system

Abstract

The system according to this embodiment aims to enable researchers to automatically convert the format of their papers for submission. [Solution] The system according to the embodiment comprises a reception unit, a selection unit, a research unit, a conversion unit, and a checking unit. The reception unit uploads papers written by researchers in Word or PDF format. The selection unit selects the desired journal based on the papers uploaded by the reception unit. The research unit checks the format of the journal selected by the selection unit. The conversion unit converts the papers to match the format checked by the research unit. The checking unit allows researchers to check the papers converted by the conversion unit.

Description

Technical Field

[0006] , , , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, since the paper submission format varies depending on the journal, there is a problem that it is troublesome for researchers to manually rewrite the format.

[0005] The system according to the embodiment aims to automatically convert the paper submission format for researchers.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a reception unit, a selection unit, a research unit, a conversion unit, and a checking unit. The reception unit allows researchers to upload papers in Word or PDF format. The selection unit selects the desired journal based on the papers uploaded by the reception unit. The research unit examines the format of the journals selected by the selection unit. The conversion unit converts the papers to match the format examined by the research unit. The checking unit allows researchers to check the papers converted by the conversion unit. [Effects of the Invention]

[0007] The system according to this embodiment allows researchers to automatically convert the format of their papers for submission. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10]This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] 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), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) An AI agent system according to an embodiment of the present invention is a system that automatically converts papers written by researchers to conform to journal formats. This AI agent system allows researchers to upload their papers in Word or PDF format and select a desired journal. The system then examines the format of the selected journal and automatically converts the word count, title style, reference display style, etc. For example, the AI ​​agent system accepts papers in Word or PDF format. Next, the AI ​​agent system allows researchers to select a desired journal. The AI ​​agent system uses web scraping and document analysis to examine the format of the selected journal. For example, the AI ​​agent system obtains submission guidelines from the journal's website. Next, the AI ​​agent system analyzes the submission guidelines using natural language processing (NLP) and regenerates the paper using a generative model (e.g., a large-scale language model). For example, the AI ​​agent system converts the paper to conform to format requirements such as word count, title style, and reference display style. Finally, the AI ​​agent system allows the researcher to check the format created by the AI ​​agent system. This significantly reduces the time and effort required for researchers to change the format of their papers, allowing them to focus on other research activities. Furthermore, the AI ​​agent system accurately understands the formatting requirements of each journal and converts them appropriately, streamlining the submission process while maintaining the quality of the paper. This allows researchers to easily submit their papers in accordance with the journal's format.

[0029] The AI ​​agent system according to this embodiment comprises a reception unit, a selection unit, a research unit, a conversion unit, and a checking unit. The reception unit uploads papers written by researchers in Word or PDF format. Papers written by researchers include, but are not limited to, academic papers, technical reports, and review articles. The reception unit uploads papers written by researchers by drag and drop, for example. The reception unit can also upload papers using a file selection dialog. Furthermore, the reception unit can set a file size limit. For example, the reception unit can set a maximum file size of 10MB. The selection unit selects the desired journal based on the papers uploaded by the reception unit. For example, the selection unit allows researchers to select the desired journal from a drop-down menu. The selection unit can also provide a journal search function. For example, the selection unit can provide a function to search by journal name or keyword. Furthermore, the selection unit can also provide a function to filter journals by category. For example, the selection unit displays journals by category such as science, technology, and medicine. The research unit examines the format of the journals selected by the selection unit. The research department can, for example, obtain journal submission guidelines using web scraping. The research department can also analyze the submission guidelines using document analysis. For example, the research department can obtain the submission guidelines from the journal's website and analyze them using natural language processing techniques. Furthermore, the research department can store the journal's submission guidelines in a database. For example, the research department can store the obtained submission guidelines in a database for later reference. The transformation department transforms the paper to conform to the format examined by the research department. The transformation department can, for example, analyze the submission guidelines using natural language processing (NLP) and regenerate the paper using a generative model. For example, the transformation department can regenerate the paper using a generative model such as a large-scale language model. The transformation department can also transform the paper to conform to formatting requirements such as character count, title style, and reference display style. For example, the transformation department can shorten the paper to conform to character limits. Title style changes include, for example, altering font size, font type, and alignment.The reference display style can be changed, for example, the citation format or the format of the bibliography. The checking unit allows researchers to check the papers converted by the conversion unit. The checking unit provides, for example, an interface for researchers to verify the format created by the AI ​​agent system. The checking unit can also provide a function for researchers to modify the format as needed. For example, the checking unit provides an editor for researchers to manually modify the format. This allows the AI ​​agent system according to the embodiment to enable researchers to easily submit papers in accordance with journal formats.

[0030] The reception desk allows researchers to upload papers in Word or PDF format. These papers include, but are not limited to, academic papers, technical reports, and review articles. The reception desk allows researchers to upload papers via drag-and-drop, for example. Alternatively, researchers can upload papers using a file selection dialog. Furthermore, the reception desk can set file size limits; for example, it can set a maximum file size of 10MB. The reception desk is designed to allow researchers to easily upload papers through its user interface. Specifically, researchers can easily upload files using the drag-and-drop function. When using the file selection dialog, researchers simply navigate to select files and click the upload button. In addition, the reception desk automatically detects the format of uploaded files and performs the appropriate processing. For example, for Word files, it extracts text and images; for PDF files, it analyzes the content page by page. This ensures that the reception desk can properly process papers regardless of the format uploaded by researchers. Furthermore, by setting file size limits, the reception desk reduces system load and achieves efficient processing. For example, setting the maximum file size to 10MB can prevent system delays caused by large files. This allows the reception desk to not only enable researchers to easily upload papers but also maintain overall system performance.

[0031] The selection section allows researchers to choose their desired journals based on the papers uploaded by the submission section. For example, researchers can select their desired journals from a dropdown menu. The selection section can also provide a journal search function, such as searching by journal name or keywords. Furthermore, it can provide a filtering function by journal category, such as displaying journals by category (e.g., science, technology, medicine). The selection section is designed to allow researchers to easily select their desired journals through its user interface. Specifically, researchers can select their desired journals from a list using a dropdown menu. When using the search function, researchers can enter journal names or keywords to find the relevant journals. When using the category filtering function, researchers can select categories such as science, technology, or medicine to display the relevant journals. This allows the selection section not only to easily select desired journals but also to efficiently search for them. Additionally, the selection section can provide detailed journal information to help researchers make their selections. For example, it can display information such as journal submission guidelines, impact factor, and past publications. This allows the selection section to provide researchers with reference information when choosing a journal they wish to review, thereby supporting them in making an appropriate selection.

[0032] The research department examines the format of the journals selected by the selection department. The research department can obtain journal submission guidelines, for example, by using web scraping. Alternatively, the research department can analyze the submission guidelines using document analysis. For example, the research department can obtain the guidelines from the journal's website and analyze them using natural language processing techniques. Furthermore, the research department can store the journal's submission guidelines in a database. For example, the research department can save the obtained submission guidelines in a database for later reference. The research department automatically obtains submission guidelines from journal websites using web scraping techniques. Specifically, it uses web scraping tools to analyze the HTML structure of the journal's website and extract the text of the submission guidelines. When using document analysis techniques, the research department uses natural language processing techniques to analyze the text of the submission guidelines and extract the necessary information. For example, it extracts information such as character limits, formatting requirements, and citation formats from the submission guidelines. This allows the research department to accurately understand the journal's submission guidelines and provide the information necessary for subsequent processing. The research department also saves the obtained submission guidelines in a database for later reference. For example, submission guidelines stored in the database can be reused by other researchers when submitting to the same journal. This allows the research department to efficiently retrieve journal submission guidelines and improve the overall efficiency of the system.

[0033] The conversion unit transforms the paper to match the format researched by the research unit. The conversion unit, for example, analyzes the submission guidelines using natural language processing (NLP) and regenerates the paper using generative models. For example, the conversion unit regenerates the paper using generative models such as large-scale language models. The conversion unit can also transform the paper to match formatting requirements such as character count, title style, and reference display style. For example, the conversion unit shortens the paper to meet character limits. Title style changes include, for example, font size, font type, and alignment. Reference display style changes include, for example, citation format and bibliography format. The conversion unit uses natural language processing techniques to analyze the details of the submission guidelines and automatically transforms the paper's content. Specifically, it uses generative models to regenerate the paper's content and convert it to a format that meets the submission guidelines. For example, it uses generative models such as large-scale language models to regenerate the paper's content and shorten it to meet character limits. When changing the title style, the conversion unit changes the font size, font type, alignment, etc., and converts it to a style that meets the submission guidelines. When changing the style of reference display, the conversion unit modifies the citation format and bibliography format to conform to the submission guidelines. This allows the conversion unit to automatically convert the paper to match the submission guidelines, making it easy for researchers to submit their papers. Furthermore, to improve the accuracy of the conversion process, the conversion unit regularly updates the training data of its generative model to keep up with the latest submission guidelines. This ensures that the conversion unit always provides highly accurate conversions that comply with the most up-to-date submission guidelines.

[0034] The checking section allows researchers to review papers converted by the conversion section. For example, the checking section provides an interface for researchers to verify the format created by the AI ​​agent system. It can also provide a function for researchers to modify the format as needed. For instance, the checking section provides an editor for researchers to manually correct the format. The checking section is designed to allow researchers to review converted papers and make necessary corrections through a user interface. Specifically, it provides an interface for researchers to preview the converted paper and verify the accuracy of the format. If researchers need to correct the format, the checking section provides an editor for manual correction. Using the editor, researchers can fine-tune the format details and correct them to perfectly match the submission guidelines. This provides the checking section with a flexible tool for researchers to review converted papers and make necessary corrections. Furthermore, the checking section allows researchers to save the corrections and run the conversion process again to verify the final format. This allows the checking section to support researchers in verifying the accuracy of the format and making necessary corrections before submitting their papers.

[0035] The research department can obtain journal submission guidelines using web scraping and document analysis. For example, the research department can obtain submission guidelines from journal websites using web scraping. For example, the research department can analyze web pages using the Python BeautifulSoup library and extract submission guidelines. The research department can also analyze submission guidelines using document analysis. For example, the research department can analyze submission guidelines using natural language processing techniques and extract necessary information. For example, the research department can analyze the text of the submission guidelines using an NLP library and extract information such as character count, title style, and reference display style. This allows the research department to accurately obtain journal submission guidelines. Web scraping is performed using libraries such as Python's BeautifulSoup or Scrapy. Document analysis is performed using NLP techniques or text mining techniques. Some or all of the above processes performed by the research department may be performed using AI, for example, or not using AI. For example, the research department can input text data of submission guidelines obtained through web scraping into a generating AI and have the generating AI perform an analysis of the submission guidelines.

[0036] The transformation unit can analyze submission guidelines using natural language processing and regenerate the paper using a generative model. For example, the transformation unit analyzes submission guidelines using natural language processing techniques. For example, the transformation unit analyzes submission guidelines using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The transformation unit can also regenerate the paper using a generative model. For example, the transformation unit regenerates the paper using a generative model such as a large-scale language model. For example, the transformation unit generates an abstract of the paper using a large-scale language model. This allows the transformation unit to accurately convert the paper into the journal format. Natural language processing is performed using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The generative model is performed using a model such as a large-scale language model. Some or all of the above processing in the transformation unit may be performed using AI, or not. For example, the transformation unit can input the text data of the submission guidelines into a generative AI and have the generative AI regenerate the paper.

[0037] The conversion unit can convert a paper to meet formatting requirements such as character count, title style, and reference display style. For example, the conversion unit can shorten a paper to meet character limits. For instance, it calculates the character count of each section of the paper and removes any parts that exceed the limit. The conversion unit can also change the title style. For example, it can change the font size, font type, and alignment of the title. Furthermore, the conversion unit can change the reference display style. For example, it can change the citation format and the format of the bibliography. This allows the conversion unit to accurately conform to the formatting requirements of the paper. Character limits are set based on criteria such as maximum and minimum character counts. Title styles are set based on requirements such as font size, font type, and alignment. Reference display styles are set based on requirements such as citation format and bibliography format. Some or all of the above processing in the conversion unit may be performed using AI, for example, or not. For example, the conversion unit can input the text data of a paper into a generating AI, which can then perform adjustments to the number of characters and changes to the style.

[0038] The checking unit allows researchers to check the format created by the AI ​​agent. The checking unit provides, for example, an interface for researchers to review the format created by the AI ​​agent system. For example, the checking unit provides a screen for researchers to preview the format. The checking unit can also provide a function for researchers to modify the format as needed. For example, the checking unit provides an editor for researchers to manually modify the format. This allows the checking unit to allow researchers to review the format and modify it as needed. The AI ​​agent creates the format using, for example, natural language processing techniques or generative models. Some or all of the above processing in the checking unit may be performed using, for example, AI, or not using AI. For example, the checking unit presents the format created by the generative AI to the researcher and provides an interface for the researcher to review it.

[0039] The reception desk can analyze a researcher's past paper submission history and select the optimal upload method. For example, the reception desk can prioritize suggesting upload methods the researcher has used in the past (e.g., drag and drop, file selection). The reception desk can also send notifications to researchers if they have previously uploaded during specific time periods. The reception desk can also automatically select file formats the researcher has used in the past (e.g., Word, PDF). This allows the reception desk to select the optimal upload method based on the researcher's past history. Past paper submission history includes, for example, submission date and time, and the journal to which the paper was submitted. The optimal upload method is selected based on, for example, the researcher's past history. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception department can input a researcher's past paper submission history data into a generating AI and have the AI ​​select the optimal upload method.

[0040] The reception system can filter papers upon upload based on the researcher's current research topic and areas of interest. For example, the reception system may prioritize displaying journals related to the researcher's current research topic. The reception system can also automatically apply relevant formatting requirements based on the researcher's areas of interest. The reception system can also analyze the content of the researcher's past papers and suggest relevant formatting requirements. This allows the reception system to perform optimal filtering based on the researcher's areas of interest. Research topics include definitions and classifications such as specific academic disciplines and research topics. Areas of interest include definitions and classifications such as specific technological fields and application fields. Filtering is performed based on, for example, the researcher's current research topic and areas of interest. Some or all of the above processing in the reception system may be performed using, for example, AI, or not using AI. For example, the reception desk can input data on researchers' research themes and areas of interest into a generating AI, and have the AI ​​perform filtering.

[0041] The reception desk can prioritize uploading highly relevant papers by considering the researcher's geographical location when they upload their papers. For example, if a researcher is in a specific region, the reception desk will prioritize the format of journals relevant to that region. For example, if a researcher is in a specific region, the reception desk will prioritize the format of journals relevant to that region. For example, if a researcher is attending an international conference, the reception desk will prioritize the format of journals recommended by that university if the researcher is affiliated with a specific university. For example, if a researcher is affiliated with a specific university, the reception desk will prioritize the format of journals recommended by that university. This allows the reception desk to upload the most relevant papers based on the researcher's geographical location. Geographical location information includes, for example, specific methods of acquisition and use such as GPS data and IP addresses. Highly relevant papers are selected based on criteria and selection methods such as the degree of agreement on research themes and citation relationships. Some or all of the above-described processes in the reception area may be performed using AI, for example, or without AI. For example, the reception area can input the geographical location data of researchers into a generating AI and have the generating AI select highly relevant papers.

[0042] The reception desk can analyze a researcher's social media activity when they upload a paper and upload relevant papers. For example, the reception desk can prioritize uploading papers that the researcher has shared on social media. The reception desk can also prioritize uploading papers related to topics that the researcher has shown interest in on social media. The reception desk can also prioritize uploading papers related to topics that the researcher's social media followers have shown interest in. This allows the reception desk to upload the most relevant papers based on the researcher's social media activity. Social media activity includes specific details and analysis methods such as post content, follower count, and engagement rate. Relevant papers are selected based on criteria and selection methods such as the degree of agreement on research themes and citation relationships. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input researchers' social media activity data into a generative AI and have the AI ​​select relevant papers.

[0043] The selection unit can suggest the most suitable journals by referring to the researcher's past submission history when selecting journals. For example, the selection unit can suggest highly relevant journals based on the journals the researcher has previously submitted to. For example, the selection unit can suggest highly relevant journals based on the journals the researcher has previously submitted to. The selection unit can also suggest the journal with the highest success rate based on the researcher's past submission history. For example, the selection unit can suggest the journal with the highest success rate based on the researcher's past submission history. The selection unit can also suggest the most suitable journal by analyzing the researcher's past submission history. For example, the selection unit can suggest the most suitable journal by analyzing the researcher's past submission history. This allows the selection unit to suggest the most suitable journal based on the researcher's past submission history. Past submission history includes, for example, the submission date and the journal to which it was submitted. The most suitable journal is selected based on criteria and selection methods such as the degree of match in research theme and journal influence factors. Some or all of the above processing in the selection unit may be performed using, for example, AI, or not using AI. For example, the selection unit can input a researcher's past publication history data into a generating AI and have the AI ​​suggest the most suitable journals.

[0044] The selection unit can apply different selection algorithms depending on the researcher's field of study when selecting journals. For example, the selection unit may prioritize displaying journals that are specialized in the researcher's field of study. The selection unit can also apply different selection algorithms depending on the researcher's field of study to suggest the most suitable journals. The selection unit can also make selections considering influencing factors of journals related to the researcher's field of study. This allows the selection unit to select the most suitable journals according to the researcher's field of study. The field of study includes definitions and classifications such as specific academic disciplines and research topics. The selection algorithm includes types and methods of use such as machine learning algorithms and heuristic algorithms. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input researcher field data into a generating AI and have the generating AI perform the application of the selection algorithm.

[0045] The selection unit can make selections by considering the influence factors and evaluations of journals. For example, the selection unit can suggest the most suitable journal based on the influence factors of the journals. For example, the selection unit can suggest the most suitable journal for researchers by considering the evaluations of the journals. For example, the selection unit can suggest the most suitable journal for researchers by comprehensively considering the influence factors and evaluations of the journals. For example, the selection unit can suggest the most suitable journal by comprehensively considering the influence factors and evaluations of the journals. In this way, the selection unit can select the most suitable journal based on the influence factors and evaluations of the journals. Influence factors include definitions and evaluation methods such as impact factor and citation count. Evaluation includes criteria and methods such as peer review results and journal rankings. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input journal influence factor and evaluation data into a generating AI and have the generating AI select the most suitable journal.

[0046] The selection function can prioritize displaying journals recommended by the researcher's affiliated institution when selecting journals. For example, the selection function can prioritize displaying journals recommended by the researcher's affiliated institution. The selection function can also suggest the most suitable journal based on the recommended journals of the researcher's affiliated institution. The selection function can also narrow down the options by considering the recommended journals of the researcher's affiliated institution. For example, the selection function can narrow down the options by considering the recommended journals of the researcher's affiliated institution. In this way, the selection function can select the most suitable journal by prioritizing the display of journals recommended by the researcher's affiliated institution. Journals recommended by the affiliated institution are selected based on criteria and selection methods such as the institution's research policy and past recommendation history. Some or all of the above processing in the selection function may be performed using AI, for example, or without AI. For example, the selection unit can input recommended journal data from the researcher's affiliated institution into the generating AI, allowing the AI ​​to select the most suitable journal.

[0047] The research department can improve the accuracy of its research by referring to the magazine's past format change history during format research. For example, the research department can investigate the latest format requirements based on the magazine's past format change history. The research department can also analyze the magazine's format change history and prioritize investigating the most important changes. The research department can also improve the accuracy of its research by referring to the magazine's format change history. For example, the research department can improve the accuracy of its research by referring to the magazine's format change history. This allows the research department to improve the accuracy of its research based on the magazine's past format change history. The format change history includes specific details such as the date and time of change and the content of the change, as well as how to refer to it. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input the magazine's past format change history data into a generating AI and have the generating AI perform the task of improving the accuracy of the research.

[0048] The research department can apply different research methods to each journal category when conducting format research. For example, the research department can apply different research methods depending on the journal category. For example, the research department can apply different research methods depending on the journal category. The research department can also select the optimal format research method for each journal category. For example, the research department can select the optimal format research method for each journal category. The research department can also adjust the research method based on the journal category. For example, the research department can adjust the research method based on the journal category. This allows the research department to apply the optimal research method according to the journal category. Categories include definitions and classifications such as academic fields and research themes. Research methods include types and methods of use such as questionnaire surveys and interview surveys. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input journal category data into a generating AI and have the generating AI perform the application of research methods.

[0049] The research department can conduct format research while considering the geographical distribution of magazines. For example, the research department can investigate optimal format requirements based on the geographical distribution of magazines. The research department can also narrow down the scope of the research while considering the geographical distribution of magazines. For example, the research department can narrow down the scope of the research while considering the geographical distribution of magazines. The research department can also improve the accuracy of the research by referring to the geographical distribution of magazines. For example, the research department can improve the accuracy of the research by referring to the geographical distribution of magazines. This allows the research department to conduct optimal format research based on the geographical distribution of magazines. Geographical distribution includes definitions and methods of consideration such as country-specific and regional distributions. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input geographical distribution data of magazines into a generating AI and have the generating AI perform the research.

[0050] The research department can improve the accuracy of its research by referring to relevant literature in journals during format research. For example, the research department can investigate the optimal format requirements based on relevant literature in journals. The research department can also narrow down the scope of its research by referring to relevant literature in journals. For example, the research department can narrow down the scope of its research by referring to relevant literature in journals. The research department can also improve the accuracy of its research by analyzing relevant literature in journals. For example, the research department can improve the accuracy of its research by analyzing relevant literature in journals. This allows the research department to improve the accuracy of its research based on relevant literature in journals. Relevant literature includes criteria and reference methods such as citation relationships and the degree of thematic agreement. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can input relevant literature data from journals into a generating AI and have the generating AI perform the research.

[0051] The conversion unit can select the optimal conversion method by referring to the researcher's past paper style when converting a paper. For example, the conversion unit selects the optimal conversion method based on the researcher's past paper style. The conversion unit can also analyze the researcher's past paper style and apply the most suitable format requirements. The conversion unit can also improve the accuracy of the conversion by referring to the researcher's past paper style. This allows the conversion unit to select the optimal conversion method based on the researcher's past paper style. Past paper style includes specific details such as format and citation style, as well as citation methods. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the researcher's past paper style data into a generating AI and have the generating AI select the optimal conversion method.

[0052] The conversion unit can apply different conversion algorithms depending on the journal's format requirements when converting a paper. For example, the conversion unit can apply different conversion algorithms depending on the journal's format requirements. For example, the conversion unit can apply different conversion algorithms depending on the journal's format requirements. The conversion unit can also select the optimal conversion algorithm based on the journal's format requirements. For example, the conversion unit can select the optimal conversion algorithm based on the journal's format requirements. The conversion unit can also adjust the conversion algorithm based on the journal's format requirements. For example, the conversion unit adjusts the conversion algorithm based on the journal's format requirements. This allows the conversion unit to apply the optimal conversion algorithm depending on the journal's format requirements. The conversion algorithms include, for example, machine learning algorithms and rule-based algorithms, and their usage methods. Some or all of the above processing in the conversion unit may be performed using, for example, AI, or not using AI. For example, the conversion unit can input journal format requirement data into a generating AI and have the generating AI perform the application of the conversion algorithm.

[0053] The conversion unit can select the optimal conversion method when converting articles, taking into account the geographical distribution of journals. For example, the conversion unit selects the optimal conversion method based on the geographical distribution of journals. The conversion unit can also narrow down the scope of the conversion by considering the geographical distribution of journals. For example, the conversion unit narrows down the scope of the conversion by considering the geographical distribution of journals. The conversion unit can also improve the accuracy of the conversion by referring to the geographical distribution of journals. For example, the conversion unit improves the accuracy of the conversion by referring to the geographical distribution of journals. This allows the conversion unit to select the optimal conversion method based on the geographical distribution of journals. Geographical distribution includes definitions and considerations such as country-specific and regional distributions. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input geographical distribution data of journals into a generating AI and have the generating AI select the conversion method.

[0054] The conversion unit can improve the accuracy of the conversion by referring to related literature in the journal during the conversion of articles. For example, the conversion unit can select the optimal conversion method based on the related literature in the journal. For example, the conversion unit can select the optimal conversion method based on the related literature in the journal. The conversion unit can also narrow down the scope of the conversion by referring to related literature in the journal. For example, the conversion unit can narrow down the scope of the conversion by referring to related literature in the journal. The conversion unit can also improve the accuracy of the conversion by analyzing the related literature in the journal. For example, the conversion unit can improve the accuracy of the conversion by analyzing the related literature in the journal. This allows the conversion unit to improve the accuracy of the conversion based on related literature in the journal. Related literature includes, for example, criteria and reference methods such as citation relationships and the degree of thematic agreement. Some or all of the above processing in the conversion unit may be performed using, for example, AI, or not using AI. For example, the conversion unit can input the related literature data of the journal into a generating AI and have the generating AI perform the conversion.

[0055] The checking unit can select the optimal checking method by referring to the researcher's past checking history during the checking process. For example, the checking unit selects the optimal checking method based on the researcher's past checking history. The checking unit can also analyze the researcher's past checking history and display the most suitable checking items. The checking unit can also improve the accuracy of the check by referring to the researcher's past checking history. This allows the checking unit to select the optimal checking method based on the researcher's past checking history. Past checking history includes specific details such as the date and time of the check, the items checked, and how to refer to them. Some or all of the above-described processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the researcher's past checking history data into a generating AI and have the generating AI select the optimal checking method.

[0056] The checking unit can apply different checking methods to each category of paper during the checking process. For example, the checking unit can apply different checking methods depending on the category of the paper. For example, the checking unit can apply different checking methods depending on the category of the paper. The checking unit can also select the optimal checking method for each category of paper. For example, the checking unit can select the optimal checking method for each category of paper. The checking unit can also adjust the checking method based on the category of the paper. For example, the checking unit adjusts the checking method based on the category of the paper. This allows the checking unit to apply the optimal checking method according to the category of the paper. Categories include definitions and classifications such as academic fields and research themes. Checking methods include types and methods of use such as questionnaire surveys and interview surveys. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input paper category data into a generating AI and have the generating AI perform the application of checking methods.

[0057] The checking unit can select the optimal checking method while considering the researcher's geographical location information. For example, the checking unit selects the optimal checking method based on the researcher's geographical location information. The checking unit can also narrow down the scope of the check while considering the researcher's geographical location information. For example, the checking unit narrows down the scope of the check while considering the researcher's geographical location information. The checking unit can also improve the accuracy of the check by referring to the researcher's geographical location information. For example, the checking unit improves the accuracy of the check by referring to the researcher's geographical location information. This allows the checking unit to select the optimal checking method based on the researcher's geographical location information. Geographical location information includes, for example, specific acquisition methods and usage methods such as GPS data and IP addresses. Some or all of the above processing in the checking unit may be performed using, for example, AI, or without using AI. For example, the checking unit can input the researcher's geographical location information data into a generating AI and have the generating AI perform the selection of the checking method.

[0058] The checking unit can analyze the researcher's social media activity during the checking process and propose checking methods. For example, the checking unit can propose the most suitable checking method based on the researcher's social media activity. The checking unit can also analyze the researcher's social media activity and display the most appropriate checking items. The checking unit can also improve the accuracy of the check by referring to the researcher's social media activity. This allows the checking unit to propose the most suitable checking method based on the researcher's social media activity. Social media activity includes specific details and analysis methods such as post content, follower count, and engagement rate. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the researcher's social media activity data into a generating AI and have the generating AI execute the proposal of checking methods.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The reception system can automatically analyze the content of a paper when a researcher uploads it and extract appropriate keywords. For example, the reception system can use natural language processing technology to analyze the content of the paper and extract key keywords. The reception system can also suggest relevant journals based on the extracted keywords. For example, the reception system can suggest relevant journals based on the extracted keywords. Furthermore, the reception system can present the extracted keywords to the researcher and provide a function for modifying or adding keywords. For example, the reception system can present the extracted keywords to the researcher and provide a function for modifying or adding keywords. In this way, the reception system can extract appropriate keywords based on the content of the paper and suggest relevant journals.

[0061] The research department can conduct its research on journal format requirements while considering the journal's influencing factors and evaluations. For example, the research department can investigate the optimal format requirements based on the journal's influencing factors. The research department can also investigate format requirements while considering the journal's evaluations. For example, the research department can investigate format requirements while considering the journal's evaluations. Furthermore, the research department can comprehensively assess the journal's influencing factors and evaluations to investigate the optimal format requirements. For example, the research department comprehensively assesses the journal's influencing factors and evaluations to investigate the optimal format requirements. This allows the research department to investigate the optimal format requirements based on the journal's influencing factors and evaluations.

[0062] The conversion unit can select the optimal conversion method when converting a paper by referring to the researcher's past paper style. For example, the conversion unit selects the optimal conversion method based on the researcher's past paper style. The conversion unit can also analyze the researcher's past paper style and apply the most suitable format requirements. For example, the conversion unit analyzes the researcher's past paper style and applies the most suitable format requirements. Furthermore, the conversion unit can improve the accuracy of the conversion by referring to the researcher's past paper style. For example, the conversion unit improves the accuracy of the conversion by referring to the researcher's past paper style. This allows the conversion unit to select the optimal conversion method based on the researcher's past paper style.

[0063] The checking unit can select the optimal checking method by referring to the researcher's past checking history during the checking process. For example, the checking unit selects the optimal checking method based on the researcher's past checking history. Furthermore, the checking unit can analyze the researcher's past checking history and display the most suitable checking items. For example, the checking unit analyzes the researcher's past checking history and displays the most suitable checking items. In addition, the checking unit can improve the accuracy of the checks by referring to the researcher's past checking history. For example, the checking unit improves the accuracy of the checks by referring to the researcher's past checking history. This allows the checking unit to select the optimal checking method based on the researcher's past checking history.

[0064] The reception desk can analyze a researcher's past paper submission history and select the most suitable upload method. For example, the reception desk will prioritize suggesting upload methods the researcher has used in the past (e.g., drag and drop, file selection). The reception desk can also send notifications during specific time periods if the researcher has previously uploaded during those times. Furthermore, the reception desk can automatically select file formats the researcher has used in the past (e.g., Word, PDF). This allows the reception desk to select the most suitable upload method based on the researcher's past history.

[0065] The following briefly describes the processing flow for example form 1.

[0066] Step 1: The reception desk allows researchers to upload their papers in Word or PDF format. Researchers can upload academic papers, technical reports, review articles, etc., using drag-and-drop or a file selection dialog. The reception desk can also set file size limits, for example, setting a maximum file size of 10MB. Step 2: The selection section selects the desired journal based on the papers uploaded by the reception section. Researchers can select their desired journal from a dropdown menu, search by journal name or keywords, or filter the journals by category. Step 3: The research team examines the format of the journals selected by the selection team. The research team obtains the journal submission guidelines using web scraping and document analysis, and analyzes them using natural language processing techniques. They also save the obtained submission guidelines to a database for later reference. Step 4: The conversion unit converts the paper to conform to the format researched by the research unit. The conversion unit uses natural language processing (NLP) to analyze the submission guidelines and a generative model to regenerate the paper. For example, it converts the paper to conform to formatting requirements such as word count, title style, and reference display style. Step 5: The checking unit allows researchers to review the papers converted by the conversion unit. The checking unit provides an interface for researchers to verify the format created by the AI ​​agent system and provides the function to correct the format as needed.

[0067] (Example of form 2) An AI agent system according to an embodiment of the present invention is a system that automatically converts papers written by researchers to conform to journal formats. This AI agent system allows researchers to upload their papers in Word or PDF format and select a desired journal. The system then examines the format of the selected journal and automatically converts the word count, title style, reference display style, etc. For example, the AI ​​agent system accepts papers in Word or PDF format. Next, the AI ​​agent system allows researchers to select a desired journal. The AI ​​agent system uses web scraping and document analysis to examine the format of the selected journal. For example, the AI ​​agent system obtains submission guidelines from the journal's website. Next, the AI ​​agent system analyzes the submission guidelines using natural language processing (NLP) and regenerates the paper using a generative model (e.g., a large-scale language model). For example, the AI ​​agent system converts the paper to conform to format requirements such as word count, title style, and reference display style. Finally, the AI ​​agent system allows the researcher to check the format created by the AI ​​agent system. This significantly reduces the time and effort required for researchers to change the format of their papers, allowing them to focus on other research activities. Furthermore, the AI ​​agent system accurately understands the formatting requirements of each journal and converts them appropriately, streamlining the submission process while maintaining the quality of the paper. This allows researchers to easily submit their papers in accordance with the journal's format.

[0068] The AI ​​agent system according to this embodiment comprises a reception unit, a selection unit, a research unit, a conversion unit, and a checking unit. The reception unit uploads papers written by researchers in Word or PDF format. Papers written by researchers include, but are not limited to, academic papers, technical reports, and review articles. The reception unit uploads papers written by researchers by drag and drop, for example. The reception unit can also upload papers using a file selection dialog. Furthermore, the reception unit can set a file size limit. For example, the reception unit can set a maximum file size of 10MB. The selection unit selects the desired journal based on the papers uploaded by the reception unit. For example, the selection unit allows researchers to select the desired journal from a drop-down menu. The selection unit can also provide a journal search function. For example, the selection unit can provide a function to search by journal name or keyword. Furthermore, the selection unit can also provide a function to filter journals by category. For example, the selection unit displays journals by category such as science, technology, and medicine. The research unit examines the format of the journals selected by the selection unit. The research department can, for example, obtain journal submission guidelines using web scraping. The research department can also analyze the submission guidelines using document analysis. For example, the research department can obtain the submission guidelines from the journal's website and analyze them using natural language processing techniques. Furthermore, the research department can store the journal's submission guidelines in a database. For example, the research department can store the obtained submission guidelines in a database for later reference. The transformation department transforms the paper to conform to the format examined by the research department. The transformation department can, for example, analyze the submission guidelines using natural language processing (NLP) and regenerate the paper using a generative model. For example, the transformation department can regenerate the paper using a generative model such as a large-scale language model. The transformation department can also transform the paper to conform to formatting requirements such as character count, title style, and reference display style. For example, the transformation department can shorten the paper to conform to character limits. Title style changes include, for example, altering font size, font type, and alignment.The reference display style can be changed, for example, the citation format or the format of the bibliography. The checking unit allows researchers to check the papers converted by the conversion unit. The checking unit provides, for example, an interface for researchers to verify the format created by the AI ​​agent system. The checking unit can also provide a function for researchers to modify the format as needed. For example, the checking unit provides an editor for researchers to manually modify the format. This allows the AI ​​agent system according to the embodiment to enable researchers to easily submit papers in accordance with journal formats.

[0069] The reception desk allows researchers to upload papers in Word or PDF format. These papers include, but are not limited to, academic papers, technical reports, and review articles. The reception desk allows researchers to upload papers via drag-and-drop, for example. Alternatively, researchers can upload papers using a file selection dialog. Furthermore, the reception desk can set file size limits; for example, it can set a maximum file size of 10MB. The reception desk is designed to allow researchers to easily upload papers through its user interface. Specifically, researchers can easily upload files using the drag-and-drop function. When using the file selection dialog, researchers simply navigate to select files and click the upload button. In addition, the reception desk automatically detects the format of uploaded files and performs the appropriate processing. For example, for Word files, it extracts text and images; for PDF files, it analyzes the content page by page. This ensures that the reception desk can properly process papers regardless of the format uploaded by researchers. Furthermore, by setting file size limits, the reception desk reduces system load and achieves efficient processing. For example, setting the maximum file size to 10MB can prevent system delays caused by large files. This allows the reception desk to not only enable researchers to easily upload papers but also maintain overall system performance.

[0070] The selection section allows researchers to choose their desired journals based on the papers uploaded by the submission section. For example, researchers can select their desired journals from a dropdown menu. The selection section can also provide a journal search function, such as searching by journal name or keywords. Furthermore, it can provide a filtering function by journal category, such as displaying journals by category (e.g., science, technology, medicine). The selection section is designed to allow researchers to easily select their desired journals through its user interface. Specifically, researchers can select their desired journals from a list using a dropdown menu. When using the search function, researchers can enter journal names or keywords to find the relevant journals. When using the category filtering function, researchers can select categories such as science, technology, or medicine to display the relevant journals. This allows the selection section not only to easily select desired journals but also to efficiently search for them. Additionally, the selection section can provide detailed journal information to help researchers make their selections. For example, it can display information such as journal submission guidelines, impact factor, and past publications. This allows the selection section to provide researchers with reference information when choosing a journal they wish to review, thereby supporting them in making an appropriate selection.

[0071] The research department examines the format of the journals selected by the selection department. The research department can obtain journal submission guidelines, for example, by using web scraping. Alternatively, the research department can analyze the submission guidelines using document analysis. For example, the research department can obtain the guidelines from the journal's website and analyze them using natural language processing techniques. Furthermore, the research department can store the journal's submission guidelines in a database. For example, the research department can save the obtained submission guidelines in a database for later reference. The research department automatically obtains submission guidelines from journal websites using web scraping techniques. Specifically, it uses web scraping tools to analyze the HTML structure of the journal's website and extract the text of the submission guidelines. When using document analysis techniques, the research department uses natural language processing techniques to analyze the text of the submission guidelines and extract the necessary information. For example, it extracts information such as character limits, formatting requirements, and citation formats from the submission guidelines. This allows the research department to accurately understand the journal's submission guidelines and provide the information necessary for subsequent processing. The research department also saves the obtained submission guidelines in a database for later reference. For example, submission guidelines stored in the database can be reused by other researchers when submitting to the same journal. This allows the research department to efficiently retrieve journal submission guidelines and improve the overall efficiency of the system.

[0072] The conversion unit transforms the paper to match the format researched by the research unit. For example, the conversion unit uses natural language processing (NLP) to analyze submission guidelines and generative models to regenerate the paper. For instance, the conversion unit uses generative models such as large-scale language models to regenerate the paper. The conversion unit can also transform the paper to match formatting requirements such as character count, title style, and reference display style. For example, the conversion unit shortens the paper to meet character limits. Title style changes include, for example, font size, font type, and alignment. Reference display style changes include, for example, citation formatting and bibliography formatting. The conversion unit uses natural language processing techniques to analyze the details of submission guidelines and automatically transforms the paper's content. Specifically, it uses generative models to regenerate the paper's content and convert it to a format that meets the submission guidelines. For example, it uses generative models such as large-scale language models to regenerate the paper's content and shorten it to meet character limits. When changing the title style, the conversion unit changes the font size, font type, and alignment to convert it to a style that meets the submission guidelines. When changing the style of reference display, the conversion unit modifies the citation format and bibliography format to conform to the submission guidelines. This allows the conversion unit to automatically convert the paper to match the submission guidelines, making it easy for researchers to submit their papers. Furthermore, to improve the accuracy of the conversion process, the conversion unit regularly updates the training data of its generative model to keep up with the latest submission guidelines. This ensures that the conversion unit always provides highly accurate conversions that comply with the most up-to-date submission guidelines.

[0073] The checking section allows researchers to review papers converted by the conversion section. For example, the checking section provides an interface for researchers to verify the format created by the AI ​​agent system. It can also provide a function for researchers to modify the format as needed. For instance, the checking section provides an editor for researchers to manually correct the format. The checking section is designed to allow researchers to review converted papers and make necessary corrections through a user interface. Specifically, it provides an interface for researchers to preview the converted paper and verify the accuracy of the format. If researchers need to correct the format, the checking section provides an editor for manual correction. Using the editor, researchers can fine-tune the format details and correct them to perfectly match the submission guidelines. This provides the checking section with a flexible tool for researchers to review converted papers and make necessary corrections. Furthermore, the checking section allows researchers to save the corrections and run the conversion process again to verify the final format. This allows the checking section to support researchers in verifying the accuracy of the format and making necessary corrections before submitting their papers.

[0074] The research department can obtain journal submission guidelines using web scraping and document analysis. For example, the research department can obtain submission guidelines from journal websites using web scraping. For example, the research department can analyze web pages using the Python BeautifulSoup library and extract submission guidelines. The research department can also analyze submission guidelines using document analysis. For example, the research department can analyze submission guidelines using natural language processing techniques and extract necessary information. For example, the research department can analyze the text of the submission guidelines using an NLP library and extract information such as character count, title style, and reference display style. This allows the research department to accurately obtain journal submission guidelines. Web scraping is performed using libraries such as Python's BeautifulSoup or Scrapy. Document analysis is performed using NLP techniques or text mining techniques. Some or all of the above processes performed by the research department may be performed using AI, for example, or not using AI. For example, the research department can input text data of submission guidelines obtained through web scraping into a generating AI and have the generating AI perform an analysis of the submission guidelines.

[0075] The transformation unit can analyze submission guidelines using natural language processing and regenerate the paper using a generative model. For example, the transformation unit analyzes submission guidelines using natural language processing techniques. For example, the transformation unit analyzes submission guidelines using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The transformation unit can also regenerate the paper using a generative model. For example, the transformation unit regenerates the paper using a generative model such as a large-scale language model. For example, the transformation unit generates an abstract of the paper using a large-scale language model. This allows the transformation unit to accurately convert the paper into the journal format. Natural language processing is performed using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The generative model is performed using a model such as a large-scale language model. Some or all of the above processing in the transformation unit may be performed using AI, or not. For example, the transformation unit can input the text data of the submission guidelines into a generative AI and have the generative AI regenerate the paper.

[0076] The conversion unit can convert a paper to meet formatting requirements such as character count, title style, and reference display style. For example, the conversion unit can shorten a paper to meet character limits. For instance, it calculates the character count of each section of the paper and removes any parts that exceed the limit. The conversion unit can also change the title style. For example, it can change the font size, font type, and alignment of the title. Furthermore, the conversion unit can change the reference display style. For example, it can change the citation format and the format of the bibliography. This allows the conversion unit to accurately conform to the formatting requirements of the paper. Character limits are set based on criteria such as maximum and minimum character counts. Title styles are set based on requirements such as font size, font type, and alignment. Reference display styles are set based on requirements such as citation format and bibliography format. Some or all of the above processing in the conversion unit may be performed using AI, for example, or not. For example, the conversion unit can input the text data of a paper into a generating AI, which can then perform adjustments to the number of characters and changes to the style.

[0077] The checking unit allows researchers to check the format created by the AI ​​agent. The checking unit provides, for example, an interface for researchers to review the format created by the AI ​​agent system. For example, the checking unit provides a screen for researchers to preview the format. The checking unit can also provide a function for researchers to modify the format as needed. For example, the checking unit provides an editor for researchers to manually modify the format. This allows the checking unit to allow researchers to review the format and modify it as needed. The AI ​​agent creates the format using, for example, natural language processing techniques or generative models. Some or all of the above processing in the checking unit may be performed using, for example, AI, or not using AI. For example, the checking unit presents the format created by the generative AI to the researcher and provides an interface for the researcher to review it.

[0078] The reception desk can estimate the researcher's emotions and adjust the timing of the paper upload based on the estimated emotions. For example, if the researcher is feeling stressed, the reception desk can send a notification prompting them to upload during a time when they can relax. The reception desk can also prompt the researcher to upload immediately if they are concentrating. The reception desk can also suggest that the researcher upload after a break if they are tired. This allows the reception desk to upload the paper at the optimal time according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI or not using AI. For example, the reception desk can input researchers' emotional data into a generative AI and have the AI ​​perform emotion estimation.

[0079] The reception desk can analyze a researcher's past paper submission history and select the optimal upload method. For example, the reception desk can prioritize suggesting upload methods the researcher has used in the past (e.g., drag and drop, file selection). The reception desk can also send notifications to researchers if they have previously uploaded during specific time periods. The reception desk can also automatically select file formats the researcher has used in the past (e.g., Word, PDF). This allows the reception desk to select the optimal upload method based on the researcher's past history. Past paper submission history includes, for example, submission date and time, and the journal to which the paper was submitted. The optimal upload method is selected based on, for example, the researcher's past history. Some or all of the above processing in the reception desk may be performed using, for example, AI, or not using AI. For example, the reception department can input a researcher's past paper submission history data into a generating AI and have the AI ​​select the optimal upload method.

[0080] The reception system can filter papers upon upload based on the researcher's current research topic and areas of interest. For example, the reception system may prioritize displaying journals related to the researcher's current research topic. The reception system can also automatically apply relevant formatting requirements based on the researcher's areas of interest. The reception system can also analyze the content of the researcher's past papers and suggest relevant formatting requirements. This allows the reception system to perform optimal filtering based on the researcher's areas of interest. Research topics include definitions and classifications such as specific academic disciplines and research topics. Areas of interest include definitions and classifications such as specific technological fields and application fields. Filtering is performed based on, for example, the researcher's current research topic and areas of interest. Some or all of the above processing in the reception system may be performed using, for example, AI, or not using AI. For example, the reception desk can input data on researchers' research themes and areas of interest into a generating AI, and have the AI ​​perform filtering.

[0081] The reception desk can estimate the researcher's emotions and determine the priority of papers to upload based on the estimated emotions. For example, if the researcher is anxious, the reception desk may suggest uploading the most important papers first. The reception desk may also suggest uploading multiple papers at once if the researcher is relaxed. The reception desk may also suggest uploading papers in order from easiest to most difficult if the researcher is tired. This allows the reception desk to upload papers with the optimal priority according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the reception desk may be performed using AI, for example, or without AI. For example, the reception desk can input researchers' emotional data into a generative AI and have the AI ​​perform emotion estimation.

[0082] The reception desk can prioritize uploading highly relevant papers by considering the researcher's geographical location when they upload their papers. For example, if a researcher is in a specific region, the reception desk will prioritize the format of journals relevant to that region. For example, if a researcher is in a specific region, the reception desk will prioritize the format of journals relevant to that region. For example, if a researcher is attending an international conference, the reception desk will prioritize the format of journals recommended by that university if the researcher is affiliated with a specific university. For example, if a researcher is affiliated with a specific university, the reception desk will prioritize the format of journals recommended by that university. This allows the reception desk to upload the most relevant papers based on the researcher's geographical location. Geographical location information includes, for example, specific methods of acquisition and use such as GPS data and IP addresses. Highly relevant papers are selected based on criteria and selection methods such as the degree of agreement on research themes and citation relationships. Some or all of the above-described processes in the reception area may be performed using AI, for example, or without AI. For example, the reception area can input the geographical location data of researchers into a generating AI and have the generating AI select highly relevant papers.

[0083] The reception desk can analyze a researcher's social media activity when they upload a paper and upload relevant papers. For example, the reception desk can prioritize uploading papers that the researcher has shared on social media. The reception desk can also prioritize uploading papers related to topics that the researcher has shown interest in on social media. The reception desk can also prioritize uploading papers related to topics that the researcher's social media followers have shown interest in. This allows the reception desk to upload the most relevant papers based on the researcher's social media activity. Social media activity includes specific details and analysis methods such as post content, follower count, and engagement rate. Relevant papers are selected based on criteria and selection methods such as the degree of agreement on research themes and citation relationships. Some or all of the above processing in the reception desk may be performed using AI, for example, or not. For example, the reception desk can input researchers' social media activity data into a generative AI and have the AI ​​select relevant papers.

[0084] The selection unit can estimate the researcher's emotions and adjust the journal selection method based on the estimated emotions. For example, if the researcher is stressed, the selection unit can provide a simple interface for selecting journals. For example, if the researcher is stressed, the selection unit can provide a simple interface for selecting journals. For example, if the researcher is relaxed, the selection unit can provide detailed information for selecting journals. For example, if the researcher is relaxed, the selection unit can provide detailed information for selecting journals. For example, if the researcher is in a hurry, the selection unit can automatically suggest the most relevant journals. For example, if the researcher is in a hurry, the selection unit can automatically suggest the most relevant journals. This allows the selection unit to select journals in the most optimal way according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the researcher's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0085] The selection unit can suggest the most suitable journals by referring to the researcher's past submission history when selecting journals. For example, the selection unit can suggest highly relevant journals based on the journals the researcher has previously submitted to. For example, the selection unit can suggest highly relevant journals based on the journals the researcher has previously submitted to. The selection unit can also suggest the journal with the highest success rate based on the researcher's past submission history. For example, the selection unit can suggest the journal with the highest success rate based on the researcher's past submission history. The selection unit can also suggest the most suitable journal by analyzing the researcher's past submission history. For example, the selection unit can suggest the most suitable journal by analyzing the researcher's past submission history. This allows the selection unit to suggest the most suitable journal based on the researcher's past submission history. Past submission history includes, for example, the submission date and the journal to which it was submitted. The most suitable journal is selected based on criteria and selection methods such as the degree of match in research theme and journal influence factors. Some or all of the above processing in the selection unit may be performed using, for example, AI, or not using AI. For example, the selection unit can input a researcher's past publication history data into a generating AI and have the AI ​​suggest the most suitable journals.

[0086] The selection unit can apply different selection algorithms depending on the researcher's field of study when selecting journals. For example, the selection unit may prioritize displaying journals that are specialized in the researcher's field of study. The selection unit can also apply different selection algorithms depending on the researcher's field of study to suggest the most suitable journals. The selection unit can also make selections considering influencing factors of journals related to the researcher's field of study. This allows the selection unit to select the most suitable journals according to the researcher's field of study. The field of study includes definitions and classifications such as specific academic disciplines and research topics. The selection algorithm includes types and methods of use such as machine learning algorithms and heuristic algorithms. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input researcher field data into a generating AI and have the generating AI perform the application of the selection algorithm.

[0087] The selection unit can estimate the researcher's emotions and adjust the order of journal selection based on the estimated emotions. For example, if the researcher is anxious, the selection unit can display the most relevant journals first. The selection unit can also provide more detailed information to help the researcher make a selection if they are relaxed. The selection unit can also display the journals in an easier order if the researcher is tired. This allows the selection unit to select journals in the optimal order according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input the researcher's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0088] The selection unit can make selections by considering the influence factors and evaluations of journals. For example, the selection unit can suggest the most suitable journal based on the influence factors of the journals. For example, the selection unit can suggest the most suitable journal for researchers by considering the evaluations of the journals. For example, the selection unit can suggest the most suitable journal for researchers by comprehensively considering the influence factors and evaluations of the journals. For example, the selection unit can suggest the most suitable journal by comprehensively considering the influence factors and evaluations of the journals. In this way, the selection unit can select the most suitable journal based on the influence factors and evaluations of the journals. Influence factors include definitions and evaluation methods such as impact factor and citation count. Evaluation includes criteria and methods such as peer review results and journal rankings. Some or all of the above processing in the selection unit may be performed using AI, for example, or without AI. For example, the selection unit can input journal influence factor and evaluation data into a generating AI and have the generating AI select the most suitable journal.

[0089] The selection function can prioritize displaying journals recommended by the researcher's affiliated institution when selecting journals. For example, the selection function can prioritize displaying journals recommended by the researcher's affiliated institution. The selection function can also suggest the most suitable journal based on the recommended journals of the researcher's affiliated institution. The selection function can also narrow down the options by considering the recommended journals of the researcher's affiliated institution. For example, the selection function can narrow down the options by considering the recommended journals of the researcher's affiliated institution. In this way, the selection function can select the most suitable journal by prioritizing the display of journals recommended by the researcher's affiliated institution. Journals recommended by the affiliated institution are selected based on criteria and selection methods such as the institution's research policy and past recommendation history. Some or all of the above processing in the selection function may be performed using AI, for example, or without AI. For example, the selection unit can input recommended journal data from the researcher's affiliated institution into the generating AI, allowing the AI ​​to select the most suitable journal.

[0090] The research department can estimate the researcher's emotions and adjust the criteria for the format survey based on the estimated emotions. For example, if the researcher is stressed, the research department can conduct a simple format survey. For example, if the researcher is stressed, the research department can conduct a simple format survey. For example, if the researcher is relaxed, the research department can conduct a detailed format survey. For example, if the researcher is relaxed, the research department can conduct a detailed format survey. For example, if the researcher is in a hurry, the research department can prioritize the most important format requirements. For example, if the researcher is in a hurry, the research department can prioritize the most important format requirements. This allows the research department to conduct the format survey with the most appropriate criteria depending on the researcher's emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research department may be performed using AI, for example, or not using AI. For example, the research department can input researchers' emotional data into a generative AI and have the AI ​​perform emotion estimation.

[0091] The research department can improve the accuracy of its research by referring to the magazine's past format change history during format research. For example, the research department can investigate the latest format requirements based on the magazine's past format change history. The research department can also analyze the magazine's format change history and prioritize investigating the most important changes. The research department can also improve the accuracy of its research by referring to the magazine's format change history. For example, the research department can improve the accuracy of its research by referring to the magazine's format change history. This allows the research department to improve the accuracy of its research based on the magazine's past format change history. The format change history includes specific details such as the date and time of change and the content of the change, as well as how to refer to it. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input the magazine's past format change history data into a generating AI and have the generating AI perform the task of improving the accuracy of the research.

[0092] The research department can apply different research methods to each journal category when conducting format research. For example, the research department can apply different research methods depending on the journal category. For example, the research department can apply different research methods depending on the journal category. The research department can also select the optimal format research method for each journal category. For example, the research department can select the optimal format research method for each journal category. The research department can also adjust the research method based on the journal category. For example, the research department can adjust the research method based on the journal category. This allows the research department to apply the optimal research method according to the journal category. Categories include definitions and classifications such as academic fields and research themes. Research methods include types and methods of use such as questionnaire surveys and interview surveys. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input journal category data into a generating AI and have the generating AI perform the application of research methods.

[0093] The research unit can estimate the researcher's emotions and adjust the order in which the results of the format survey are displayed based on the estimated emotions. For example, if the researcher is anxious, the research unit can display the most important format requirements first. For example, if the researcher is anxious, the research unit can display the most important format requirements first. For example, if the researcher is relaxed, the research unit can display the detailed format requirements in order. For example, if the researcher is tired, the research unit can display the simpler format requirements first. For example, if the researcher is tired, the research unit can display the simpler format requirements first. In this way, the research unit can display the results of the format survey in the optimal order according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the research unit may be performed using AI, for example, or without AI. For example, the research department can input researchers' emotional data into a generative AI and have the AI ​​perform emotion estimation.

[0094] The research department can conduct format research while considering the geographical distribution of magazines. For example, the research department can investigate optimal format requirements based on the geographical distribution of magazines. The research department can also narrow down the scope of the research while considering the geographical distribution of magazines. For example, the research department can narrow down the scope of the research while considering the geographical distribution of magazines. The research department can also improve the accuracy of the research by referring to the geographical distribution of magazines. For example, the research department can improve the accuracy of the research by referring to the geographical distribution of magazines. This allows the research department to conduct optimal format research based on the geographical distribution of magazines. Geographical distribution includes definitions and methods of consideration such as country-specific and regional distributions. Some or all of the above processing in the research department may be performed using AI, for example, or without AI. For example, the research department can input geographical distribution data of magazines into a generating AI and have the generating AI perform the research.

[0095] The research department can improve the accuracy of its research by referring to relevant literature in journals during format research. For example, the research department can investigate the optimal format requirements based on relevant literature in journals. The research department can also narrow down the scope of its research by referring to relevant literature in journals. For example, the research department can narrow down the scope of its research by referring to relevant literature in journals. The research department can also improve the accuracy of its research by analyzing relevant literature in journals. For example, the research department can improve the accuracy of its research by analyzing relevant literature in journals. This allows the research department to improve the accuracy of its research based on relevant literature in journals. Relevant literature includes criteria and reference methods such as citation relationships and the degree of thematic agreement. Some or all of the above processes in the research department may be performed using AI, for example, or not using AI. For example, the research department can input relevant literature data from journals into a generating AI and have the generating AI perform the research.

[0096] The transformation unit can estimate the researcher's emotions and adjust the method of transforming the paper based on the estimated emotions. For example, if the researcher is stressed, the transformation unit can apply a simple transformation method. For example, if the researcher is stressed, the transformation unit can apply a simple transformation method. For example, if the researcher is relaxed, the transformation unit can apply a detailed transformation method. For example, if the researcher is relaxed, the transformation unit can apply a detailed transformation method. For example, if the researcher is in a hurry, the transformation unit can prioritize the transformation of the most important formatting requirements. For example, if the researcher is in a hurry, the transformation unit can prioritize the transformation of the most important formatting requirements. This allows the transformation unit to transform the paper in the most optimal way according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the transformation unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the researcher's emotional data into a generating AI, allowing the AI ​​to perform emotion estimation.

[0097] The conversion unit can select the optimal conversion method by referring to the researcher's past paper style when converting a paper. For example, the conversion unit selects the optimal conversion method based on the researcher's past paper style. The conversion unit can also analyze the researcher's past paper style and apply the most suitable format requirements. The conversion unit can also improve the accuracy of the conversion by referring to the researcher's past paper style. This allows the conversion unit to select the optimal conversion method based on the researcher's past paper style. Past paper style includes specific details such as format and citation style, as well as citation methods. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the researcher's past paper style data into a generating AI and have the generating AI select the optimal conversion method.

[0098] The conversion unit can apply different conversion algorithms depending on the journal's format requirements when converting a paper. For example, the conversion unit can apply different conversion algorithms depending on the journal's format requirements. For example, the conversion unit can apply different conversion algorithms depending on the journal's format requirements. The conversion unit can also select the optimal conversion algorithm based on the journal's format requirements. For example, the conversion unit can select the optimal conversion algorithm based on the journal's format requirements. The conversion unit can also adjust the conversion algorithm based on the journal's format requirements. For example, the conversion unit adjusts the conversion algorithm based on the journal's format requirements. This allows the conversion unit to apply the optimal conversion algorithm depending on the journal's format requirements. The conversion algorithms include, for example, machine learning algorithms and rule-based algorithms, and their usage methods. Some or all of the above processing in the conversion unit may be performed using, for example, AI, or not using AI. For example, the conversion unit can input journal format requirement data into a generating AI and have the generating AI perform the application of the conversion algorithm.

[0099] The conversion unit can estimate the researcher's emotions and determine the priority of paper conversion based on the estimated emotions. For example, if the researcher is anxious, the conversion unit will prioritize converting the most important papers. The conversion unit can also convert multiple papers at once if the researcher is relaxed. The conversion unit can also convert papers in order from easiest to hardest if the researcher is tired. This allows the conversion unit to convert papers in the optimal priority according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input the researcher's emotional data into a generating AI, allowing the AI ​​to perform emotion estimation.

[0100] The conversion unit can select the optimal conversion method when converting articles, taking into account the geographical distribution of journals. For example, the conversion unit selects the optimal conversion method based on the geographical distribution of journals. The conversion unit can also narrow down the scope of the conversion by considering the geographical distribution of journals. For example, the conversion unit narrows down the scope of the conversion by considering the geographical distribution of journals. The conversion unit can also improve the accuracy of the conversion by referring to the geographical distribution of journals. For example, the conversion unit improves the accuracy of the conversion by referring to the geographical distribution of journals. This allows the conversion unit to select the optimal conversion method based on the geographical distribution of journals. Geographical distribution includes definitions and considerations such as country-specific and regional distributions. Some or all of the above processing in the conversion unit may be performed using AI, for example, or without AI. For example, the conversion unit can input geographical distribution data of journals into a generating AI and have the generating AI select the conversion method.

[0101] The conversion unit can improve the accuracy of the conversion by referring to related literature in the journal during the conversion of articles. For example, the conversion unit can select the optimal conversion method based on the related literature in the journal. For example, the conversion unit can select the optimal conversion method based on the related literature in the journal. The conversion unit can also narrow down the scope of the conversion by referring to related literature in the journal. For example, the conversion unit can narrow down the scope of the conversion by referring to related literature in the journal. The conversion unit can also improve the accuracy of the conversion by analyzing the related literature in the journal. For example, the conversion unit can improve the accuracy of the conversion by analyzing the related literature in the journal. This allows the conversion unit to improve the accuracy of the conversion based on related literature in the journal. Related literature includes, for example, criteria and reference methods such as citation relationships and the degree of thematic agreement. Some or all of the above processing in the conversion unit may be performed using, for example, AI, or not using AI. For example, the conversion unit can input the related literature data of the journal into a generating AI and have the generating AI perform the conversion.

[0102] The checking unit can estimate the researcher's emotions and adjust the checking method based on the estimated emotions. For example, if the researcher is stressed, the checking unit can apply a simple checking method. For example, if the researcher is stressed, the checking unit can apply a simple checking method. For example, if the researcher is relaxed, the checking unit can apply a detailed checking method. For example, if the researcher is relaxed, the checking unit can apply a detailed checking method. For example, if the researcher is in a hurry, the checking unit can prioritize displaying the most important check items. For example, if the researcher is in a hurry, the checking unit can prioritize displaying the most important check items. This allows the checking unit to perform the check in the most optimal way according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the researcher's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0103] The checking unit can select the optimal checking method by referring to the researcher's past checking history during the checking process. For example, the checking unit selects the optimal checking method based on the researcher's past checking history. The checking unit can also analyze the researcher's past checking history and display the most suitable checking items. The checking unit can also improve the accuracy of the check by referring to the researcher's past checking history. This allows the checking unit to select the optimal checking method based on the researcher's past checking history. Past checking history includes specific details such as the date and time of the check, the items checked, and how to refer to them. Some or all of the above-described processes in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the researcher's past checking history data into a generating AI and have the generating AI select the optimal checking method.

[0104] The checking unit can apply different checking methods to each category of paper during the checking process. For example, the checking unit can apply different checking methods depending on the category of the paper. For example, the checking unit can apply different checking methods depending on the category of the paper. The checking unit can also select the optimal checking method for each category of paper. For example, the checking unit can select the optimal checking method for each category of paper. The checking unit can also adjust the checking method based on the category of the paper. For example, the checking unit adjusts the checking method based on the category of the paper. This allows the checking unit to apply the optimal checking method according to the category of the paper. Categories include definitions and classifications such as academic fields and research themes. Checking methods include types and methods of use such as questionnaire surveys and interview surveys. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input paper category data into a generating AI and have the generating AI perform the application of checking methods.

[0105] The checking unit can estimate the researcher's emotions and determine the priority of checks based on the estimated emotions. For example, if the researcher is anxious, the checking unit will prioritize displaying the most important check items. For example, if the researcher is anxious, the checking unit will prioritize displaying the most important check items. Also, if the researcher is relaxed, the checking unit can display detailed check items in order. For example, if the researcher is relaxed, the checking unit can display detailed check items in order. Also, if the researcher is tired, the checking unit can display simpler check items first. For example, if the researcher is tired, the checking unit can display simpler check items first. In this way, the checking unit can perform checks with the optimal priority according to the researcher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the researcher's emotional data into a generating AI and have the generating AI perform emotion estimation.

[0106] The checking unit can select the optimal checking method while considering the researcher's geographical location information. For example, the checking unit selects the optimal checking method based on the researcher's geographical location information. The checking unit can also narrow down the scope of the check while considering the researcher's geographical location information. For example, the checking unit narrows down the scope of the check while considering the researcher's geographical location information. The checking unit can also improve the accuracy of the check by referring to the researcher's geographical location information. For example, the checking unit improves the accuracy of the check by referring to the researcher's geographical location information. This allows the checking unit to select the optimal checking method based on the researcher's geographical location information. Geographical location information includes, for example, specific acquisition methods and usage methods such as GPS data and IP addresses. Some or all of the above processing in the checking unit may be performed using, for example, AI, or without using AI. For example, the checking unit can input the researcher's geographical location information data into a generating AI and have the generating AI perform the selection of the checking method.

[0107] The checking unit can analyze the researcher's social media activity during the checking process and propose checking methods. For example, the checking unit can propose the most suitable checking method based on the researcher's social media activity. The checking unit can also analyze the researcher's social media activity and display the most appropriate checking items. The checking unit can also improve the accuracy of the check by referring to the researcher's social media activity. This allows the checking unit to propose the most suitable checking method based on the researcher's social media activity. Social media activity includes specific details and analysis methods such as post content, follower count, and engagement rate. Some or all of the above processing in the checking unit may be performed using AI, for example, or without AI. For example, the checking unit can input the researcher's social media activity data into a generating AI and have the generating AI execute the proposal of checking methods.

[0108] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0109] The reception system can automatically analyze the content of a paper when a researcher uploads it and extract appropriate keywords. For example, the reception system can use natural language processing technology to analyze the content of the paper and extract key keywords. The reception system can also suggest relevant journals based on the extracted keywords. For example, the reception system can suggest relevant journals based on the extracted keywords. Furthermore, the reception system can present the extracted keywords to the researcher and provide a function for modifying or adding keywords. For example, the reception system can present the extracted keywords to the researcher and provide a function for modifying or adding keywords. In this way, the reception system can extract appropriate keywords based on the content of the paper and suggest relevant journals.

[0110] The research department can conduct its research on journal format requirements while considering the journal's influencing factors and evaluations. For example, the research department can investigate the optimal format requirements based on the journal's influencing factors. The research department can also investigate format requirements while considering the journal's evaluations. For example, the research department can investigate format requirements while considering the journal's evaluations. Furthermore, the research department can comprehensively assess the journal's influencing factors and evaluations to investigate the optimal format requirements. For example, the research department comprehensively assesses the journal's influencing factors and evaluations to investigate the optimal format requirements. This allows the research department to investigate the optimal format requirements based on the journal's influencing factors and evaluations.

[0111] The conversion unit can select the optimal conversion method when converting a paper by referring to the researcher's past paper style. For example, the conversion unit selects the optimal conversion method based on the researcher's past paper style. The conversion unit can also analyze the researcher's past paper style and apply the most suitable format requirements. For example, the conversion unit analyzes the researcher's past paper style and applies the most suitable format requirements. Furthermore, the conversion unit can improve the accuracy of the conversion by referring to the researcher's past paper style. For example, the conversion unit improves the accuracy of the conversion by referring to the researcher's past paper style. This allows the conversion unit to select the optimal conversion method based on the researcher's past paper style.

[0112] The checking unit can estimate the researcher's emotions and adjust the checking method based on the estimated emotions. For example, if the researcher is stressed, the checking unit will apply a simpler checking method. Conversely, if the researcher is relaxed, the checking unit can apply a more detailed checking method. Furthermore, if the researcher is in a hurry, the checking unit can prioritize displaying the most important check items. This allows the checking unit to perform the check in the most appropriate way according to the researcher's emotions.

[0113] The reception desk can estimate the researcher's emotions and adjust the timing of paper uploads based on those estimates. For example, if the reception desk is stressed, it can send a notification encouraging the researcher to upload during a time when they can relax. It can also encourage the researcher to upload immediately if they are focused. Furthermore, if the researcher is tired, it can suggest uploading after a break. This allows the reception desk to upload papers at the optimal time based on the researcher's emotions.

[0114] The selection process can estimate the researcher's emotions and adjust its journal selection method based on those emotions. For example, if the researcher is stressed, the selection process can provide a simple interface for selecting journals. Alternatively, if the researcher is relaxed, the selection process can provide more detailed information for journal selection. Furthermore, if the researcher is in a hurry, the selection process can automatically suggest the most relevant journals. This allows the selection process to select journals in the most appropriate way based on the researcher's emotions.

[0115] The research department can estimate the researcher's emotions and adjust the criteria for the format survey based on those estimates. For example, if the research department is stressed, it can conduct a simple format survey. Conversely, if the research department is relaxed, it can conduct a more detailed format survey. For example, if the research department is relaxed, it can conduct a more detailed format survey. Furthermore, if the research department is in a hurry, it can prioritize the most important format requirements. For example, if the research department is in a hurry, it will prioritize the most important format requirements. This allows the research department to conduct the format survey with the most appropriate criteria depending on the researcher's emotions.

[0116] The conversion unit can estimate the researcher's emotions and adjust the method of converting the paper based on the estimated emotions. For example, if the researcher is stressed, the conversion unit will apply a simple conversion method. Alternatively, if the researcher is relaxed, the conversion unit can apply a more detailed conversion method. Furthermore, if the researcher is in a hurry, the conversion unit can prioritize the most important formatting requirements. This allows the conversion unit to convert the paper in the most optimal way according to the researcher's emotions.

[0117] The checking unit can select the optimal checking method by referring to the researcher's past checking history during the checking process. For example, the checking unit selects the optimal checking method based on the researcher's past checking history. Furthermore, the checking unit can analyze the researcher's past checking history and display the most suitable checking items. For example, the checking unit analyzes the researcher's past checking history and displays the most suitable checking items. In addition, the checking unit can improve the accuracy of the checks by referring to the researcher's past checking history. For example, the checking unit improves the accuracy of the checks by referring to the researcher's past checking history. This allows the checking unit to select the optimal checking method based on the researcher's past checking history.

[0118] The reception desk can analyze a researcher's past paper submission history and select the most suitable upload method. For example, the reception desk will prioritize suggesting upload methods the researcher has used in the past (e.g., drag and drop, file selection). The reception desk can also send notifications during specific time periods if the researcher has previously uploaded during those times. Furthermore, the reception desk can automatically select file formats the researcher has used in the past (e.g., Word, PDF). This allows the reception desk to select the most suitable upload method based on the researcher's past history.

[0119] The following briefly describes the processing flow for example form 2.

[0120] Step 1: The reception desk allows researchers to upload their papers in Word or PDF format. Researchers can upload academic papers, technical reports, review articles, etc., using drag-and-drop or a file selection dialog. The reception desk can also set file size limits, for example, setting a maximum file size of 10MB. Step 2: The selection section selects the desired journal based on the papers uploaded by the reception section. Researchers can select their desired journal from a dropdown menu, search by journal name or keywords, or filter the journals by category. Step 3: The research team examines the format of the journals selected by the selection team. The research team obtains the journal submission guidelines using web scraping and document analysis, and analyzes them using natural language processing techniques. They also save the obtained submission guidelines to a database for later reference. Step 4: The conversion unit converts the paper to conform to the format researched by the research unit. The conversion unit uses natural language processing (NLP) to analyze the submission guidelines and a generative model to regenerate the paper. For example, it converts the paper to conform to formatting requirements such as word count, title style, and reference display style. Step 5: The checking unit allows researchers to review the papers converted by the conversion unit. The checking unit provides an interface for researchers to verify the format created by the AI ​​agent system and provides the function to correct the format as needed.

[0121] 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.

[0122] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0123] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0124] Each of the multiple elements described above, including the reception unit, selection unit, investigation unit, conversion unit, and checking unit, is implemented by, for example, at least one of the smart device 14 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the smart device 14 and uploads the paper written by the researcher. The selection unit is implemented by, for example, the control unit 46A of the smart device 14 and selects the journal desired by the researcher. The investigation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and checks the format of the selected journal. The conversion unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and converts the paper to match the format. The checking unit is implemented by, for example, the control unit 46A of the smart device 14 and checks the converted paper by the researcher. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0125] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0126] 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.

[0127] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0128] 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.

[0129] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0130] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0131] 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.

[0132] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0133] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0134] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0135] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0136] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0137] 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.

[0138] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0139] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0140] Each of the multiple elements described above, including the reception unit, selection unit, investigation unit, conversion unit, and checking unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit is implemented by the control unit 46A of the smart glasses 214 and uploads the paper written by the researcher. The selection unit is implemented, for example, by the control unit 46A of the smart glasses 214 and selects the journal desired by the researcher. The investigation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and checks the format of the selected journal. The conversion unit is implemented, for example, by the specific processing unit 290 of the data processing device 12 and converts the paper to match the format. The checking unit is implemented, for example, by the control unit 46A of the smart glasses 214 and checks the converted paper by the researcher. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0141] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0142] 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.

[0143] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0144] 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.

[0145] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0146] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0147] 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.

[0148] 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.

[0149] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0150] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0151] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0152] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0153] 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.

[0154] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0155] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0156] Each of the multiple elements described above, including the reception unit, selection unit, investigation unit, conversion unit, and checking unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the headset terminal 314 and uploads the paper written by the researcher. The selection unit is implemented by, for example, the control unit 46A of the headset terminal 314 and selects the journal desired by the researcher. The investigation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and checks the format of the selected journal. The conversion unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and converts the paper to match the format. The checking unit is implemented by, for example, the control unit 46A of the headset terminal 314 and checks the converted paper by the researcher. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0157] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0158] 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.

[0159] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0160] 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.

[0161] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0162] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0163] 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.

[0164] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0165] 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.

[0166] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0167] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0168] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0169] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0170] 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.

[0171] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0172] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0173] Each of the multiple elements described above, including the reception unit, selection unit, investigation unit, conversion unit, and checking unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the reception unit is implemented by the control unit 46A of the robot 414 and uploads the paper written by the researcher. The selection unit is implemented by, for example, the control unit 46A of the robot 414 and selects the journal desired by the researcher. The investigation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and checks the format of the selected journal. The conversion unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and converts the paper to match the format. The checking unit is implemented by, for example, the control unit 46A of the robot 414 and checks the converted paper by the researcher. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0174] 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.

[0175] Figure 9 shows the 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.

[0176] 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.

[0177] 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.

[0178] 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, and motorcycles, 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 based, for example, 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.

[0179] 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."

[0180] 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.

[0181] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0190] 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 other things 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.

[0191] 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 to be incorporated by reference.

[0192] (Note 1) A reception area where researchers upload papers in Word or PDF format, A selection unit that selects a desired journal based on the papers uploaded by the aforementioned reception unit, A research unit that examines the format of the magazine selected by the aforementioned selection unit, A conversion unit that converts the paper to match the format investigated by the aforementioned research unit, The system comprises a checking unit in which researchers check the papers converted by the conversion unit, A system characterized by the following features. (Note 2) The aforementioned investigation department, Obtain journal submission guidelines using web scraping and document analysis. The system described in Appendix 1, characterized by the features described herein. (Note 3) The conversion unit is We use natural language processing to analyze submission guidelines and generative models to regenerate the paper. The system described in Appendix 1, characterized by the features described herein. (Note 4) The conversion unit is Convert the paper to meet formatting requirements such as word count, title style, and reference display style. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned checking unit is Researchers check the format created by the AI ​​agent. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned reception unit is We estimate researchers' sentiments and adjust the timing of paper uploads based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned reception unit is Analyze the researcher's past paper submission history to select the optimal upload method. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned reception unit is When uploading papers, filtering is performed based on the researcher's current research topic and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned reception unit is It estimates researchers' sentiments and prioritizes papers to upload based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned reception unit is When uploading papers, the system prioritizes uploading highly relevant papers by considering the researcher's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned reception unit is When uploading a paper, the system analyzes the researcher's social media activity and uploads relevant papers. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned selection unit is We estimate researchers' sentiments and adjust the journal selection method based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned selection unit is When selecting a journal, we suggest the most suitable journal by referring to the researcher's past publication history. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned selection unit is When selecting journals, different selection algorithms are applied depending on the researcher's field of study. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned selection unit is We estimate researchers' sentiments and adjust the order of journal selection based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned selection unit is When selecting a magazine, consider its influencing factors and evaluations. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned selection unit is When selecting a journal, prioritize displaying journals recommended by the researcher's affiliated institution. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned investigation department, We estimate the researchers' sentiments and adjust the criteria for the survey format based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned investigation department, When conducting a format survey, we improve the accuracy of the survey by referring to the magazine's past format change history. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned investigation department, When conducting format research, different research methods are applied to each magazine category. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned investigation department, The system estimates the researchers' sentiments and adjusts the order in which the results of the format survey are displayed based on the estimated researchers' sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned investigation department, When conducting a format survey, the geographical distribution of magazines should be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned investigation department, When conducting a format search, referencing relevant literature in journals can improve the accuracy of the search. The system described in Appendix 1, characterized by the features described herein. (Note 24) The conversion unit is We estimate the sentiments of researchers and adjust the method of converting papers based on those estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 25) The conversion unit is When converting a paper, the optimal conversion method is selected by referring to the researcher's past paper style. The system described in Appendix 1, characterized by the features described herein. (Note 26) The conversion unit is When converting a paper, different conversion algorithms are applied depending on the journal's formatting requirements. The system described in Appendix 1, characterized by the features described herein. (Note 27) The conversion unit is The system estimates researchers' sentiments and determines the priority of paper conversion based on these estimated sentiments. The system described in Appendix 1, characterized by the features described herein. (Note 28) The conversion unit is When converting research papers, the optimal conversion method is selected considering the geographical distribution of journals. The system described in Appendix 1, characterized by the features described herein. (Note 29) The conversion unit is When converting papers, we improve the accuracy of the conversion by referring to related literature in the journal. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned checking unit is We estimate the researchers' emotions and adjust the checking method based on the estimated emotions of the researchers. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned checking unit is During the check, the optimal check method is selected by referring to the researcher's past check history. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned checking unit is During the review process, different review methods are applied to each category of paper. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned checking unit is The system estimates the researchers' emotions and prioritizes checks based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned checking unit is During the check, the most suitable check method will be selected, taking into account the researcher's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned checking unit is During the check, we analyze the researcher's social media activity and propose methods for checking. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0193] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A reception area where researchers upload papers in Word or PDF format, A selection unit that selects a desired journal based on the papers uploaded by the aforementioned reception unit, A research unit that examines the format of the magazine selected by the aforementioned selection unit, A conversion unit that converts the paper to match the format investigated by the aforementioned research unit, The system comprises a checking unit in which researchers check the papers converted by the conversion unit, A system characterized by the following features.

2. The aforementioned investigation department, Obtain journal submission guidelines using web scraping and document analysis. The system according to feature 1.

3. The conversion unit is We use natural language processing to analyze submission guidelines and generative models to regenerate the paper. The system according to feature 1.

4. The conversion unit is Convert the paper to meet formatting requirements such as word count, title style, and reference display style. The system according to feature 1.

5. The aforementioned checking unit is Researchers check the format created by the AI ​​agent. The system according to feature 1.

6. The aforementioned reception unit is We estimate researchers' sentiments and adjust the timing of paper uploads based on those estimated sentiments. The system according to feature 1.

7. The aforementioned reception unit is Analyze the researcher's past paper submission history to select the optimal upload method. The system according to feature 1.

8. The aforementioned reception unit is When uploading papers, filtering is performed based on the researcher's current research topic and areas of interest. The system according to feature 1.

Images