system

Abstract

The system according to the embodiment aims to quickly and accurately generate summaries of published papers and technical reports, appropriately classify them, and share them. [Solution] A system according to an embodiment includes a reception unit, a generation unit, a classification unit, and a posting unit. The reception unit inputs published papers or technical reports. The generation unit analyzes the papers or technical reports input by the reception unit and generates summaries. The classification unit classifies the summaries generated by the generation unit into categories. The posting unit posts the summaries classified by the classification unit on an intranet.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have faced challenges in quickly and accurately generating summaries of published papers and technical reports, and then appropriately categorizing and sharing them.

[0005] The system according to the embodiment aims to quickly and accurately generate summaries of published papers and technical reports, appropriately classify them, and share them. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a generation unit, a classification unit, and a posting unit. The reception unit inputs published papers or technical reports. The generation unit analyzes the papers or technical reports input by the reception unit and generates summaries. The classification unit classifies the summaries generated by the generation unit into categories. The posting unit posts the summaries classified by the classification unit on an intranet. [Effects of the Invention]

[0007] The system according to the embodiment can quickly and accurately generate summaries of published papers and technical reports, appropriately categorize them, and share them. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A technical information summarization system according to an embodiment of the present invention uses a generative AI to automatically summarize selected research and cutting-edge technology presentations, making them easily accessible on an intranet. This system inputs published papers and technical reports into the generative AI, analyzes their content, and generates summaries. The generated summaries are then categorized and posted on the intranet. This allows employees to easily grasp the latest technical information and develop a perspective on new business ventures. For example, published papers and technical reports are input into the generative AI. The format of the papers and reports is not important, and various formats, including PDF and text files, are supported. For example, the generative AI can analyze papers and technical reports written in English. The generative AI then analyzes the content of the input paper or technical report. The generative AI uses natural language processing technology to extract key points from the paper or report and generate a summary. For example, it focuses on analyzing the paper's abstract and conclusion to extract important information. The generated summaries are then classified into categories, such as AI technology, biotechnology, and energy technology. This allows employees to easily find summaries related to their interests and work. Finally, the generated summaries are posted on the intranet. Employees can easily view the latest technical information by accessing the intranet. For example, a list of summaries by category is displayed on the intranet, and by clicking on a summary, they can view the detailed content. This allows employees to easily grasp the latest technical information and develop a perspective on new business ventures. For example, by understanding the latest trends in AI technology, they can get ideas for new AI-related businesses. Also, by learning about the latest research in biotechnology, they can explore the possibility of new medical-related businesses. In this way, the technical information summarization system allows employees to quickly and efficiently grasp the latest technical information and develop a perspective on new business ventures.

[0029] A technical information summarization system according to an embodiment includes a receiving unit, a generating unit, a classification unit, and a publishing unit. The receiving unit inputs published papers or technical reports. Published papers or technical reports include, but are not limited to, academic papers, technical reports, and white papers. The receiving unit can receive papers or technical reports in various formats, such as PDF, text, and image formats. The generating unit uses a generation AI to analyze the papers or technical reports input by the receiving unit and generate summaries. The generating unit extracts key points from the papers or reports using natural language processing technology, for example, to generate summaries. The generating unit analyzes the contents of the papers or reports using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The generating unit can also focus on analyzing the abstract and conclusion of the papers to extract important information. The classification unit classifies the summaries generated by the generating unit into categories. The classification unit classifies the summaries into categories such as AI technology, biotechnology, and energy technology. The classification unit can classify abstracts based on criteria such as technical field, application field, and research theme. The posting unit posts the abstracts classified by the classification unit on an intranet. The posting unit can, for example, display a list of summaries by category on the intranet, allowing users to click on a summary to view detailed content. The posting unit can provide display formats such as a list view, a detailed view, and a search function. As a result, the technical information summarization system according to the embodiment automatically summarizes published papers and technical reports, allowing them to be easily viewed on the intranet. This allows employees to quickly and efficiently grasp the latest technical information. Some or all of the above-described processing by the generation unit may be performed using, for example, a generative AI. For example, the generation unit can generate summaries using a generative AI model that takes papers and technical reports as input and outputs summaries. As a result, the generation unit can efficiently extract key points from papers and reports using natural language processing technology and generate summaries. As a result, the technical information summarization system according to the embodiment automatically summarizes published papers and technical reports, allowing them to be easily viewed on the intranet.

[0030] The generation unit can use natural language processing technology to extract the main points of a paper or report and generate a summary. The generation unit can extract the main points of a paper or report using, for example, morphological analysis. For example, the generation unit can use morphological analysis to divide a sentence into words and analyze the part of speech of each word. The generation unit can also extract the main points of a paper or report using grammatical analysis. For example, the generation unit can use grammatical analysis to analyze the structure of a sentence and clarify the relationships between subjects, predicates, objects, etc. The generation unit can also extract the main points of a paper or report using semantic analysis. For example, the generation unit can use semantic analysis to analyze the meaning of a sentence and extract important information. In this way, the generation unit can efficiently extract the main points of a paper or report and generate a summary using natural language processing technology. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generative AI. For example, the generation unit can generate a summary using a generative AI model that takes a paper or technical report as input and outputs a summary. This allows the generation unit to use natural language processing technology to efficiently extract the main points of a paper or report and generate a summary.

[0031] The generation unit can focus its analysis on the abstract and conclusion of a paper to extract important information. The generation unit, for example, focuses its analysis on the abstract of a paper. For example, the generation unit extracts keywords contained in the abstract of a paper to identify important information. The generation unit can also focus its analysis on the conclusion of a paper. For example, the generation unit extracts key points contained in the conclusion of a paper to identify important information. The generation unit can also analyze a combination of the abstract and conclusion of a paper. For example, the generation unit integrates information from the abstract and conclusion to extract important information. This allows the generation unit to focus its analysis on the abstract and conclusion of a paper to efficiently extract important information. Some or all of the above-described processing in the generation unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the generation unit can extract important information using a generative AI model that inputs the abstract and conclusion of a paper and outputs important information. This allows the generation unit to focus its analysis on the abstract and conclusion of the paper and efficiently extract important information.

[0032] The classification unit can classify abstracts into categories of AI technology, biotechnology, and energy technology. The classification unit, for example, classifies abstracts into the AI ​​technology category. For example, the classification unit analyzes keywords included in the abstracts to identify abstracts related to AI technology. The classification unit can also classify abstracts into the biotechnology category. For example, the classification unit analyzes keywords included in the abstracts to identify abstracts related to biotechnology. The classification unit can also classify abstracts into the energy technology category. For example, the classification unit analyzes keywords included in the abstracts to identify abstracts related to energy technology. As a result, the classification unit can classify abstracts into the AI ​​technology, biotechnology, and energy technology categories. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can classify abstracts using a generative AI model that receives abstracts as input and outputs categories. As a result, the classification unit can classify abstracts into the AI ​​technology, biotechnology, and energy technology categories.

[0033] The posting unit can display a list of summaries by category on the intranet, allowing detailed summary content to be confirmed by clicking on them. The posting unit, for example, displays the list of summaries by category on the intranet. For example, the posting unit displays a list of summaries by category, such as AI technology, biotechnology, and energy technology. The posting unit can also display detailed summary content by clicking on each item in the list of summaries. For example, the posting unit can display detailed summary content in a pop-up window when an item in the list of summaries is clicked. The posting unit can also display detailed summary content in a new page when an item in the list of summaries is clicked. In this way, the posting unit can display a list of summaries by category on the intranet, allowing detailed summary content to be confirmed by clicking on it. Some or all of the above-described processing by the posting unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the posting unit can display detailed summary content using a generation AI model that inputs the list of summaries and outputs detailed summary content. In this way, the posting unit can display a list of summaries by category on the intranet, allowing detailed summary content to be confirmed by clicking on it.

[0034] When accepting papers or technical reports, the reception unit can analyze the user's past submission history and select the optimal reception method. For example, the reception unit analyzes the format of papers previously submitted by the user and recommends submitting them in the same format. For example, the reception unit analyzes the format of papers previously submitted by the user and recommends submitting them in the same format. The reception unit can also analyze the content of papers previously submitted by the user and prioritize accepting papers on related topics. For example, the reception unit can analyze the content of papers previously submitted by the user and prioritize accepting papers on related topics. The reception unit can also suggest an optimal submission time based on the user's past submission history. For example, the reception unit analyzes the user's past submission history and suggests an optimal submission time. This allows the reception unit to select the optimal reception method by analyzing the user's past submission history, enabling efficient reception. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can select the optimal reception method using an AI model that inputs the user's past submission history and outputs the optimal reception method. This allows the reception unit to analyze the user's past submission history to select the most appropriate reception method, enabling efficient reception.

[0035] When receiving papers or technical reports, the reception unit can filter them based on the user's current research topic or field of interest. For example, the reception unit prioritizes receiving papers related to the user's current research topic. For example, the reception unit prioritizes receiving papers containing keywords related to the user's current research topic. The reception unit can also filter related technical reports based on the user's field of interest. For example, the reception unit filters technical reports containing keywords related to the user's field of interest. The reception unit can also prioritize receiving papers containing related keywords based on the user's research topic. For example, the reception unit prioritizes receiving papers containing keywords related to the user's research topic. In this way, the reception unit can prioritize receiving highly relevant materials by filtering based on the user's research topic or field of interest. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the user's research topic or field of interest and outputs related materials. This allows the reception unit to perform filtering based on the user's research theme or field of interest, allowing it to preferentially receive highly relevant materials.

[0036] When accepting papers or technical reports, the reception unit can prioritize accepting highly relevant materials by taking into account the user's geographical location information. For example, if the user is in a specific region, the reception unit prioritizes accepting papers related to that region. For example, if the user is in a specific region, the reception unit prioritizes accepting papers containing keywords related to that region. Furthermore, if the user is overseas, the reception unit can prioritize accepting international technical reports. For example, if the user is overseas, the reception unit prioritizes accepting international technical reports. Furthermore, if the user is in a specific city, the reception unit can prioritize accepting research related to that city. For example, if the user is in a specific city, the reception unit prioritizes accepting research containing keywords related to that city. In this way, the reception unit can prioritize accepting highly relevant materials by taking the user's geographical location information into account. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can prioritize accepting highly relevant materials using an AI model that inputs the user's geographical location information and outputs related materials. This allows the reception unit to give priority to receiving highly relevant materials by taking into account the user's geographical location information.

[0037] The reception unit can analyze the user's social media activity and receive related materials when receiving a paper or technical report. For example, the reception unit prioritizes receiving papers shared by the user on social media. For example, the reception unit prioritizes receiving papers shared by the user on social media. The reception unit can also prioritize receiving papers by researchers the user follows on social media. For example, the reception unit prioritizes receiving papers by researchers the user follows on social media. The reception unit can also prioritize receiving technical reports in which the user has shown interest on social media. For example, the reception unit prioritizes receiving technical reports in which the user has shown interest on social media. In this way, the reception unit can analyze the user's social media activity and prioritize receiving highly relevant materials. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can receive related materials using an AI model that inputs the user's social media activity and outputs related materials. In this way, the reception unit can analyze the user's social media activity and prioritize receiving highly relevant materials.

[0038] When generating a summary, the generation unit can adjust the level of detail of the summary based on the importance of the paper or technical report. For example, the generation unit generates a detailed summary for a paper with high importance. For example, the generation unit generates a detailed summary for a paper with high importance. The generation unit can also generate a concise summary for a paper with low importance. For example, the generation unit generates a concise summary for a paper with low importance. The generation unit can also generate a moderately detailed summary for a paper with medium importance. For example, the generation unit generates a moderately detailed summary for a paper with medium importance. In this way, the generation unit can generate an appropriate summary by adjusting the level of detail of the summary based on the importance of the paper or technical report. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI. For example, the generation unit can adjust the level of detail of the summary using a generation AI model that inputs the importance of the paper or technical report and outputs the level of detail of the summary. In this way, the generation unit can generate an appropriate summary by adjusting the level of detail of the summary based on the importance of the paper or technical report.

[0039] When generating a summary, the generation unit can apply different summarization algorithms depending on the category of the paper or technical report. For example, for a paper on AI technology, the generation unit generates a summary using a specific algorithm. For example, the generation unit generates a summary using a specific summarization algorithm for a paper on AI technology. The generation unit can also generate a summary using a different algorithm for a paper on biotechnology. For example, the generation unit can generate a summary using a different summarization algorithm for a paper on biotechnology. The generation unit can also generate a summary using yet another algorithm for a paper on energy technology. For example, the generation unit can generate a summary using yet another summarization algorithm for a paper on energy technology. In this way, the generation unit can generate more appropriate summaries by applying different summarization algorithms depending on the category of the paper or technical report. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generative AI. For example, the generation unit can apply a summarization algorithm using a generative AI model that inputs the category of the paper or technical report and outputs a summarization algorithm. In this way, the generation unit can generate more appropriate summaries by applying different summarization algorithms depending on the category of the paper or technical report.

[0040] When generating summaries, the generation unit can determine the priority of summaries based on the submission date of the paper or technical report. For example, the generation unit prioritizes summaries of recently submitted papers. For example, the generation unit prioritizes generating summaries for recently submitted papers. The generation unit can also postpone papers that were submitted recently. For example, the generation unit postpones generating summaries for recently submitted papers. The generation unit can also moderately summarize papers that were submitted recently. For example, the generation unit generates moderate summaries for papers that were submitted recently. In this way, the generation unit can prioritize summaries of the latest information by determining the priority of summaries based on the submission date of the paper or technical report. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can determine the priority of summaries using a generation AI model that inputs the submission date of the paper or technical report and outputs the priority of summaries. This allows the generation unit to prioritize summaries based on the submission date of papers and technical reports, allowing the latest information to be summarized first.

[0041] When generating summaries, the generation unit can adjust the order of summaries based on the relevance of papers or technical reports. The generation unit, for example, prioritizes summaries of highly relevant papers. For example, the generation unit prioritizes generating summaries for highly relevant papers. The generation unit can also postpone generating summaries for less relevant papers. For example, the generation unit postpones generating summaries for less relevant papers. The generation unit can also moderately summarize papers with moderate relevance. For example, the generation unit generates moderate summaries for papers with moderate relevance. In this way, the generation unit can prioritize summarizing highly relevant information by adjusting the order of summaries based on the relevance of papers or technical reports. Some or all of the above-described processing in the generation unit may be performed using, for example, a generative AI. For example, the generation unit can adjust the order of summaries using a generative AI model that inputs the relevance of papers or technical reports and outputs the order of summaries. In this way, the generation unit can prioritize summarizing highly relevant information by adjusting the order of summaries based on the relevance of papers or technical reports.

[0042] The classification unit can improve the accuracy of classification by taking into account the interrelationships between papers and technical reports during classification. The classification unit, for example, considers the citation relationships between papers when classifying. For example, the classification unit analyzes the citation relationships between papers and classifies related papers into the same category. The classification unit can also consider the co-authorship relationships between technical reports when classifying. For example, the classification unit analyzes the co-authorship relationships between technical reports and classifies related reports into the same category. The classification unit can also consider common keywords between papers when classifying. For example, the classification unit analyzes common keywords between papers and classifies related papers into the same category. In this way, the classification unit can improve the accuracy of classification by taking into account the interrelationships between papers and technical reports. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can improve the accuracy of classification by using a generative AI model that inputs the interrelationships between papers and technical reports and outputs classification results. In this way, the classification unit can improve the accuracy of classification by taking into account the interrelationships between papers and technical reports.

[0043] The classification unit can perform classification by taking into account attribute information of the submitter of the paper or technical report. The classification unit, for example, performs classification by taking into account the submitter's affiliated institution. For example, the classification unit analyzes the submitter's affiliated institution and classifies papers and technical reports submitted by submitters from the same affiliated institution into the same category. The classification unit can also perform classification by taking into account the submitter's field of expertise. For example, the classification unit analyzes the submitter's field of expertise and classifies papers and technical reports submitted by submitters in the same field of expertise into the same category. The classification unit can also perform classification by taking into account the submitter's past research themes. For example, the classification unit analyzes the submitter's past research themes and classifies related papers and technical reports into the same category. This allows the classification unit to perform classification by taking into account the submitter's attribute information, thereby enabling more appropriate classification. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can perform classification using a generative AI model that inputs the submitter's attribute information and outputs a classification result. This allows the classification unit to perform classification taking into consideration the attribute information of the submitter, thereby enabling more appropriate classification.

[0044] The classification unit can perform classification taking into account the geographical distribution of papers and technical reports. The classification unit, for example, performs classification taking into account the region in which the papers were published. For example, the classification unit analyzes the region in which the papers were published and classifies papers published in the same region into the same category. The classification unit can also perform classification taking into account the country in which the technical reports were published. For example, the classification unit analyzes the country in which the technical reports were published and classifies reports published in the same country into the same category. The classification unit can also perform classification taking into account the city in which the papers were published. For example, the classification unit analyzes the city in which the papers were published and classifies papers published in the same city into the same category. In this way, the classification unit can appropriately classify information related to regions by performing classification taking into account the geographical distribution of papers and technical reports. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can perform classification using a generative AI model that inputs the geographical distribution of papers and technical reports and outputs classification results. In this way, the classification unit can appropriately classify information related to regions by performing classification taking into account the geographical distribution of papers and technical reports.

[0045] The classification unit can improve the accuracy of classification by referring to related documents of papers and technical reports during classification. The classification unit, for example, considers citation relationships among the related documents when classifying. For example, the classification unit analyzes the citation relationships among the related documents and classifies the related documents into the same category. The classification unit can also consider co-authorship relationships among the related documents when classifying. For example, the classification unit analyzes the co-authorship relationships among the related documents and classifies the related documents into the same category. The classification unit can also consider common keywords among the related documents when classifying. For example, the classification unit analyzes common keywords among the related documents and classifies the related documents into the same category. This allows the classification unit to improve the accuracy of classification by referring to related documents of papers and technical reports. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can improve the accuracy of classification by using a generative AI model that inputs related documents and outputs classification results. This allows the classification unit to improve the accuracy of classification by referring to related documents of papers and technical reports.

[0046] When posting, the posting unit can select the optimal display method by referring to the user's past browsing history. The posting unit, for example, prioritizes displaying categories that the user has previously browsed. For example, the posting unit can analyze categories that the user has previously browsed and prioritize displaying summaries of the same category. The posting unit can also prioritize displaying related summaries based on the user's past browsing history. For example, the posting unit can analyze the user's past browsing history and prioritize displaying related summaries. The posting unit can also analyze the user's past browsing history and suggest an optimal display method. For example, the posting unit can analyze the user's past browsing history and suggest an optimal display method. In this way, the posting unit can provide the user with the optimal display method by referring to the past browsing history. Some or all of the above-described processing in the posting unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the posting unit can select the optimal display method using a generation AI model that inputs the user's past browsing history and outputs the optimal display method. In this way, the posting unit can provide the user with the optimal display method by referring to the past browsing history.

[0047] The publishing unit can apply different display formats to each category of paper or technical report when publishing. For example, the publishing unit uses a specific display format for AI technology summaries. For example, the publishing unit uses a specific display format for AI technology summaries. The publishing unit can also use a different display format for biotechnology summaries. For example, the publishing unit can use a different display format for biotechnology summaries. The publishing unit can also use yet another display format for energy technology summaries. For example, the publishing unit can use yet another display format for energy technology summaries. In this way, the publishing unit applies different display formats to each category of paper or technical report, thereby improving the visibility of the information. Some or all of the above-mentioned processing in the publishing unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the publishing unit can apply the display format using a generative AI model that inputs the category of the paper or technical report and outputs a display format. In this way, the publishing unit applies different display formats to each category of paper or technical report, thereby improving the visibility of the information.

[0048] The publishing unit can adjust the order of publication based on the submission date of the paper or technical report when publishing. For example, the publishing unit prioritizes publishing recently submitted papers. For example, the publishing unit prioritizes publishing recently submitted papers. The publishing unit can also postpone papers submitted earlier. For example, the publishing unit postpones publishing papers submitted earlier. The publishing unit can also moderately publish papers submitted at an intermediate date. For example, the publishing unit moderately publishes papers submitted at an intermediate date. In this way, the publishing unit can prioritize providing the latest information by adjusting the publication order based on the submission date of the paper or technical report. Some or all of the above-described processing in the publishing unit can be performed using, for example, a generative AI, or can be performed without using a generative AI. For example, the publishing unit can adjust the publication order using a generative AI model that inputs the submission date of the paper or technical report and outputs the publication order. In this way, the publishing unit can prioritize providing the latest information by adjusting the publication order based on the submission date of the paper or technical report.

[0049] The publishing department can adjust the published content by referring to market data related to the paper or technical report when publishing it. For example, the publishing department prioritizes publishing technical reports with high demand based on market data. For example, the publishing department analyzes market data and prioritizes publishing technical reports with high demand. The publishing department can also postpone technical reports with low demand based on market data. For example, the publishing department analyzes market data and postpones publishing technical reports with low demand. The publishing department can also moderately publish technical reports with medium demand based on market data. For example, the publishing department analyzes market data and moderately publishes technical reports with medium demand. In this way, the publishing department can prioritize providing information with high demand by referring to the related market data. Some or all of the above-mentioned processing in the publishing department can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the publishing department can adjust the published content using a generation AI model that inputs market data and outputs the published content. In this way, the publishing department can prioritize providing information with high demand by referring to the related market data.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The reception unit can analyze the user's past submission history and select the optimal reception method. For example, the reception unit can analyze the format of papers the user has submitted in the past and recommend submitting in the same format. The reception unit can also analyze the content of papers the user has submitted in the past and prioritize receiving papers on related topics. Furthermore, the reception unit can suggest the optimal submission time based on the user's past submission history. In this way, the reception unit can select the optimal reception method by analyzing the user's past submission history, enabling efficient reception.

[0052] When generating a summary, the generator can adjust the level of detail of the summary based on the importance of the paper or technical report. For example, a detailed summary can be generated for a paper of high importance. A concise summary can also be generated for a paper of low importance. Furthermore, a summary with appropriate detail can be generated for a paper of medium importance. In this way, the generator can generate an appropriate summary by adjusting the level of detail of the summary based on the importance of the paper or technical report.

[0053] When generating summaries, the generation unit can apply different summaries algorithms depending on the category of the paper or technical report. For example, for papers on AI technology, a specific algorithm can be used to generate summaries. For papers on biotechnology, a different algorithm can be used to generate summaries. Furthermore, for papers on energy technology, a still different algorithm can be used to generate summaries. This allows the generation unit to generate more appropriate summaries by applying different summaries algorithms depending on the category of the paper or technical report.

[0054] When generating summaries, the generation unit can determine the priority of summaries based on the submission date of the paper or technical report. For example, it can prioritize summaries of recently submitted papers. It can also postpone papers that have been submitted a long time ago. Furthermore, it can appropriately summarize papers that have been submitted a medium time ago. In this way, by determining the priority of summaries based on the submission date of the paper or technical report, the generation unit can prioritize summarizing the latest information.

[0055] When generating summaries, the generator can adjust the order of summaries based on the relevance of the papers and technical reports. For example, highly relevant papers can be summarized with priority. Papers with low relevance can also be postponed. Furthermore, papers with medium relevance can be summarized moderately. In this way, the generator can prioritize summarizing highly relevant information by adjusting the order of summaries based on the relevance of the papers and technical reports.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The reception department inputs published papers or technical reports. Published papers or technical reports include academic papers, technical reports, white papers, etc. The reception department can accept papers and technical reports in various formats, such as PDF, text, and image formats. Step 2: The generation unit uses generation AI to analyze the paper or technical report entered by the reception unit and generate a summary. The generation unit uses natural language processing technology to extract the main points of the paper or report and generate a summary. The generation unit analyzes the content of the paper or report using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The generation unit can also focus on analyzing the summary and conclusion of the paper to extract important information. Step 3: The classifier classifies the summaries generated by the generator into categories. The classifier classifies the summaries into categories such as AI technology, biotechnology, and energy technology. The classifier can classify the summaries based on criteria such as technical field, application field, and research topic. Step 4: The posting unit posts the summaries classified by the classification unit on the intranet. The posting unit displays a list of summaries by category on the intranet, allowing users to click on a summary to view its detailed content. The posting unit can provide display formats such as list view, detailed view, and search function.

[0058] (Example 2) A technical information summarization system according to an embodiment of the present invention uses a generative AI to automatically summarize selected research and cutting-edge technology presentations, making them easily accessible on an intranet. This system inputs published papers and technical reports into the generative AI, analyzes their content, and generates summaries. The generated summaries are then categorized and posted on the intranet. This allows employees to easily grasp the latest technical information and develop a perspective on new business ventures. For example, published papers and technical reports are input into the generative AI. The format of the papers and reports is not important, and various formats, including PDF and text files, are supported. For example, the generative AI can analyze papers and technical reports written in English. The generative AI then analyzes the content of the input paper or technical report. The generative AI uses natural language processing technology to extract key points from the paper or report and generate a summary. For example, it focuses on analyzing the paper's abstract and conclusion to extract important information. The generated summaries are then classified into categories, such as AI technology, biotechnology, and energy technology. This allows employees to easily find summaries related to their interests and work. Finally, the generated summaries are posted on the intranet. Employees can easily view the latest technical information by accessing the intranet. For example, a list of summaries by category is displayed on the intranet, and by clicking on a summary, they can view the detailed content. This allows employees to easily grasp the latest technical information and develop a perspective on new business ventures. For example, by understanding the latest trends in AI technology, they can get ideas for new AI-related businesses. Also, by learning about the latest research in biotechnology, they can explore the possibility of new medical-related businesses. In this way, the technical information summarization system allows employees to quickly and efficiently grasp the latest technical information and develop a perspective on new business ventures.

[0059] A technical information summarization system according to an embodiment includes a receiving unit, a generating unit, a classification unit, and a publishing unit. The receiving unit inputs published papers or technical reports. Published papers or technical reports include, but are not limited to, academic papers, technical reports, and white papers. The receiving unit can receive papers or technical reports in various formats, such as PDF, text, and image formats. The generating unit uses a generation AI to analyze the papers or technical reports input by the receiving unit and generate summaries. The generating unit extracts key points from the papers or reports using natural language processing technology, for example, to generate summaries. The generating unit analyzes the contents of the papers or reports using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The generating unit can also focus on analyzing the abstract and conclusion of the papers to extract important information. The classification unit classifies the summaries generated by the generating unit into categories. The classification unit classifies the summaries into categories such as AI technology, biotechnology, and energy technology. The classification unit can classify abstracts based on criteria such as technical field, application field, and research theme. The posting unit posts the abstracts classified by the classification unit on an intranet. The posting unit can, for example, display a list of summaries by category on the intranet, allowing users to click on a summary to view detailed content. The posting unit can provide display formats such as a list view, a detailed view, and a search function. As a result, the technical information summarization system according to the embodiment automatically summarizes published papers and technical reports, allowing them to be easily viewed on the intranet. This allows employees to quickly and efficiently grasp the latest technical information. Some or all of the above-described processing by the generation unit may be performed using, for example, a generative AI. For example, the generation unit can generate summaries using a generative AI model that takes papers and technical reports as input and outputs summaries. As a result, the generation unit can efficiently extract key points from papers and reports using natural language processing technology and generate summaries. As a result, the technical information summarization system according to the embodiment automatically summarizes published papers and technical reports, allowing them to be easily viewed on the intranet.

[0060] The generation unit can use natural language processing technology to extract the main points of a paper or report and generate a summary. The generation unit can extract the main points of a paper or report using, for example, morphological analysis. For example, the generation unit can use morphological analysis to divide a sentence into words and analyze the part of speech of each word. The generation unit can also extract the main points of a paper or report using grammatical analysis. For example, the generation unit can use grammatical analysis to analyze the structure of a sentence and clarify the relationships between subjects, predicates, objects, etc. The generation unit can also extract the main points of a paper or report using semantic analysis. For example, the generation unit can use semantic analysis to analyze the meaning of a sentence and extract important information. In this way, the generation unit can efficiently extract the main points of a paper or report and generate a summary using natural language processing technology. Some or all of the above-mentioned processing in the generation unit can be performed using, for example, a generative AI. For example, the generation unit can generate a summary using a generative AI model that takes a paper or technical report as input and outputs a summary. This allows the generation unit to use natural language processing technology to efficiently extract the main points of a paper or report and generate a summary.

[0061] The generation unit can focus its analysis on the abstract and conclusion of a paper to extract important information. The generation unit, for example, focuses its analysis on the abstract of a paper. For example, the generation unit extracts keywords contained in the abstract of a paper to identify important information. The generation unit can also focus its analysis on the conclusion of a paper. For example, the generation unit extracts key points contained in the conclusion of a paper to identify important information. The generation unit can also analyze a combination of the abstract and conclusion of a paper. For example, the generation unit integrates information from the abstract and conclusion to extract important information. This allows the generation unit to focus its analysis on the abstract and conclusion of a paper to efficiently extract important information. Some or all of the above-described processing in the generation unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the generation unit can extract important information using a generative AI model that inputs the abstract and conclusion of a paper and outputs important information. This allows the generation unit to focus its analysis on the abstract and conclusion of the paper and efficiently extract important information.

[0062] The classification unit can classify abstracts into categories of AI technology, biotechnology, and energy technology. The classification unit, for example, classifies abstracts into the AI ​​technology category. For example, the classification unit analyzes keywords included in the abstracts to identify abstracts related to AI technology. The classification unit can also classify abstracts into the biotechnology category. For example, the classification unit analyzes keywords included in the abstracts to identify abstracts related to biotechnology. The classification unit can also classify abstracts into the energy technology category. For example, the classification unit analyzes keywords included in the abstracts to identify abstracts related to energy technology. As a result, the classification unit can classify abstracts into the AI ​​technology, biotechnology, and energy technology categories. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can classify abstracts using a generative AI model that receives abstracts as input and outputs categories. As a result, the classification unit can classify abstracts into the AI ​​technology, biotechnology, and energy technology categories.

[0063] The posting unit can display a list of summaries by category on the intranet, allowing detailed summary content to be confirmed by clicking on them. The posting unit, for example, displays the list of summaries by category on the intranet. For example, the posting unit displays a list of summaries by category, such as AI technology, biotechnology, and energy technology. The posting unit can also display detailed summary content by clicking on each item in the list of summaries. For example, the posting unit can display detailed summary content in a pop-up window when an item in the list of summaries is clicked. The posting unit can also display detailed summary content in a new page when an item in the list of summaries is clicked. In this way, the posting unit can display a list of summaries by category on the intranet, allowing detailed summary content to be confirmed by clicking on it. Some or all of the above-described processing by the posting unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the posting unit can display detailed summary content using a generation AI model that inputs the list of summaries and outputs detailed summary content. In this way, the posting unit can display a list of summaries by category on the intranet, allowing detailed summary content to be confirmed by clicking on it.

[0064] The reception unit can estimate the user's emotions and adjust the timing of receiving papers and technical reports based on the estimated user emotions. For example, the reception unit captures the user's facial expressions with a camera and estimates the emotions using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expressions and adjusts the timing of receiving the papers and technical reports. The reception unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the timing of receiving the papers and technical reports. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations and adjusts the timing of receiving the papers and technical reports. This allows the reception unit to adjust the timing of receiving the papers and technical reports based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions. This allows the reception unit to adjust the reception timing according to the user's emotions, thereby reducing user stress and enabling efficient reception.

[0065] When accepting papers or technical reports, the reception unit can analyze the user's past submission history and select the optimal reception method. For example, the reception unit analyzes the format of papers previously submitted by the user and recommends submitting them in the same format. For example, the reception unit analyzes the format of papers previously submitted by the user and recommends submitting them in the same format. The reception unit can also analyze the content of papers previously submitted by the user and prioritize accepting papers on related topics. For example, the reception unit can analyze the content of papers previously submitted by the user and prioritize accepting papers on related topics. The reception unit can also suggest an optimal submission time based on the user's past submission history. For example, the reception unit analyzes the user's past submission history and suggests an optimal submission time. This allows the reception unit to select the optimal reception method by analyzing the user's past submission history, enabling efficient reception. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can select the optimal reception method using an AI model that inputs the user's past submission history and outputs the optimal reception method. This allows the reception unit to analyze the user's past submission history to select the most appropriate reception method, enabling efficient reception.

[0066] When receiving papers or technical reports, the reception unit can filter them based on the user's current research topic or field of interest. For example, the reception unit prioritizes receiving papers related to the user's current research topic. For example, the reception unit prioritizes receiving papers containing keywords related to the user's current research topic. The reception unit can also filter related technical reports based on the user's field of interest. For example, the reception unit filters technical reports containing keywords related to the user's field of interest. The reception unit can also prioritize receiving papers containing related keywords based on the user's research topic. For example, the reception unit prioritizes receiving papers containing keywords related to the user's research topic. In this way, the reception unit can prioritize receiving highly relevant materials by filtering based on the user's research topic or field of interest. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can perform filtering using an AI model that inputs the user's research topic or field of interest and outputs related materials. This allows the reception unit to perform filtering based on the user's research theme or field of interest, allowing it to preferentially receive highly relevant materials.

[0067] The reception unit can estimate the user's emotions and determine the priority of papers and technical reports to be accepted based on the estimated user emotions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on changes in facial expression and determines the priority of papers and technical reports to be accepted. The reception unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the reception unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the priority of papers and technical reports to be accepted. The reception unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the reception unit calculates an emotion score based on heart rate fluctuations and determines the priority of papers and technical reports to be accepted. In this way, the reception unit can prioritize important materials by determining the priority according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, an emotion engine or generative AI. The generation AI may be 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-described processing in the reception unit may be performed using AI, for example, or may be performed without using AI. For example, the reception unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions. This allows the reception unit to prioritize important documents by determining the order of priority according to the user's emotions.

[0068] When accepting papers or technical reports, the reception unit can prioritize accepting highly relevant materials by taking into account the user's geographical location information. For example, if the user is in a specific region, the reception unit prioritizes accepting papers related to that region. For example, if the user is in a specific region, the reception unit prioritizes accepting papers containing keywords related to that region. Furthermore, if the user is overseas, the reception unit can prioritize accepting international technical reports. For example, if the user is overseas, the reception unit prioritizes accepting international technical reports. Furthermore, if the user is in a specific city, the reception unit can prioritize accepting research related to that city. For example, if the user is in a specific city, the reception unit prioritizes accepting research containing keywords related to that city. In this way, the reception unit can prioritize accepting highly relevant materials by taking the user's geographical location information into account. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can prioritize accepting highly relevant materials using an AI model that inputs the user's geographical location information and outputs related materials. This allows the reception unit to give priority to receiving highly relevant materials by taking into account the user's geographical location information.

[0069] The reception unit can analyze the user's social media activity and receive related materials when receiving a paper or technical report. For example, the reception unit prioritizes receiving papers shared by the user on social media. For example, the reception unit prioritizes receiving papers shared by the user on social media. The reception unit can also prioritize receiving papers by researchers the user follows on social media. For example, the reception unit prioritizes receiving papers by researchers the user follows on social media. The reception unit can also prioritize receiving technical reports in which the user has shown interest on social media. For example, the reception unit prioritizes receiving technical reports in which the user has shown interest on social media. In this way, the reception unit can analyze the user's social media activity and prioritize receiving highly relevant materials. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can receive related materials using an AI model that inputs the user's social media activity and outputs related materials. In this way, the reception unit can analyze the user's social media activity and prioritize receiving highly relevant materials.

[0070] The generation unit can estimate the user's emotion and adjust the presentation style of the summary based on the estimated user emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expression and adjusts the presentation style of the summary. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the presentation style of the summary. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations and adjusts the presentation style of the summary. This allows the generation unit to adjust the presentation style of the summary according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions. This allows the generation unit to generate a more appropriate summary by adjusting the summary expression method according to the user's emotions.

[0071] When generating a summary, the generation unit can adjust the level of detail of the summary based on the importance of the paper or technical report. For example, the generation unit generates a detailed summary for a paper with high importance. For example, the generation unit generates a detailed summary for a paper with high importance. The generation unit can also generate a concise summary for a paper with low importance. For example, the generation unit generates a concise summary for a paper with low importance. The generation unit can also generate a moderately detailed summary for a paper with medium importance. For example, the generation unit generates a moderately detailed summary for a paper with medium importance. In this way, the generation unit can generate an appropriate summary by adjusting the level of detail of the summary based on the importance of the paper or technical report. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI. For example, the generation unit can adjust the level of detail of the summary using a generation AI model that inputs the importance of the paper or technical report and outputs the level of detail of the summary. In this way, the generation unit can generate an appropriate summary by adjusting the level of detail of the summary based on the importance of the paper or technical report.

[0072] When generating a summary, the generation unit can apply different summarization algorithms depending on the category of the paper or technical report. For example, for a paper on AI technology, the generation unit generates a summary using a specific algorithm. For example, the generation unit generates a summary using a specific summarization algorithm for a paper on AI technology. The generation unit can also generate a summary using a different algorithm for a paper on biotechnology. For example, the generation unit can generate a summary using a different summarization algorithm for a paper on biotechnology. The generation unit can also generate a summary using yet another algorithm for a paper on energy technology. For example, the generation unit can generate a summary using yet another summarization algorithm for a paper on energy technology. In this way, the generation unit can generate more appropriate summaries by applying different summarization algorithms depending on the category of the paper or technical report. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generative AI. For example, the generation unit can apply a summarization algorithm using a generative AI model that inputs the category of the paper or technical report and outputs a summarization algorithm. In this way, the generation unit can generate more appropriate summaries by applying different summarization algorithms depending on the category of the paper or technical report.

[0073] The generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user emotion. For example, the generation unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on changes in facial expression and adjusts the length of the summary. The generation unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the generation unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the length of the summary. The generation unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the generation unit calculates an emotion score based on heart rate fluctuations and adjusts the length of the summary. This allows the generation unit to adjust the length of the summary based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the generation unit may be performed using, for example, AI, or may be performed without using AI. For example, the generation unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions. This allows the generation unit to generate a more appropriate summary by adjusting the length of the summary according to the user's emotions.

[0074] When generating summaries, the generation unit can determine the priority of summaries based on the submission date of the paper or technical report. For example, the generation unit prioritizes summaries of recently submitted papers. For example, the generation unit prioritizes generating summaries for recently submitted papers. The generation unit can also postpone papers that were submitted recently. For example, the generation unit postpones generating summaries for recently submitted papers. The generation unit can also moderately summarize papers that were submitted recently. For example, the generation unit generates moderate summaries for papers that were submitted recently. In this way, the generation unit can prioritize summaries of the latest information by determining the priority of summaries based on the submission date of the paper or technical report. Some or all of the above-mentioned processing in the generation unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the generation unit can determine the priority of summaries using a generation AI model that inputs the submission date of the paper or technical report and outputs the priority of summaries. This allows the generation unit to prioritize summaries based on the submission date of papers and technical reports, allowing the latest information to be summarized first.

[0075] When generating summaries, the generation unit can adjust the order of summaries based on the relevance of papers or technical reports. The generation unit, for example, prioritizes summaries of highly relevant papers. For example, the generation unit prioritizes generating summaries for highly relevant papers. The generation unit can also postpone generating summaries for less relevant papers. For example, the generation unit postpones generating summaries for less relevant papers. The generation unit can also moderately summarize papers with moderate relevance. For example, the generation unit generates moderate summaries for papers with moderate relevance. In this way, the generation unit can prioritize summarizing highly relevant information by adjusting the order of summaries based on the relevance of papers or technical reports. Some or all of the above-described processing in the generation unit may be performed using, for example, a generative AI. For example, the generation unit can adjust the order of summaries using a generative AI model that inputs the relevance of papers or technical reports and outputs the order of summaries. In this way, the generation unit can prioritize summarizing highly relevant information by adjusting the order of summaries based on the relevance of papers or technical reports.

[0076] The classification unit can estimate the user's emotion and adjust the classification criteria based on the estimated user's emotion. For example, the classification unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the classification unit calculates an emotion score based on changes in facial expression and adjusts the classification criteria. The classification unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the classification unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the classification criteria. The classification unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the classification unit calculates an emotion score based on heart rate fluctuations and adjusts the classification criteria. This allows the classification unit to adjust the classification criteria according to the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generative AI. Some or all of the above-described processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions. This allows the classification unit to adjust the classification criteria according to the user's emotions, enabling more appropriate classification.

[0077] The classification unit can improve the accuracy of classification by taking into account the interrelationships between papers and technical reports during classification. The classification unit, for example, considers the citation relationships between papers when classifying. For example, the classification unit analyzes the citation relationships between papers and classifies related papers into the same category. The classification unit can also consider the co-authorship relationships between technical reports when classifying. For example, the classification unit analyzes the co-authorship relationships between technical reports and classifies related reports into the same category. The classification unit can also consider common keywords between papers when classifying. For example, the classification unit analyzes common keywords between papers and classifies related papers into the same category. In this way, the classification unit can improve the accuracy of classification by taking into account the interrelationships between papers and technical reports. Some or all of the above-mentioned processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can improve the accuracy of classification by using a generative AI model that inputs the interrelationships between papers and technical reports and outputs classification results. In this way, the classification unit can improve the accuracy of classification by taking into account the interrelationships between papers and technical reports.

[0078] The classification unit can perform classification by taking into account attribute information of the submitter of the paper or technical report. The classification unit, for example, performs classification by taking into account the submitter's affiliated institution. For example, the classification unit analyzes the submitter's affiliated institution and classifies papers and technical reports submitted by submitters from the same affiliated institution into the same category. The classification unit can also perform classification by taking into account the submitter's field of expertise. For example, the classification unit analyzes the submitter's field of expertise and classifies papers and technical reports submitted by submitters in the same field of expertise into the same category. The classification unit can also perform classification by taking into account the submitter's past research themes. For example, the classification unit analyzes the submitter's past research themes and classifies related papers and technical reports into the same category. This allows the classification unit to perform classification by taking into account the submitter's attribute information, thereby enabling more appropriate classification. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can perform classification using a generative AI model that inputs the submitter's attribute information and outputs a classification result. This allows the classification unit to perform classification taking into consideration the attribute information of the submitter, thereby enabling more appropriate classification.

[0079] The classification unit can estimate the user's emotion and adjust the display order of the classification results based on the estimated user emotion. For example, the classification unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. For example, the classification unit calculates an emotion score based on changes in facial expression and adjusts the display order of the classification results. The classification unit can also record the user's voice and estimate the emotion using voice analysis technology. For example, the classification unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the display order of the classification results. The classification unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotion using an emotion estimation algorithm. For example, the classification unit calculates an emotion score based on heart rate fluctuations and adjusts the display order of the classification results. This allows the classification unit to adjust the display order of the classification results according to the user's emotion. Emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generative AI. The generative AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the classification unit may be performed using, for example, AI, or may be performed without using AI. For example, the classification unit may input image data of a user taken with a camera into the generation AI and cause the generation AI to estimate the user's emotions. This allows the classification unit to adjust the order in which the classification results are displayed depending on the user's emotions, thereby providing more appropriate information.

[0080] The classification unit can perform classification taking into account the geographical distribution of papers and technical reports. The classification unit, for example, performs classification taking into account the region in which the papers were published. For example, the classification unit analyzes the region in which the papers were published and classifies papers published in the same region into the same category. The classification unit can also perform classification taking into account the country in which the technical reports were published. For example, the classification unit analyzes the country in which the technical reports were published and classifies reports published in the same country into the same category. The classification unit can also perform classification taking into account the city in which the papers were published. For example, the classification unit analyzes the city in which the papers were published and classifies papers published in the same city into the same category. In this way, the classification unit can appropriately classify information related to regions by performing classification taking into account the geographical distribution of papers and technical reports. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can perform classification using a generative AI model that inputs the geographical distribution of papers and technical reports and outputs classification results. In this way, the classification unit can appropriately classify information related to regions by performing classification taking into account the geographical distribution of papers and technical reports.

[0081] The classification unit can improve the accuracy of classification by referring to related documents of papers and technical reports during classification. The classification unit, for example, considers citation relationships among the related documents when classifying. For example, the classification unit analyzes the citation relationships among the related documents and classifies the related documents into the same category. The classification unit can also consider co-authorship relationships among the related documents when classifying. For example, the classification unit analyzes the co-authorship relationships among the related documents and classifies the related documents into the same category. The classification unit can also consider common keywords among the related documents when classifying. For example, the classification unit analyzes common keywords among the related documents and classifies the related documents into the same category. This allows the classification unit to improve the accuracy of classification by referring to related documents of papers and technical reports. Some or all of the above-described processing in the classification unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the classification unit can improve the accuracy of classification by using a generative AI model that inputs related documents and outputs classification results. This allows the classification unit to improve the accuracy of classification by referring to related documents of papers and technical reports.

[0082] The posting unit can estimate the user's emotions and adjust the display method of the posting based on the estimated user emotions. For example, the posting unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the posting unit calculates an emotion score based on changes in facial expression and adjusts the display method of the posting. The posting unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the posting unit analyzes the tone and speed of the voice, calculates an emotion score, and adjusts the display method of the posting. The posting unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the posting unit calculates an emotion score based on heart rate fluctuations and adjusts the display method of the posting. This allows the posting unit to adjust the display method of the posting according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing by the publishing unit may be performed using, for example, AI, or may be performed without using AI. For example, the publishing unit may input image data of a user taken with a camera into the generating AI and cause the generating AI to estimate the user's emotions. This allows the publishing unit to adjust the display method of the posting according to the user's emotions, thereby providing more appropriate information.

[0083] When posting, the posting unit can select the optimal display method by referring to the user's past browsing history. The posting unit, for example, prioritizes displaying categories that the user has previously browsed. For example, the posting unit can analyze categories that the user has previously browsed and prioritize displaying summaries of the same category. The posting unit can also prioritize displaying related summaries based on the user's past browsing history. For example, the posting unit can analyze the user's past browsing history and prioritize displaying related summaries. The posting unit can also analyze the user's past browsing history and suggest an optimal display method. For example, the posting unit can analyze the user's past browsing history and suggest an optimal display method. In this way, the posting unit can provide the user with the optimal display method by referring to the past browsing history. Some or all of the above-described processing in the posting unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the posting unit can select the optimal display method using a generation AI model that inputs the user's past browsing history and outputs the optimal display method. In this way, the posting unit can provide the user with the optimal display method by referring to the past browsing history.

[0084] The publishing unit can apply different display formats to each category of paper or technical report when publishing. For example, the publishing unit uses a specific display format for AI technology summaries. For example, the publishing unit uses a specific display format for AI technology summaries. The publishing unit can also use a different display format for biotechnology summaries. For example, the publishing unit can use a different display format for biotechnology summaries. The publishing unit can also use yet another display format for energy technology summaries. For example, the publishing unit can use yet another display format for energy technology summaries. In this way, the publishing unit applies different display formats to each category of paper or technical report, thereby improving the visibility of the information. Some or all of the above-mentioned processing in the publishing unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the publishing unit can apply the display format using a generative AI model that inputs the category of the paper or technical report and outputs a display format. In this way, the publishing unit applies different display formats to each category of paper or technical report, thereby improving the visibility of the information.

[0085] The posting unit can estimate the user's emotions and determine the posting priority based on the estimated user emotions. For example, the posting unit captures the user's facial expression with a camera and estimates the emotions using an emotion estimation algorithm. For example, the posting unit calculates an emotion score based on changes in facial expression and determines the posting priority. The posting unit can also record the user's voice and estimate the emotions using voice analysis technology. For example, the posting unit analyzes the tone and speed of the voice, calculates an emotion score, and determines the posting priority. The posting unit can also collect the user's biometric data (heart rate and electrodermal activity) with a sensor and estimate the emotions using an emotion estimation algorithm. For example, the posting unit calculates an emotion score based on heart rate fluctuations and determines the posting priority. This allows the posting unit to determine the posting priority based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing by the publishing unit may be performed using, for example, AI, or may be performed without using AI. For example, the publishing unit may input image data of a user taken with a camera into the generating AI and cause the generating AI to estimate the user's emotions. This allows the publishing unit to prioritize publishing according to the user's emotions, thereby providing important information preferentially.

[0086] The publishing unit can adjust the order of publication based on the submission date of the paper or technical report when publishing. For example, the publishing unit prioritizes publishing recently submitted papers. For example, the publishing unit prioritizes publishing recently submitted papers. The publishing unit can also postpone papers submitted earlier. For example, the publishing unit postpones publishing papers submitted earlier. The publishing unit can also moderately publish papers submitted at an intermediate date. For example, the publishing unit moderately publishes papers submitted at an intermediate date. In this way, the publishing unit can prioritize providing the latest information by adjusting the publication order based on the submission date of the paper or technical report. Some or all of the above-described processing in the publishing unit can be performed using, for example, a generative AI, or can be performed without using a generative AI. For example, the publishing unit can adjust the publication order using a generative AI model that inputs the submission date of the paper or technical report and outputs the publication order. In this way, the publishing unit can prioritize providing the latest information by adjusting the publication order based on the submission date of the paper or technical report.

[0087] The publishing department can adjust the published content by referring to market data related to the paper or technical report when publishing it. For example, the publishing department prioritizes publishing technical reports with high demand based on market data. For example, the publishing department analyzes market data and prioritizes publishing technical reports with high demand. The publishing department can also postpone technical reports with low demand based on market data. For example, the publishing department analyzes market data and postpones publishing technical reports with low demand. The publishing department can also moderately publish technical reports with medium demand based on market data. For example, the publishing department analyzes market data and moderately publishes technical reports with medium demand. In this way, the publishing department can prioritize providing information with high demand by referring to the related market data. Some or all of the above-mentioned processing in the publishing department can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the publishing department can adjust the published content using a generation AI model that inputs market data and outputs the published content. In this way, the publishing department can prioritize providing information with high demand by referring to the related market data. === Hard Collateral 1-1 === Each of the above-described elements, including the reception unit, generation unit, classification unit, and posting unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the reception unit detects the user's facial expression and voice using the camera 42 and microphone 38B of the smart device 14, and estimates the user's emotion using the control unit 46A. The generation unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, analyzes papers and technical reports using a generation AI to generate summaries. The classification unit, implemented, for example, by the specific processing unit 290 of the data processing device 12, classifies the generated summaries by category. The posting unit, implemented, for example, by the control unit 46A of the smart device 14, posts the summaries on an intranet. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned reception unit, generation unit, classification unit, and posting unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit detects the user's facial expression and voice using the camera 42 and microphone 238 of the smart glasses 214, and estimates the emotion using the control unit 46A. The generation unit, realized, for example, by the specific processing unit 290 of the data processing device 12, analyzes papers and technical reports using a generation AI and generates summaries. The classification unit, realized, for example, by the specific processing unit 290 of the data processing device 12, classifies the generated summaries by category. The posting unit, realized, for example, by the control unit 46A of the smart glasses 214, posts the summaries on an intranet. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned reception unit, generation unit, classification unit, and posting unit is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit detects the user's facial expression and voice using the camera 42 and microphone 238 of the headset-type terminal 314, and estimates the emotion using the control unit 46A. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes papers and technical reports using a generation AI to generate summaries. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and classifies the generated summaries by category. The posting unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and posts the summaries on an intranet. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned reception unit, generation unit, classification unit, and posting unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit detects the user's facial expression and voice using the camera 42 and microphone 238 of the robot 414, and estimates the user's emotions using the control unit 46A. The generation unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes papers and technical reports using a generation AI to generate summaries. The classification unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and classifies the generated summaries by category. The posting unit is realized, for example, by the control unit 46A of the robot 414, and posts the summaries on an intranet.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] The reception unit can analyze the user's past submission history and select the optimal reception method. For example, the reception unit can analyze the format of papers the user has submitted in the past and recommend submitting in the same format. The reception unit can also analyze the content of papers the user has submitted in the past and prioritize receiving papers on related topics. Furthermore, the reception unit can suggest the optimal submission time based on the user's past submission history. In this way, the reception unit can select the optimal reception method by analyzing the user's past submission history, enabling efficient reception.

[0090] When generating a summary, the generator can adjust the level of detail of the summary based on the importance of the paper or technical report. For example, a detailed summary can be generated for a paper of high importance. A concise summary can also be generated for a paper of low importance. Furthermore, a summary with appropriate detail can be generated for a paper of medium importance. In this way, the generator can generate an appropriate summary by adjusting the level of detail of the summary based on the importance of the paper or technical report.

[0091] When generating summaries, the generation unit can apply different summaries algorithms depending on the category of the paper or technical report. For example, for papers on AI technology, a specific algorithm can be used to generate summaries. For papers on biotechnology, a different algorithm can be used to generate summaries. Furthermore, for papers on energy technology, a still different algorithm can be used to generate summaries. This allows the generation unit to generate more appropriate summaries by applying different summaries algorithms depending on the category of the paper or technical report.

[0092] When generating summaries, the generation unit can determine the priority of summaries based on the submission date of the paper or technical report. For example, it can prioritize summaries of recently submitted papers. It can also postpone papers that have been submitted a long time ago. Furthermore, it can appropriately summarize papers that have been submitted a medium time ago. In this way, by determining the priority of summaries based on the submission date of the paper or technical report, the generation unit can prioritize summarizing the latest information.

[0093] When generating summaries, the generator can adjust the order of summaries based on the relevance of the papers and technical reports. For example, highly relevant papers can be summarized with priority. Papers with low relevance can also be postponed. Furthermore, papers with medium relevance can be summarized moderately. In this way, the generator can prioritize summarizing highly relevant information by adjusting the order of summaries based on the relevance of the papers and technical reports.

[0094] The reception unit can estimate the user's emotions and adjust the timing of receiving papers and technical reports based on the estimated user emotions. For example, the user's facial expression can be captured with a camera and the emotion can be estimated using an emotion estimation algorithm. The user's voice can also be recorded and the emotion can be estimated using voice analysis technology. Furthermore, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and the emotion can be estimated using an emotion estimation algorithm. This allows the reception unit to adjust the timing of receiving applications according to the user's emotions, reducing user stress and enabling efficient reception.

[0095] The generation unit can estimate the user's emotion and adjust the summary presentation method based on the estimated user emotion. For example, the user's facial expression can be captured with a camera and the emotion can be estimated using an emotion estimation algorithm. Alternatively, the user's voice can be recorded and the emotion can be estimated using voice analysis technology. Furthermore, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and the emotion can be estimated using an emotion estimation algorithm. This allows the generation unit to generate a more appropriate summary by adjusting the summary presentation method according to the user's emotion.

[0096] The generation unit can estimate the user's emotion and adjust the length of the summary based on the estimated user emotion. For example, the user's facial expression can be captured with a camera and the emotion can be estimated using an emotion estimation algorithm. Alternatively, the user's voice can be recorded and the emotion can be estimated using voice analysis technology. Furthermore, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and the emotion can be estimated using an emotion estimation algorithm. This allows the generation unit to generate a more appropriate summary by adjusting the length of the summary according to the user's emotion.

[0097] The classification unit can estimate the user's emotion and adjust the classification criteria based on the estimated user's emotion. For example, the user's facial expression can be captured with a camera and the emotion can be estimated using an emotion estimation algorithm. The user's voice can also be recorded and the emotion can be estimated using voice analysis technology. Furthermore, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and the emotion can be estimated using an emotion estimation algorithm. This allows the classification unit to adjust the classification criteria according to the user's emotion, enabling more appropriate classification.

[0098] The posting unit can estimate the user's emotions and adjust the display method of the posting based on the estimated user's emotions. For example, the user's facial expression can be captured with a camera and the emotion can be estimated using an emotion estimation algorithm. The user's voice can also be recorded and the emotion can be estimated using voice analysis technology. Furthermore, the user's biometric data (heart rate and electrodermal activity) can be collected with a sensor and the emotion can be estimated using an emotion estimation algorithm. This allows the posting unit to adjust the display method of the posting according to the user's emotions, thereby enabling more appropriate information to be provided.

[0099] The processing flow of the second embodiment will be briefly explained below.

[0100] Step 1: The reception department inputs published papers or technical reports. Published papers or technical reports include academic papers, technical reports, white papers, etc. The reception department can accept papers and technical reports in various formats, such as PDF, text, and image formats. Step 2: The generation unit uses generation AI to analyze the paper or technical report entered by the reception unit and generate a summary. The generation unit uses natural language processing technology to extract the main points of the paper or report and generate a summary. The generation unit analyzes the content of the paper or report using techniques such as morphological analysis, grammatical analysis, and semantic analysis. The generation unit can also focus on analyzing the summary and conclusion of the paper to extract important information. Step 3: The classifier classifies the summaries generated by the generator into categories. The classifier classifies the summaries into categories such as AI technology, biotechnology, and energy technology. The classifier can classify the summaries based on criteria such as technical field, application field, and research topic. Step 4: The posting unit posts the summaries classified by the classification unit on the intranet. The posting unit displays a list of summaries by category on the intranet, allowing users to click on a summary to view its detailed content. The posting unit can provide display formats such as list view, detailed view, and search function.

[0101] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0102] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0103] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0104] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0105] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0106] 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.

[0107] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0108] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0109] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0110] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0111] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0112] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0113] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0114] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0115] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0116] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0117] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0118] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0119] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0120] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0132] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0135] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, 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), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0152] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0155] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0156] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0157] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0158] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0159] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0160] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0161] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0162] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0163] 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.

[0164] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0165] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0166] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0167] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0168] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0169] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0170] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0171] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0172] [Explanation of symbols]

[0173] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception desk for inputting published papers or technical reports; a generation unit that analyzes the paper or technical report input by the reception unit and generates a summary; a classification unit that classifies the summaries generated by the generation unit into categories; a publishing unit that publishes the abstracts classified by the classification unit on an intranet; Equipped with A system characterized by:

2. The generation unit Extract the main points of papers and reports and generate summaries using natural language processing technology 2. The system of claim 1.

3. The generation unit Focus on analyzing the abstract and conclusion of the paper to extract important information 2. The system of claim 1.

4. The classification unit Classify the abstracts into categories of AI technology, biotechnology, and energy technology.

2. The system of claim 1.

5. The publishing section Display a list of summaries by category on the intranet, and enable users to click on the summary to view detailed content.

2. The system of claim 1.

6. The reception unit Estimate user emotions and adjust the timing of accepting papers and technical reports based on the estimated user emotions 2. The system of claim 1.

7. The reception unit When accepting papers or technical reports, analyze the user's past submission history and select the optimal submission method.

2. The system of claim 1.

8. The reception unit Filtering papers and technical reports based on the user's current research topic or area of ​​interest 2. The system of claim 1.

Images