligent tool" is a system that uses artificial intelligence technology to automatically perform specific tasks.

[1073] A "cognitive analysis engine" is a system that analyzes a user's text input and voice data to detect their emotional state.

[1074] An "information terminal" is a device that allows users to access information through an interface. Examples include personal computers and smartphones.

[1075] An "interface" refers to the user interface or input tools that allow a user to interact with a system.

[1076] "Feedback" refers to evaluations and opinions provided by users, and is used to improve the system and enhance the accuracy of suggestions.

[1077] An "intelligent model" refers to the structure or pattern of artificial intelligence generated by a learning algorithm and used to perform a specific task.

[1078] The system of the present invention automates the process of collecting the latest information, generating application suggestions for business operations, and continuously improving it based on user feedback. The embodiments for carrying out the present invention are described in detail below.

[1079] Server Role

[1080] Data collection

[1081] First, the server accesses an information resource database. This access uses an API (e.g., PubMed API, IEEE Xplore API). It searches for and effectively collects information related to a specified field. For example, it executes queries using keywords such as "artificial intelligence" or "medical device development" and stores the retrieved data in a database (e.g., MySQL, MongoDB).

[1082] Information extraction and summary generation

[1083] The server analyzes the collected information using an NLP module (e.g., spaCy, BERT). This analysis extracts key information such as the summary, conclusions, and results. Next, a summarization algorithm (e.g., TF-IDF, topic modeling) is used to convert the extracted information into a concise and easy-to-understand summary.

[1084] Generating business application proposals

[1085] Furthermore, the server's intelligent model (e.g., GPT-3, Transformers) generates business application suggestions based on the generated summary. This process uses specific templates (e.g., SWOT analysis framework) to suggest how the new insights can help improve business processes.

[1086] Emotion analysis

[1087] The server is equipped with a cognitive analysis engine (e.g., IBM Watson, sentimentr) that analyzes user feedback to understand their emotional state. This allows for the acquisition of information that can be used to assess the usefulness of suggestions and improve future offerings.

[1088] Terminal role

[1089] Dashboard display

[1090] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. This interface is built using, for example, React.js. Through this dashboard, users can review the information and evaluate the suggestions. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[1091] Submitting feedback

[1092] A form is installed on the device to easily collect user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The server analyzes the submitted feedback data and stores it in a database along with the user's emotional state.

[1093] User roles

[1094] Information verification and evaluation

[1095] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they will determine whether it is applicable to their own marketing strategy.

[1096] Provide feedback

[1097] Users try out the suggested features and provide feedback on the results. Feedback is given through an evaluation form, and the emotion engine analyzes the user's input data, saving their emotional state as part of the feedback.

[1098] Specific example

[1099] Example 1: Application in the development of medical devices

[1100] 1. The server collects the latest medical literature and generates summaries using natural language processing.

[1101] 2. The intelligent model generates proposals on how the research findings in this document can be applied to the company's medical devices.

[1102] 3. The terminal presents this proposal to an employee in the medical device development department, who reviews the proposal and provides feedback.

[1103] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback, and this information is also sent to the server.

[1104] Example 2: Application in improving marketing strategies

[1105] 1. The server collects the latest marketing-related literature and generates summaries using natural language processing.

[1106] 2. The intelligent model extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies.

[1107] 3. The terminal presents this proposal to the sales representative, who then tries out the proposal and provides feedback on the results.

[1108] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback and sends the results to the server.

[1109] Example of a prompt

[1110] "Summarize the latest academic literature on medical devices and propose how to apply it to our company's product development."

[1111] "Collect the latest literature on new marketing techniques, generate summaries, and propose how these techniques can be applied to consumer behavior analysis."

[1112] As described above, through the system of the present invention, companies can apply academic knowledge to their operations quickly and efficiently, thereby achieving innovation in business processes and continuous improvement of systems.

[1113] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1114] Step 1:

[1115] Data collection

[1116] The server accesses an information resource database (e.g., PubMed, IEEE Xplore). The input is a query related to a specified topic (e.g., "artificial intelligence," "medical device development"). Based on this query, the server searches the database for relevant information. The search results (bibliographic data) are output. The server saves this bibliographic data to a database (e.g., MySQL, MongoDB).

[1117] Step 2:

[1118] Information Extraction

[1119] The server analyzes collected literature data using an NLP module (e.g., spaCy, BERT). The input is literature data stored in a database. The NLP module automatically extracts the abstract, conclusion, and results of the literature. This extracted information is then generated as output. This information is passed on to the next step in summary generation.

[1120] Step 3:

[1121] Summary generation

[1122] The server uses a summarization algorithm (e.g., TF-IDF, topic modeling) to generate a concise and easy-to-understand summary from the extracted information. The input is the extracted information. The algorithm selects key points and formats them into a summary. The generated summary is output and used to generate business application proposals.

[1123] Step 4:

[1124] Generating business application proposals

[1125] The server's intelligent model (e.g., GPT-3, Transformers) automatically generates business application proposals based on the generated summary. The input is the generated summary. The intelligent model constructs the proposals using a specific template (e.g., SWOT analysis framework). The proposed content is output and formatted for display.

[1126] Step 5:

[1127] Emotion analysis

[1128] A cognitive analysis engine (e.g., IBM Watson, sentimentr) installed on the server analyzes user feedback. The input is feedback text or audio data sent by the user. The analysis engine detects the emotional state (e.g., positive, negative) and generates the result as output. This analysis result is also stored in a database.

[1129] Step 6:

[1130] Dashboard display

[1131] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. Input consists of suggestions and summary information sent from the server. The terminal builds the dashboard using React.js and displays it to the user. The user can access the information through this dashboard. The displayed content may also be dynamically adjusted based on the user's emotional state.

[1132] Step 7:

[1133] Submitting feedback

[1134] Users evaluate the proposals through a dashboard and submit the feedback form with the necessary information. This feedback consists of user opinions regarding the evaluation and potential improvements to the proposals. The feedback data is sent from the device to the server, where it is analyzed by a cognitive analysis engine, including the user's emotional state.

[1135] Step 8:

[1136] Storing and learning from feedback

[1137] The server stores user feedback data and sentiment analysis results in a database. The input consists of user-provided feedback and analysis results of emotional states. This data is used in the next model retraining process. The output is an improvement to the AI ​​model and increased suggestion accuracy.

[1138] The above outlines the specific processing steps of this system. Through the specific actions of the server, terminal, and user in each step, it becomes possible to quickly collect the latest academic knowledge and apply it to work. Furthermore, the system is continuously improved based on user feedback.

[1139] (Application Example 2)

[1140] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1141] Traditional advertising strategies faced the challenge of quickly gathering information on the latest marketing techniques and consumer behavior analysis, and then formulating effective strategies based on that information. Furthermore, there was a lack of systems capable of evaluating the effectiveness of advertising strategies and providing real-time feedback and sentiment analysis for continuous improvement.

[1142] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a dashboard accessible to the user, means for collecting feedback from the user and continuously improving the artificial intelligence model, and means for providing advertising-related information via a display device that allows the user to visually confirm it. This enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[1143] A "scholarly literature database" is a database that contains academic research results and papers.

[1144] An "abstract" is a short, concise summary of the content of a document, highlighting its main points and conclusions.

[1145] A "conclusion" refers to the final judgment or opinion that the author has arrived at as a result of their research in a given document.

[1146] "Experimental results" refer to data and observations obtained during the course of research or experiments.

[1147] A "summary" is a concise document that summarizes the main points of a text, and is used to aid in understanding the overall content.

[1148] "Artificial intelligence" is a general term for software and systems that can perform information processing and decision-making by mimicking human intelligence.

[1149] A "terminal" is an electronic device used by a user to access and operate information.

[1150] A "dashboard" is a visual interface that allows users to see multiple pieces of information at a glance.

[1151] "Feedback" refers to the opinions and evaluations that users provide to a system or service.

[1152] A "display device" is a device used to visually display information, and includes screens and displays.

[1153] "Advertising-related information" refers to useful data, knowledge, and analytical methods within the advertising industry.

[1154] "Visual inspection" refers to the act of directly seeing something with the human eye.

[1155] "Collection" refers to a series of activities that involve gathering specific information or data.

[1156] "Extraction" refers to the operation of taking out specific elements or information from a whole.

[1157] "Generation" refers to the process of creating new information or data.

[1158] "Provision" refers to the act of a system or service delivering information to a user.

[1159] "Most suitable" means being judged to be the best for a particular purpose.

[1160] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and display device as a means for displaying advertising-related information. This system enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[1161] 1. Server Role

[1162] Data collection

[1163] The server accesses academic literature databases and collects the latest literature related to the specified topic. The collection process uses work-related keywords and filtering criteria. The literature data is stored in a database on the server.

[1164] Information extraction and summary generation

[1165] Using a natural language processing (NLP) module installed on the server, abstracts, conclusions, and experimental results are automatically extracted from collected literature to generate summaries. Generative AI models such as Hugging Face's transformers library are used for summary generation.

[1166] Generating business application proposals

[1167] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates that present application methods tailored to predefined business contexts and business processes.

[1168] Analysis of the Emotion Engine

[1169] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[1170] Providing a user interface (UI)

[1171] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[1172] Gathering feedback and learning

[1173] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This improves the accuracy and usefulness of future suggestions.

[1174] 2. The role of the terminal

[1175] Dashboard display

[1176] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[1177] Submitting feedback

[1178] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[1179] 3. User Roles

[1180] Information verification and evaluation

[1181] Users who are advertising industry professionals review the suggestions provided through the dashboard on their devices and evaluate those that are useful for their work. For example, if a new marketing method is suggested, they decide whether to apply it to their actual advertising strategy.

[1182] Provide feedback

[1183] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form and sent to the server. An emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[1184] Specific example

[1185] Sample generation AI prompt text

[1186] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[1187] Abstract: {Abstract of the literature}

[1188] Conclusion: {Conclusion of the literature}

[1189] for example:

[1190] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[1191] Abstract: This study focuses on the latest trends in consumer behavior analysis...

[1192] Conclusion: The findings suggest that integrating AI models with traditional marketing strategies...

[1193] This system enables advertising professionals to quickly develop effective advertising strategies based on the latest marketing techniques and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[1194] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1195] Step 1:

[1196] The server accesses an academic literature database and collects the latest literature related to the specified topic. The data used as input consists of business-related keywords and filtering conditions. This ensures that the latest marketing-related literature is stored in the database on the server.

[1197] Step 2:

[1198] A natural language processing (NLP) module installed on the server automatically extracts abstracts, conclusions, and experimental results from collected literature. The input is the literature data collected in step 1, and the output is the extracted abstracts, conclusions, and experimental results. Specifically, the analysis is performed using the Hugging Face transformers library.

[1199] Step 3:

[1200] The server processes the extracted information for summary generation, concisely summarizing the key points. The input is the information extracted in step 2, and the output is the generated summary. This step also utilizes the Hugging Face transformers library.

[1201] Step 4:

[1202] An artificial intelligence (AI) module installed on the server automatically generates application methods for business operations based on the generated summary. The input is the summary generated in step 3, and the output is a proposal for application methods. The AI ​​module generates proposals using predefined templates that correspond to the business context and business processes.

[1203] Step 5:

[1204] The server displays the generated application methods on the terminal. A user interface (UI) for this purpose is provided on the dashboard, making it accessible to the user. The input is the application method from step 4, and the output is the suggestion displayed on the user's terminal. The dashboard is implemented using web technologies such as HTML and JavaScript.

[1205] Step 6:

[1206] Users review application methods through a dashboard on their devices and apply them to their actual advertising strategies. Users review the suggestions and provide feedback. The input is the suggestions displayed by the server, and the output is the user's evaluation and feedback. User actions include entering opinions into a feedback form and submitting it.

[1207] Step 7:

[1208] The device collects user feedback and sends it to the server. The input is the user's feedback, and the output is the feedback data sent to the server. During this process, sentiment analysis is performed on the device, analyzing text input and voice data.

[1209] Step 8:

[1210] The server stores the collected feedback data in a database and uses it along with the sentiment analysis results in the next model retraining process. The input is the feedback data sent in step 7, and the output is the improved AI model. Specifically, the feedback data is analyzed and reused as training data for the AI ​​model.

[1211] These steps enable advertising professionals to quickly incorporate the latest marketing techniques and consumer behavior analysis to develop effective advertising strategies, and to continuously improve them through real-time feedback and sentiment analysis.

[1212] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1213] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1214] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1215] [Fourth Embodiment]

[1216] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1217] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1218] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1219] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1220] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1221] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1222] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1223] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1224] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1225] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1226] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1227] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1228] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1229] The system of the present invention is realized through the interaction of a server, terminals, and users. The embodiments for carrying out the present invention are described in detail below.

[1230] 1. Server Role

[1231] Data collection

[1232] The server accesses academic literature databases and collects the latest literature related to the specified topic. This includes scheduled searches and real-time searches based on user requests. The collected literature data is stored in a database on the server.

[1233] Information extraction and summary generation

[1234] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[1235] Generating business application proposals

[1236] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[1237] Providing a user interface (UI)

[1238] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. The dashboard displays the latest suggestions and a feedback form.

[1239] Gathering feedback and learning

[1240] The server collects user feedback and stores it in a database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[1241] 2. The role of the terminal

[1242] Dashboard display

[1243] The terminal displays an enterprise dashboard for user access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface.

[1244] Submitting feedback

[1245] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the proposed solutions. This feedback is sent to the server in real time.

[1246] 3. User Roles

[1247] Information verification and evaluation

[1248] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[1249] Provide feedback

[1250] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[1251] Specific example

[1252] Example 1: Application in the development of medical devices

[1253] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates proposals on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[1254] Example 2: Application in improving marketing strategies

[1255] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. The terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[1256] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system can be continuously improved through continuous feedback.

[1257] The following describes the processing flow.

[1258] Step 1:

[1259] The server accesses the academic literature database and searches for the latest literature based on the specified topic. The query is executed according to business-related keywords and filtering conditions.

[1260] Step 2:

[1261] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[1262] Step 3:

[1263] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[1264] Step 4:

[1265] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[1266] Step 5:

[1267] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[1268] Step 6:

[1269] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[1270] Step 7:

[1271] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[1272] Step 8:

[1273] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[1274] Step 9:

[1275] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time.

[1276] Step 10:

[1277] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[1278] Step 11:

[1279] The server retrains the artificial intelligence model based on the feedback data. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[1280] Step 12:

[1281] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[1282] (Example 1)

[1283] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1284] Currently, for companies to apply academic literature to their operations, they need to manually collect, analyze, and devise application methods for vast amounts of information. This process consumes a great deal of time and effort, and the accuracy and usefulness of the analysis results and application methods are inconsistent because they depend on human resources. Furthermore, even when feedback is collected, there is a lack of mechanisms to effectively utilize it and reflect it in future proposals, making continuous improvement difficult. As a result, it is difficult for companies to quickly and efficiently incorporate the latest academic knowledge into their operations and innovate their business processes.

[1285] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1286] This invention includes a server that includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a user-accessible dashboard, means for collecting feedback from users and storing it in an evaluation database, and means for retraining the artificial intelligence model based on the collected feedback data to successively improve the accuracy and usefulness of future suggestions. This enables companies to efficiently carry out everything from collecting academic literature to generating application suggestions and even continuous improvement through feedback, allowing for rapid and highly accurate innovation of business processes.

[1287] A "server" is a computer system that provides specific services to other computers (clients) on a network.

[1288] A "scholarly literature database" is a database system that collects and makes searchable and accessible literature information such as academic papers and research results.

[1289] An "abstract" is a concise summary of the content of an academic paper or report, providing an overview of the research's objectives, methods, results, and conclusions.

[1290] The "Conclusion" section is the part of the document that summarizes the main findings and conclusions derived from the results of research or experiments.

[1291] "Experimental results" refer to data and observations obtained in research or experiments, and include the results of their analysis.

[1292] A "Natural Language Processing (NLP) module" is a software module for analyzing and understanding text data, and in particular, it processes human language using machine learning and generative AI models.

[1293] "Artificial intelligence tools" refer to systems or modules that analyze data using machine learning algorithms or generative AI models and make judgments and suggestions like humans.

[1294] A "dashboard" is an interface that allows users to visually view and manipulate information, and it is a screen that displays specific data or analysis results.

[1295] "Feedback" refers to evaluations and opinions provided by users, and is information collected to improve the system and inform future suggestions.

[1296] An "evaluation database" is a database system that stores collected feedback information and uses it for analysis and model retraining.

[1297] "Retraining" is the process of training an existing machine learning model again using new data and feedback information to improve the model's accuracy and usefulness.

[1298] The system of the present invention is realized through the mutual cooperation of a server, terminal, and user. The embodiments for carrying out the present invention will be described in detail below.

[1299] The server accesses the latest academic literature databases to search for and collect literature related to the specified topic. Specifically, it utilizes databases such as PubMed and IEEE Xplore. The collected literature data is stored in the server's database in JSON format or similar.

[1300] The server is equipped with a natural language processing (NLP) module, which utilizes generative AI models such as BERT and GPT-3. This NLP module analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. This analysis process extracts key information and generates a summary. The summary generation algorithm picks out important keywords and sentences from the extracted text and creates a concise summary.

[1301] Next, the server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary. This AI module uses a business proposal template to suggest how the new algorithm or method can contribute to business processes. The generated application methods and summary are created in HTML format and sent to the terminal via WebSocket or REST API.

[1302] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summarized academic research information sent from the server. Users can view and evaluate the information through an intuitive interface. The dashboard also displays a feedback form, allowing users to input and submit their opinions on the effectiveness and areas for improvement of the suggested content.

[1303] User feedback is sent to the server in real time and stored in an evaluation database. Based on this feedback data, the server retrains its artificial intelligence model. This continuously improves the accuracy and usefulness of subsequent suggestions.

[1304] As a concrete example, the server collects the latest literature related to the topic of "medical devices" from PubMed and analyzes it using an NLP module. Then, based on the summary generated by the AI ​​module, it proposes applications for medical device development. The terminal presents these proposals to employees in the medical device development department, who review the proposals and provide feedback.

[1305] A similar process can be applied to improving marketing strategies. A server collects the latest marketing-related literature and generates summaries. An AI module extracts new consumer behavior analysis methods from the literature and suggests how these methods can be applied to marketing strategies. A terminal presents these suggestions to sales representatives, who then try out the suggestions and provide feedback on the results.

[1306] An example of a prompt might be: "Collect the latest marketing-related literature, generate summaries, and create marketing strategy proposals based on new consumer behavior analysis methods."

[1307] As described above, the system of the present invention enables the rapid and accurate application of academic knowledge to business operations through the collaboration of a server, terminal, and user, via data collection, summary generation, business application proposals, feedback collection, and retraining.

[1308] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1309] Step 1:

[1310] The server accesses academic literature databases to search for and collect literature related to the specified topic.

[1311] Specific operation: The server sends queries to databases such as PubMed and IEEE Xplore based on a regular schedule or user requests. The retrieved bibliographic data is stored in JSON format. The input for this step is the search query, and the output is the collected bibliographic data.

[1312] Step 2:

[1313] A natural language processing (NLP) module on the server analyzes the collected literature data, extracts abstracts, conclusions, and experimental results, and generates a summary.

[1314] Specific operation: The NLP module analyzes sections of literature using generative AI models such as BERT and GPT-3, and extracts important information.

[1315] The input for this step is collected literature data, and the output is the analyzed information and summary.

[1316] Step 3:

[1317] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summary.

[1318] Specific operation: The AI ​​module utilizes business templates to suggest how new algorithms and methods can contribute to business processes.

[1319] The input for this step is the generated summary, and the output is a proposed application method.

[1320] Step 4:

[1321] The server displays the generated application methods on the terminal and provides a user-accessible dashboard.

[1322] Specific operation: Generates proposal content and summary in HTML format and sends it to the terminal via WebSocket or REST API.

[1323] The input for this step is a proposed application method, and the output is a dashboard displayed on the terminal.

[1324] Step 5:

[1325] The dashboard on the device displays information to the user and collects feedback.

[1326] Specific operation: The device uses a web browser to render HTML data provided by the server, retrieves user-entered feedback information using JavaScript, and sends it to the server in real time.

[1327] The input for this step is the information from the dashboard, and the output is the collected feedback.

[1328] Step 6:

[1329] The server collects feedback provided by users and stores it in an evaluation database.

[1330] Specific operation: Feedback data is stored in an SQL database and used for subsequent natural language processing and AI model training.

[1331] The input for this step is the collected feedback, and the output is the feedback data stored in the evaluation database.

[1332] Step 7:

[1333] The server retrains its artificial intelligence model based on the collected feedback data, continuously improving the accuracy and usefulness of subsequent suggestions.

[1334] Specific action: Adjust the parameters of the generated AI model using the new feedback data and retrain it.

[1335] The input for this step is feedback data stored in an evaluation database, and the output is an improved generative AI model.

[1336] (Application Example 1)

[1337] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1338] Conventional systems for collecting and analyzing academic literature have made it difficult to quickly and accurately analyze the latest information and propose concrete ways to apply it to business operations. In particular, there has been a lack of systems that effectively utilize information visualization and user feedback, resulting in problems in streamlining business processes and improving the accuracy of proposals.

[1339] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1340] In this invention, the server includes means for accessing the latest academic literature databases, searching for and collecting literature related to a specified topic; means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries; artificial intelligence means for automatically generating application methods for business based on the generated summaries; means for displaying the generated application methods on a mobile communication terminal and providing a user-accessible visualized operation screen; means for collecting feedback from users and continuously improving the artificial intelligence model; and means for efficiently organizing the collected and generated information and generating proposals adaptable to various business processes. This makes it possible to quickly analyze the latest information, present it to users in a visually easy-to-understand format, and continuously improve the proposals through user feedback.

[1341] A "scholarly literature database" is an information aggregation system that collects and stores academic information such as research papers, academic books, and technical reports in a searchable format.

[1342] "Specified topics" refer to keywords or theme settings used to identify research areas or themes that the user is interested in.

[1343] "Collection methods" refer to technologies for accessing academic literature databases, automatically searching for literature related to a specified topic, and obtaining data.

[1344] An "abstract" is a concise summary of the research objectives, methods, and main findings in a document.

[1345] The "conclusion" is the section that outlines the overall judgment and future research direction derived from the research results.

[1346] "Experimental results" refers to the section that shows the specific results and data from experiments and surveys conducted in a study.

[1347] A "summary generation method" is a technique for extracting important information from collected literature and organizing it into a concise and easy-to-understand format.

[1348] "Artificial intelligence methods" refer to artificial intelligence technologies that analyze large amounts of data, recognize patterns, and generate new information and application methods.

[1349] A "mobile communication terminal" refers to a mobile device, such as a smartphone or tablet, that can connect to the internet and receive and display information.

[1350] A "visualized user interface" is a screen designed to graphically display collected information and generated suggestions, allowing users to operate it intuitively.

[1351] It refers to "feedback."

[1352] "Retraining" is the process by which an artificial intelligence model improves its prediction accuracy and suggestions based on newly collected data and user feedback.

[1353] A "business process" refers to a series of tasks or procedures performed in business or research to achieve a specific objective.

[1354] "Means for generating suggestions" refers to technologies that present users with useful action plans and areas for improvement based on collected data and generated summaries.

[1355] The system for implementing this invention collects the latest literature from a scholarly literature database, analyzes it, generates suggestions for its application to business operations, and continuously improves the system through feedback. This system is realized through the interaction of a server, terminals, and users.

[1356] Server Role

[1357] The server plays the following main roles:

[1358] 1. Data collection:

[1359] The server accesses academic literature databases on the internet to search for and collect the latest literature related to a specified topic. Specifically, it uses APIs to retrieve bibliographic information. Here, the requests library is used to access the APIs of academic literature databases.

[1360] 2. Information extraction and summarization using natural language processing:

[1361] Natural language processing (NLP) techniques are used to automatically extract abstracts, conclusions, and experimental results from collected literature and generate summaries. Here, the OpenAI API is used to generate the summaries. This process involves analyzing the main parts of the literature and concisely summarizing the key information.

[1362] 3. Generating business application proposals:

[1363] Artificial intelligence (AI) technology is used to generate application methods for business operations based on summarized information. The generated summaries are used as prompts, and business suggestions are generated via the OpenAI API. For example, the following prompts are used:

[1364] Based on the following summary, please propose an application:

[1365] (Summary text)

[1366] 4. Providing a user interface:

[1367] The generated suggestions are displayed on the device, providing a visualized, user-accessible interface. This uses a dashboard built with HTML and JavaScript. The dashboard displays the suggestions and a feedback form.

[1368] 5. Gathering feedback and relearning:

[1369] We collect user feedback and use it to retrain the AI ​​model. This retraining improves the accuracy of future suggestions. The feedback is sent to and collected on the server in real time.

[1370] Terminal role

[1371] The terminal primarily serves the following roles:

[1372] 1. Display the dashboard:

[1373] The terminal displays a visualized interface (dashboard) for the user to access. This includes the latest business application proposals and summarized academic research information sent from the server.

[1374] 2. Submitting feedback:

[1375] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the effectiveness and areas for improvement of the suggestions. This feedback is sent to the server and used for retraining.

[1376] User roles

[1377] The user will have the following roles:

[1378] 1. Information verification and evaluation:

[1379] Users review the suggestions provided through the dashboard on their device and evaluate whether to incorporate them into their work. For example, if they receive a suggestion for a new marketing method, they will decide whether to apply it to their actual marketing strategy.

[1380] 2. Providing feedback:

[1381] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. This allows us to evaluate the effectiveness of the suggestions and contribute to the continuous improvement of the system.

[1382] Specific application examples

[1383] For example, if a user specifies "artificial intelligence" as their topic, the server will collect the latest relevant literature and generate summaries from it. Based on these summaries, it will then suggest how they can be applied to content delivery services. Specifically, a possible suggestion might be, "Using this new AI algorithm will improve the accuracy of the recommendation system." Users can view these suggestions on a dashboard and contribute to improving the system's accuracy by providing feedback.

[1384] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1385] Step 1: Data Collection

[1386] The server receives a topic specified by the user. The server accesses academic literature databases on the internet and searches for literature related to the specified topic. Specifically, the server uses the requests library to send requests to the literature database API and retrieve relevant literature information. The input is the topic specified by the user, and the output is a list of retrieved literature.

[1387] Step 2: Information Extraction and Summary Generation

[1388] Based on the collected list of literature, the server extracts the abstract, conclusions, and experimental results for each document. Next, the server's natural language processing (NLP) module analyzes this information and generates a summary. This NLP processing utilizes the OpenAI API. The input is the text data of the literature, and the output is the extracted summary.

[1389] Step 3: Generating Business Application Proposals

[1390] Based on the generated summary, the server's artificial intelligence (AI) module proposes ways to apply it to the business. At this stage, the summary is used as a prompt, and specific business proposals are generated using the OpenAI API. The input is the summarized text, and the output is a proposal for application methods. Specifically, the server generates prompts such as the following:

[1391] Based on the following summary, please propose an application:

[1392] (Summary text)

[1393] Step 4: Provide the user interface

[1394] The generated business proposals are sent to the terminal, and a visualized operation screen (dashboard) accessible to the user is provided. The terminal displays these proposals using HTML and JavaScript. The input is the business proposal data, and the output is the visualized operation screen. Users can check the information through this dashboard.

[1395] Step 5: Gathering Feedback

[1396] After the user reviews and evaluates the proposal, they submit their feedback to the server via a feedback form. The server collects this feedback and stores it in a database. The input is the user's feedback information, and the output is the result of saving the feedback to the database.

[1397] Step 6: Relearning

[1398] Based on the collected feedback, the server's artificial intelligence model undergoes retraining. This retraining improves the accuracy of subsequent suggestions. In this process, the server analyzes the feedback data and generates new model parameters. The input is the feedback data, and the output is the updated AI model. As a result of retraining, the suggestions improve, and the overall accuracy of the system increases.

[1399] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1400] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and emotion engine. The embodiments for carrying out the present invention are described in detail below.

[1401] 1. Server Role

[1402] Data collection

[1403] The server accesses a scholarly literature database and collects the latest literature related to the specified topic. Queries are performed according to business-related keywords and filtering conditions. The collected literature data is stored in a database on the server.

[1404] Information extraction and summary generation

[1405] A natural language processing (NLP) module installed on the server analyzes the collected literature and automatically extracts abstracts, conclusions, and experimental results. Next, it generates a summary based on the extracted information. The summary generation algorithm extracts the important information and formats it into a concise and easy-to-understand format.

[1406] Generating business application proposals

[1407] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates to present application methods tailored to predefined business contexts and business processes. For example, in the case of literature on a new algorithm, it would suggest how that algorithm can help streamline business processes.

[1408] Analysis of the Emotion Engine

[1409] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[1410] Providing a user interface (UI)

[1411] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[1412] Gathering feedback and learning

[1413] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This continuously improves the accuracy and usefulness of subsequent suggestions.

[1414] 2. The role of the terminal

[1415] Dashboard display

[1416] The terminal displays an enterprise dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[1417] Submitting feedback

[1418] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[1419] 3. User Roles

[1420] Information verification and evaluation

[1421] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they decide whether to apply it to their actual marketing strategy.

[1422] Provide feedback

[1423] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form, and the information is sent to the server. In addition, an emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[1424] Specific example

[1425] Example 1: Application in the development of medical devices

[1426] A server collects the latest medical literature and generates summaries using natural language processing. An AI module generates suggestions on how the research findings in this literature can be applied to the company's medical devices. A terminal presents these suggestions to employees in the medical device development department, who review the suggestions and provide feedback. An emotion engine analyzes the emotions expressed by the employees during the feedback process and sends this information back to the server.

[1427] Example 2: Application in improving marketing strategies

[1428] The server collects the latest marketing-related literature and generates summaries using natural language processing. An AI module extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies. A terminal presents these proposals to sales representatives, who then try out the suggestions and provide feedback. An emotion engine analyzes the user's emotions during feedback and sends the results to the server.

[1429] As described above, through the system of the present invention, companies can quickly and efficiently apply academic knowledge to their operations and achieve innovation in business processes. Furthermore, the system is continuously improved based on feedback that takes user emotions into consideration.

[1430] The following describes the processing flow.

[1431] Step 1:

[1432] The server accesses the academic literature database and searches for the latest literature related to the specified topic. The query is executed according to business-related keywords and filtering conditions.

[1433] Step 2:

[1434] The server downloads bibliographic data from the search results and stores the metadata and full text of academic papers in the database. This ensures that the data necessary for subsequent processing steps is available.

[1435] Step 3:

[1436] The server's natural language processing (NLP) module analyzes the full text of the collected literature and automatically extracts the abstract, conclusion, and experimental results sections. This extracted data is then passed on to the next summary generation process.

[1437] Step 4:

[1438] The server uses a summarization algorithm to generate a concise summary from the extracted information. The summary highlights the most important points in the paper and is presented in an easy-to-understand format.

[1439] Step 5:

[1440] The server's artificial intelligence (AI) module automatically generates application methods for business operations based on the generated summaries. The AI ​​module provides practical suggestions based on the business context and business processes.

[1441] Step 6:

[1442] The server applies the generated application proposals to a business proposal template and formats them into a visually easy-to-understand form. The formatted proposals are then prepared for subsequent dashboard display.

[1443] Step 7:

[1444] The terminal updates the enterprise dashboard provided to the user, displaying the latest business application suggestions and summary information received from the server. Users access this information through this dashboard.

[1445] Step 8:

[1446] The emotion engine analyzes the user's emotional state when providing feedback. The device acquires the user's text input and voice data and sends the emotion data to the server.

[1447] Step 9:

[1448] The server's emotion engine analyzes the transmitted emotion data to detect the user's emotional state. The analysis results are stored along with the feedback data.

[1449] Step 10:

[1450] Users review the information displayed on the dashboard and evaluate suggestions that are helpful for their work. They then decide whether or not to apply the suggestions to their tasks.

[1451] Step 11:

[1452] Users provide feedback by using a feedback form on the dashboard to evaluate the usefulness and areas for improvement of the suggestions. The feedback is sent to the server in real time, and sentiment analysis data is also attached.

[1453] Step 12:

[1454] The server collects user feedback and stores it in a database. The collected feedback data is then used in the next model retraining process.

[1455] Step 13:

[1456] The server retrains the artificial intelligence model based on feedback data and sentiment analysis results. This retraining process continuously improves the accuracy and usefulness of the generated application suggestions.

[1457] Step 14:

[1458] The server updates the learning results and incorporates them into subsequent suggestion generation processes. This improves overall system performance and user satisfaction.

[1459] (Example 2)

[1460] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1461] Conventional technologies made the process of efficiently collecting the latest academic literature, extracting its summaries and conclusions, and applying them to actual work time-consuming and limited in accuracy. Furthermore, there was insufficient method for quickly incorporating user feedback to improve the system. Therefore, challenges existed in improving work efficiency and the quality of proposed solutions.

[1462] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1463] In this invention, the server includes means for accessing the latest information resource database and searching for and collecting information related to a specified field; means for automatically extracting summaries, conclusions, and results from the collected information and generating a summary; intelligent means for automatically generating application methods for business based on the generated summary; means for analyzing the user's emotional state using a cognitive analysis engine; means for displaying the generated application methods on an information terminal and providing a user-accessible interface; and means for collecting feedback from the user and continuously improving the intelligent model. This enables the rapid application of the latest academic knowledge to business operations, the realization of efficient business processes, and the continuous improvement of the system.

[1464] An "information resource database" is a database that collects, stores, and provides information related to various fields in a searchable format.

[1465] An "abstract" is a concise summary of the content of a document or report.

[1466] The "conclusion" is the final judgment or assertion derived from the results of literature and research.

[1467] "Results" refer to data and outcomes obtained based on literature and research.

[1468] A "summary" is a short piece of text that concisely summarizes the content of a document or report, extracting the most important points.

[1469] An "intelligent tool" is a system that uses artificial intelligence technology to automatically perform specific tasks.

[1470] A "cognitive analysis engine" is a system that analyzes a user's text input and voice data to detect their emotional state.

[1471] An "information terminal" is a device that allows users to access information through an interface. Examples include personal computers and smartphones.

[1472] An "interface" refers to the user interface or input tools that allow a user to interact with a system.

[1473] "Feedback" refers to evaluations and opinions provided by users, and is used to improve the system and enhance the accuracy of suggestions.

[1474] An "intelligent model" refers to the structure or pattern of artificial intelligence generated by a learning algorithm and used to perform a specific task.

[1475] The system of the present invention automates the process of collecting the latest information, generating application suggestions for business operations, and continuously improving it based on user feedback. The embodiments for carrying out the present invention are described in detail below.

[1476] Server Role

[1477] Data collection

[1478] First, the server accesses an information resource database. This access uses an API (e.g., PubMed API, IEEE Xplore API). It searches for and effectively collects information related to a specified field. For example, it executes queries using keywords such as "artificial intelligence" or "medical device development" and stores the retrieved data in a database (e.g., MySQL, MongoDB).

[1479] Information extraction and summary generation

[1480] The server analyzes the collected information using an NLP module (e.g., spaCy, BERT). This analysis extracts key information such as the summary, conclusions, and results. Next, a summarization algorithm (e.g., TF-IDF, topic modeling) is used to convert the extracted information into a concise and easy-to-understand summary.

[1481] Generating business application proposals

[1482] Furthermore, the server's intelligent model (e.g., GPT-3, Transformers) generates business application suggestions based on the generated summary. This process uses specific templates (e.g., SWOT analysis framework) to suggest how the new insights can help improve business processes.

[1483] Emotion analysis

[1484] The server is equipped with a cognitive analysis engine (e.g., IBM Watson, sentimentr) that analyzes user feedback to understand their emotional state. This allows for the acquisition of information that can be used to assess the usefulness of suggestions and improve future offerings.

[1485] Terminal role

[1486] Dashboard display

[1487] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. This interface is built using, for example, React.js. Through this dashboard, users can review the information and evaluate the suggestions. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[1488] Submitting feedback

[1489] A form is installed on the device to easily collect user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The server analyzes the submitted feedback data and stores it in a database along with the user's emotional state.

[1490] User roles

[1491] Information verification and evaluation

[1492] Users review the suggestions provided through a dashboard on their device and evaluate those that are useful for their work. For example, if they receive a suggestion for a new marketing method, they will determine whether it is applicable to their own marketing strategy.

[1493] Provide feedback

[1494] Users try out the suggested features and provide feedback on the results. Feedback is given through an evaluation form, and the emotion engine analyzes the user's input data, saving their emotional state as part of the feedback.

[1495] Specific example

[1496] Example 1: Application in the development of medical devices

[1497] 1. The server collects the latest medical literature and generates summaries using natural language processing.

[1498] 2. The intelligent model generates proposals on how the research findings in this document can be applied to the company's medical devices.

[1499] 3. The terminal presents this proposal to an employee in the medical device development department, who reviews the proposal and provides feedback.

[1500] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback, and this information is also sent to the server.

[1501] Example 2: Application in improving marketing strategies

[1502] 1. The server collects the latest marketing-related literature and generates summaries using natural language processing.

[1503] 2. The intelligent model extracts new consumer behavior analysis methods from the literature and proposes how these methods can be applied to marketing strategies.

[1504] 3. The terminal presents this proposal to the sales representative, who then tries out the proposal and provides feedback on the results.

[1505] 4. The cognitive analysis engine analyzes the emotions of employees when they provide feedback and sends the results to the server.

[1506] Example of a prompt

[1507] "Summarize the latest academic literature on medical devices and propose how to apply it to our company's product development."

[1508] "Collect the latest literature on new marketing techniques, generate summaries, and propose how these techniques can be applied to consumer behavior analysis."

[1509] As described above, through the system of the present invention, companies can apply academic knowledge to their operations quickly and efficiently, thereby achieving innovation in business processes and continuous improvement of systems.

[1510] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1511] Step 1:

[1512] Data collection

[1513] The server accesses an information resource database (e.g., PubMed, IEEE Xplore). The input is a query related to a specified topic (e.g., "artificial intelligence," "medical device development"). Based on this query, the server searches the database for relevant information. The search results (bibliographic data) are output. The server saves this bibliographic data to a database (e.g., MySQL, MongoDB).

[1514] Step 2:

[1515] Information Extraction

[1516] The server analyzes collected literature data using an NLP module (e.g., spaCy, BERT). The input is literature data stored in a database. The NLP module automatically extracts the abstract, conclusion, and results of the literature. This extracted information is then generated as output. This information is passed on to the next step in summary generation.

[1517] Step 3:

[1518] Summary generation

[1519] The server uses a summarization algorithm (e.g., TF-IDF, topic modeling) to generate a concise and easy-to-understand summary from the extracted information. The input is the extracted information. The algorithm selects key points and formats them into a summary. The generated summary is output and used to generate business application proposals.

[1520] Step 4:

[1521] Generating business application proposals

[1522] The server's intelligent model (e.g., GPT-3, Transformers) automatically generates business application proposals based on the generated summary. The input is the generated summary. The intelligent model constructs the proposals using a specific template (e.g., SWOT analysis framework). The proposed content is output and formatted for display.

[1523] Step 5:

[1524] Emotion analysis

[1525] A cognitive analysis engine (e.g., IBM Watson, sentimentr) installed on the server analyzes user feedback. The input is feedback text or audio data sent by the user. The analysis engine detects the emotional state (e.g., positive, negative) and generates the result as output. This analysis result is also stored in a database.

[1526] Step 6:

[1527] Dashboard display

[1528] The terminal displays the latest business application suggestions and summary information received from the server as an enterprise dashboard. Input consists of suggestions and summary information sent from the server. The terminal builds the dashboard using React.js and displays it to the user. The user can access the information through this dashboard. The displayed content may also be dynamically adjusted based on the user's emotional state.

[1529] Step 7:

[1530] Submitting feedback

[1531] Users evaluate the proposals through a dashboard and submit the feedback form with the necessary information. This feedback consists of user opinions regarding the evaluation and potential improvements to the proposals. The feedback data is sent from the device to the server, where it is analyzed by a cognitive analysis engine, including the user's emotional state.

[1532] Step 8:

[1533] Storing and learning from feedback

[1534] The server stores user feedback data and sentiment analysis results in a database. The input consists of user-provided feedback and analysis results of emotional states. This data is used in the next model retraining process. The output is an improvement to the AI ​​model and increased suggestion accuracy.

[1535] The above outlines the specific processing steps of this system. Through the specific actions of the server, terminal, and user in each step, it becomes possible to quickly collect the latest academic knowledge and apply it to work. Furthermore, the system is continuously improved based on user feedback.

[1536] (Application Example 2)

[1537] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1538] Traditional advertising strategies faced the challenge of quickly gathering information on the latest marketing techniques and consumer behavior analysis, and then formulating effective strategies based on that information. Furthermore, there was a lack of systems capable of evaluating the effectiveness of advertising strategies and providing real-time feedback and sentiment analysis for continuous improvement.

[1539] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accessing the latest academic literature database, searching for and collecting literature related to a specified topic, means for automatically extracting abstracts, conclusions, and experimental results from the collected literature and generating summaries, artificial intelligence means for automatically generating application methods for business based on the generated summaries, means for displaying the generated application methods on a terminal and providing a dashboard accessible to the user, means for collecting feedback from the user and continuously improving the artificial intelligence model, and means for providing advertising-related information via a display device that allows the user to visually confirm it. This enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[1540] A "scholarly literature database" is a database that contains academic research results and papers.

[1541] An "abstract" is a short, concise summary of the content of a document, highlighting its main points and conclusions.

[1542] A "conclusion" refers to the final judgment or opinion that the author has arrived at as a result of their research in a given document.

[1543] "Experimental results" refer to data and observations obtained during the course of research or experiments.

[1544] A "summary" is a concise document that summarizes the main points of a text, and is used to aid in understanding the overall content.

[1545] "Artificial intelligence" is a general term for software and systems that can perform information processing and decision-making by mimicking human intelligence.

[1546] A "terminal" is an electronic device used by a user to access and operate information.

[1547] A "dashboard" is a visual interface that allows users to see multiple pieces of information at a glance.

[1548] "Feedback" refers to the opinions and evaluations that users provide to a system or service.

[1549] A "display device" is a device used to visually display information, and includes screens and displays.

[1550] "Advertising-related information" refers to useful data, knowledge, and analytical methods within the advertising industry.

[1551] "Visual inspection" refers to the act of directly seeing something with the human eye.

[1552] "Collection" refers to a series of activities that involve gathering specific information or data.

[1553] "Extraction" refers to the operation of taking out specific elements or information from a whole.

[1554] "Generation" refers to the process of creating new information or data.

[1555] "Provision" refers to the act of a system or service delivering information to a user.

[1556] "Most suitable" means being judged to be the best for a particular purpose.

[1557] The system of the present invention is realized through the mutual cooperation of a server, terminal, user, and display device as a means for displaying advertising-related information. This system enables advertising industry professionals to quickly formulate effective advertising strategies based on the latest marketing methods and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[1558] 1. Server Role

[1559] Data collection

[1560] The server accesses academic literature databases and collects the latest literature related to the specified topic. The collection process uses work-related keywords and filtering criteria. The literature data is stored in a database on the server.

[1561] Information extraction and summary generation

[1562] Using a natural language processing (NLP) module installed on the server, abstracts, conclusions, and experimental results are automatically extracted from collected literature to generate summaries. Generative AI models such as Hugging Face's transformers library are used for summary generation.

[1563] Generating business application proposals

[1564] Based on the generated summary, the server's artificial intelligence (AI) module automatically generates application methods for business operations. This process uses templates that present application methods tailored to predefined business contexts and business processes.

[1565] Analysis of the Emotion Engine

[1566] The emotion engine installed on the server analyzes the user's emotional state when they provide feedback. The emotion engine analyzes the user's text input and voice data to detect their emotions.

[1567] Providing a user interface (UI)

[1568] The server sends generated suggestions to the terminal as a user interface, and the user can visually review this information through a dashboard. This dashboard displays the latest suggestions and a feedback form. Furthermore, the content and display format of the suggestions are dynamically adjusted based on the user's emotional state.

[1569] Gathering feedback and learning

[1570] The server collects user feedback and stores it in a database. This feedback data, along with the user's sentiment analysis results, is used in the next model retraining process. This improves the accuracy and usefulness of future suggestions.

[1571] 2. The role of the terminal

[1572] Dashboard display

[1573] The terminal displays a dashboard for the user to access. This dashboard contains the latest business application suggestions and summary information sent from the server. The user can access and evaluate the information through this interface. Furthermore, the displayed content is dynamically adjusted based on the user's emotional state.

[1574] Submitting feedback

[1575] The dashboard on the device includes a form for collecting user feedback. Users can input and submit their opinions on the usefulness and areas for improvement of suggestions. The emotion engine analyzes the user's input data, and their emotional state is also sent to the server as feedback.

[1576] 3. User Roles

[1577] Information verification and evaluation

[1578] Users who are advertising industry professionals review the suggestions provided through the dashboard on their devices and evaluate those that are useful for their work. For example, if a new marketing method is suggested, they decide whether to apply it to their actual advertising strategy.

[1579] Provide feedback

[1580] Users try out suggestions and provide feedback on the results. This feedback is submitted through an evaluation form and sent to the server. An emotion engine analyzes the user's input data, and their emotional state is also reflected in the feedback. This helps evaluate the effectiveness of the suggestions and contributes to the continuous improvement of the system.

[1581] Specific example

[1582] Sample generation AI prompt text

[1583] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[1584] Abstract: {Abstract of the literature}

[1585] Conclusion: {Conclusion of the literature}

[1586] for example:

[1587] Generate summaries from the abstracts and conclusions of recent marketing-related literature.

[1588] Abstract: This study focuses on the latest trends in consumer behavior analysis...

[1589] Conclusion: The findings suggest that integrating AI models with traditional marketing strategies...

[1590] This system enables advertising professionals to quickly develop effective advertising strategies based on the latest marketing techniques and consumer behavior analysis, and to continuously improve them through real-time feedback and sentiment analysis.

[1591] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1592] Step 1:

[1593] The server accesses an academic literature database and collects the latest literature related to the specified topic. The data used as input consists of business-related keywords and filtering conditions. This ensures that the latest marketing-related literature is stored in the database on the server.

[1594] Step 2:

[1595] A natural language processing (NLP) module installed on the server automatically extracts abstracts, conclusions, and experimental results from collected literature. The input is the literature data collected in step 1, and the output is the extracted abstracts, conclusions, and experimental results. Specifically, the analysis is performed using the Hugging Face transformers library.

[1596] Step 3:

[1597] The server processes the extracted information for summary generation, concisely summarizing the key points. The input is the information extracted in step 2, and the output is the generated summary. This step also utilizes the Hugging Face transformers library.

[1598] Step 4:

[1599] An artificial intelligence (AI) module installed on the server automatically generates application methods for business operations based on the generated summary. The input is the summary generated in step 3, and the output is a proposal for application methods. The AI ​​module generates proposals using predefined templates that correspond to the business context and business processes.

[1600] Step 5:

[1601] The server displays the generated application methods on the terminal. A user interface (UI) for this purpose is provided on the dashboard, making it accessible to the user. The input is the application method from step 4, and the output is the suggestion displayed on the user's terminal. The dashboard is implemented using web technologies such as HTML and JavaScript.

[1602] Step 6:

[1603] Users review application methods through a dashboard on their devices and apply them to their actual advertising strategies. Users review the suggestions and provide feedback. The input is the suggestions displayed by the server, and the output is the user's evaluation and feedback. User actions include entering opinions into a feedback form and submitting it.

[1604] Step 7:

[1605] The device collects user feedback and sends it to the server. The input is the user's feedback, and the output is the feedback data sent to the server. During this process, sentiment analysis is performed on the device, analyzing text input and voice data.

[1606] Step 8:

[1607] The server stores the collected feedback data in a database and uses it along with the sentiment analysis results in the next model retraining process. The input is the feedback data sent in step 7, and the output is the improved AI model. Specifically, the feedback data is analyzed and reused as training data for the AI ​​model.

[1608] These steps enable advertising professionals to quickly incorporate the latest marketing techniques and consumer behavior analysis to develop effective advertising strategies, and to continuously improve them through real-time feedback and sentiment analysis.

[1609] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1610] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1611] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1612] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1613] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1614] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1615] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1616] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1617] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1618] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1619] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1620] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1621] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1622] 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.

[1623] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1624] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1625] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1626] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1627] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1628] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1629] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1630] The following is further disclosed regarding the embodiments described above....

Claims

1. A means of accessing the latest academic literature databases and searching for and collecting literature related to a specified topic, A means for automatically extracting abstracts, conclusions, and experimental results from collected literature and generating summaries, An artificial intelligence tool that automatically generates application methods for business based on the generated summary, A means of displaying the generated application methods on a terminal and providing a user-accessible dashboard, A means of collecting feedback from users and continuously improving the artificial intelligence model, A system that includes this.

2. The system according to claim 1, which applies the generated application method to a business proposal template and formats it in a highly visual format.

3. The system according to claim 1, which retrains an artificial intelligence model based on user feedback to improve the accuracy of suggestions for subsequent uses.

Images