System

Abstract

A system is provided.SOLUTION: The system includes a means for collecting paper information, a means for analyzing the collected paper information and generating a summary, a means for extracting new knowledge on the basis of the summary, a means for updating the database with the extracted knowledge, and a means for searching the database for a question in natural language and generating an appropriate answer.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In accordance with this, we create the "problem that the invention aims to solve" and "means for solving the problem" in the patent specification.

[0005] In the medical field, doctors are busy with their daily work, making it difficult to keep up with the latest medical information and incorporate it into their medical practice. Furthermore, manually collecting and analyzing vast amounts of medical literature requires time and effort, and there is a risk that this will not lead to prompt and accurate treatment. Given this background, there is a need for an efficient system that allows doctors to quickly access the latest medical knowledge and provide effective medical care. [Means for solving the problem]

[0006] The present invention solves the above-mentioned problems by providing a system including a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new knowledge based on the summaries, a means for updating a database with the extracted knowledge, and a means for searching the database in response to questions in natural language and generating appropriate answers. By verifying that the collected research paper information is up-to-date and extracting in-depth knowledge using a generative model, doctors can quickly access the latest information they need, thereby improving their medical practice skills and efficiency.

[0007] "Article information" refers to the content of literature related to medical and scientific research.

[0008] "Means" refers to a method, device, or process used to achieve a particular purpose.

[0009] "Collect" refers to the act of gathering specific information or data.

[0010] "Analyze" refers to the act of analyzing collected data and information to understand its contents.

[0011] An "abstract" is a short summary of the main points of a document or piece of writing.

[0012] "Generate" refers to the act of creating new information or content based on existing data.

[0013] "Insight" refers to knowledge and understanding gained through research and experience.

[0014] "Extraction" refers to the act of extracting specific elements or patterns from a large amount of data or information.

[0015] A "database" refers to a system in which a large amount of information or data is systematically organized and stored in a format that can be used for a specific purpose.

[0016] "Updating" refers to the act of making changes or additions to existing data or information to bring it up to date.

[0017] "Natural language" refers to a language used by humans on a daily basis, as opposed to a programming language or a specialized symbol system.

[0018] A "question" refers to an inquiry made to another person in order to obtain information.

[0019] "Searching" refers to the act of finding something that matches specific conditions from a large amount of data or information.

[0020] "Answer" refers to the information or response provided in response to a question.

[0021] A "generative model" refers to algorithms or software that use machine learning or artificial intelligence techniques to create new data or content.

[0022] The above are definitions of important words included in the claims. [Brief explanation of the drawings]

[0023] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7]FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0024] 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.

[0025] First, the terms used in the following description will be explained.

[0026] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0027] 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.

[0028] 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.

[0029] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0030] 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."

[0031] [First embodiment]

[0032] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0033] 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.

[0034] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] 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.

[0036] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] 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.

[0039] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] 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.

[0041] 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.

[0042] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0043] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0044] This invention is a system that allows doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[0045] The server first accesses a designated website to collect paper information. Through this access, it obtains the content of the most recent paper page and saves it as data. Next, the server analyzes the obtained web page to extract the paper title, abstract, and publication date. From this extraction result, it saves information on the most recent papers published within the last 24 hours in a list.

[0046] The server analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper and extract new findings from the summaries, making it possible to automatically identify the new findings that are most important to physicians from a vast amount of information.

[0047] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, and always stores the latest knowledge. The database is updated automatically, so that the latest information is provided when doctors access it.

[0048] A user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question and searches the database to find the most relevant information. It uses a question-answering generation model to generate an appropriate answer and provides it to the user.

[0049] When a doctor wants to learn about new treatments or the latest research findings on a particular disease, this system allows them to access accurate information in a much shorter time than traditional manual searches. For example, the server collects and analyzes the latest research papers on the effectiveness of new anticancer drugs and stores the summaries and new findings in a database. Based on this data, the system generates specific answers, such as "New anticancer drugs are likely to be more effective than existing ones," and provides them to the user.

[0050] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[0051] The above is an embodiment of this system.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The server sends an HTTP request to the specified website to retrieve the HTML content of the latest paper page, which is then used for further analysis.

[0055] Step 2:

[0056] The server uses a library such as BeautifulSoup to parse the retrieved HTML content and extracts specific HTML elements containing paper information (title, abstract, publication date).

[0057] Step 3:

[0058] The server checks the publication date of the extracted paper information, determines that it is the most recent, and adds only the most recent papers to the list.

[0059] Step 4:

[0060] The server inputs the collected paper information into a generative AI model and processes it to generate a summary, which concisely presents the key points.

[0061] Step 5:

[0062] The server applies a text classification model to the generated summary to extract new insights, which are new discoveries or conclusions drawn from the content of the paper.

[0063] Step 6:

[0064] The server stores the extracted knowledge in a database and updates the existing database, ensuring that the database always contains the latest information.

[0065] Step 7:

[0066] The user (doctor) inputs a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[0067] Step 8:

[0068] The server analyzes the input question, searches the database, and generates the most relevant answer using a question-answering generation model.

[0069] Step 9:

[0070] The server then provides the generated answers to the user, allowing doctors to quickly obtain accurate information based on the latest medical knowledge.

[0071] The above is the flow of specific processing steps of the program of this system.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] In the medical field, new papers are published daily, making it difficult for doctors to quickly access the latest treatments and research results. Traditional manual paper searching and summarization takes time and effort, often interfering with medical practice. Furthermore, the sheer volume of information increases the likelihood of important findings being overlooked. Therefore, there is a need for a system that can quickly extract important new findings from the vast amount of paper information and provide appropriate answers.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for collecting research paper information, means for analyzing the collected research paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for providing the generated answers to users. This allows doctors to quickly and accurately access the latest knowledge in the medical field, significantly reducing the time and effort required for doctors to gather information.

[0077] "Paper information" refers to information on documents that describe academic research results, particularly those related to the medical field.

[0078] "Collection methods" refers to the processes and technologies used to automatically obtain the required data from designated sources.

[0079] "Means of analysis" refers to the processes and techniques used to organize collected data and extract useful information.

[0080] A "summary generator" refers to a technique or process that extracts the main points from detailed information and presents them in a concise form.

[0081] "New insight extraction" refers to techniques and processes for discovering new, previously unknown information from analyzed and summarized data.

[0082] "Means of updating the database" refers to the technology and process for adding new information acquired to an existing information aggregation system and keeping it up to date.

[0083] A "natural language question" refers to a human inquiry written in a common language and input in a form that can be understood by a computer system.

[0084] "Database search methods" refers to techniques and processes for searching within existing information aggregation systems to quickly find specific information.

[0085] "Means for generating appropriate answers" refers to techniques and processes that create the most appropriate response to a user's question based on information retrieved from a database.

[0086] A "generative model" refers to an algorithm or system that uses artificial intelligence or machine learning to generate new data and insights.

[0087] MODE FOR CARRYING OUT THE INVENTION

[0088] This invention is a system that enables doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[0089] First, the server accesses the specified website and collects the paper information. Specifically, the server runs a regularly scheduled job to retrieve and save the HTML content of the paper page by sending an HTTP request to the specified URL. For example, the data can be retrieved using the Python requests library.

[0090] The server then reads the saved HTML files and extracts the paper titles, abstracts, and publication dates using an HTML parsing library such as BeautifulSoup, which then stores the most recent papers published in the last 24 hours in a list.

[0091] The server then analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper. It then extracts new findings from the summaries. This process makes it possible to automatically identify the new findings that are most important to doctors from a vast amount of information.

[0092] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, so the latest knowledge is always stored. The database is updated automatically, so that the latest information is always available when doctors access it.

[0093] Next, the user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question, searches the database to find the most relevant information, and uses a question-answering generation model to generate an appropriate answer, which is then provided to the user.

[0094] For example, consider a case where a user asks, "I want to know the latest research results regarding the effectiveness of new anticancer drugs." The server accesses websites to collect the latest research papers, summarizes the main points of the papers using a generative AI model, and extracts new findings. The data is then stored in a database, and specific information such as "New anticancer drugs are likely to be more effective than conventional ones" is generated as an answer to the question and provided to the user.

[0095] This allows doctors to access the latest medical knowledge quickly and accurately, significantly reducing the time and effort required to gather information.

[0096] Here is an example prompt:

[0097] "Collect papers on recent anti-cancer drug research, summarize their key points, and store them in a database. Extract new findings and provide them to physicians as up-to-date information."

[0098] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[0099] The above is an embodiment of the present invention.

[0100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0101] Step 1:

[0102] The server accesses the specified website and collects paper information. The server runs a periodically scheduled job, sending an HTTP request to the specified URL. The input is the specified URL and the request, and the output is the HTML content of the paper page. This content is saved as a file.

[0103] Step 2:

[0104] The server reads the saved HTML file and extracts the paper title, abstract, and publication date. The server uses an HTML parsing library such as BeautifulSoup to parse the specified HTML file. It has the HTML file to parse as input and gets the extracted paper title, abstract, and publication date as output. It saves this information in a temporary list.

[0105] Step 3:

[0106] The server filters the extracted paper data for the latest paper information published within the last 24 hours. The input is a list of extracted paper data, and the output is a filtered list of the latest papers. This information is used in the next step.

[0107] Step 4:

[0108] The server analyzes the filtered paper information and generates summaries using a generative AI model. The input is a list of the latest papers, and the output is a summary of each paper. A generative AI model (e.g., GPT-3) is used to create summaries of papers.

[0109] Step 5:

[0110] The server extracts new findings from the generated summaries. The input is the summarized paper information, and the output is the extraction of new findings. The server uses a generative AI model to identify and extract important findings.

[0111] Step 6:

[0112] The server updates the database with the extracted new knowledge. It takes new knowledge as input and gets an updated database as output. It integrates it with existing data and keeps it up to date.

[0113] Step 7:

[0114] A user (doctor) inputs a question in natural language into the system through a terminal. The user's question is the input, and the server receives the question text as the output.

[0115] Step 8:

[0116] The server analyzes the user's question and searches the database for relevant information. The input is the user's question and the contents of the database, and the output is a search for and retrieves highly relevant paper information.

[0117] Step 9:

[0118] The server uses a question-and-answer generation model to generate appropriate answers based on relevant information. The input is highly relevant paper information, and the output is generated answer text. The server uses the question-and-answer generation model to generate appropriate answers.

[0119] Step 10:

[0120] The server provides the generated answer to the user. The input is the generated answer text, and the output is the answer displayed on the user's terminal. The user can then confirm the answer on the terminal.

[0121] (Application example 1)

[0122] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0123] In medical settings and physical stores such as pharmacies, it is extremely important for doctors and pharmacists to quickly access the latest medical knowledge and research results. However, when searching manually, it takes a lot of time and effort to find the appropriate information from the vast amount of information, which can reduce the efficiency of medical treatment and medication provision. An effective solution to this problem is needed.

[0124] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0125] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new findings based on the summaries, a means for updating the database with the extracted findings, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for providing information using smart glasses in a physical store, thereby enabling doctors and pharmacists to quickly and efficiently access the latest medical knowledge and research results.

[0126] "Means for collecting publication information" refers to the techniques and processes used to obtain the latest scientific publication information from designated websites on the Internet.

[0127] "Means for analyzing collected paper information and generating summaries" refers to the technology and process for automatically analyzing the content of acquired scientific papers, extracting important information, and summarizing it briefly.

[0128] "Means for extracting new knowledge from summaries" refers to techniques and processes for extracting new discoveries and important knowledge from the generated summaries.

[0129] "Means for updating the database with extracted knowledge" refers to the techniques and processes for periodically storing new extracted knowledge in a database and keeping the information up to date.

[0130] "Means for searching a database in response to a natural language question and generating an appropriate answer" refers to the technology or process for understanding a question entered by a user in natural language, searching a database for relevant information, and generating an appropriate answer.

[0131] "Means for providing information using smart glasses in physical stores" refers to the technology and process for displaying and providing the information required by users in real time through smart glasses.

[0132] This invention relates to a system that allows doctors and pharmacists in brick-and-mortar stores to quickly and efficiently access the latest medical knowledge and research results using smart glasses. The system collects and analyzes research paper information, updates the results to a database, and provides relevant, up-to-date information when users input questions in natural language.

[0133] The server first collects the latest paper information from websites, using the requests and BeautifulSoup libraries to retrieve information such as the paper title, abstract, and publication date from specified sites on the Internet.

[0134] Next, the server uses a generative AI model (e.g., OpenAI's text-davinci-002 model) to analyze the collected paper information and generate a summary. To extract new insights from this summary, the server asks the model to summarize using a prompt sentence.

[0135] For example, use the following prompt statement:

[0136] Please briefly summarize the following and extract any new findings:

[0137] (Abstract of the paper)

[0138] New findings are automatically added to the database, ensuring that it is always up-to-date.

[0139] When a user accesses the system using smart glasses, they can input a question in natural language, such as "What are the latest anti-cancer drug treatments?" This question is sent to the server, where it is analyzed using a generative AI model and relevant information is retrieved from a database.

[0140] The generated answers are displayed on the smart glasses, providing the user with the information they need in real time.

[0141] "Generate the best answer to the following questions:

[0142] Question: (User Question)

[0143] Database: (Article database)

[0144] This will enable doctors and pharmacists using smart glasses to quickly access the latest medical knowledge and significantly improve the efficiency of medical treatment and drug provision. This system will reduce the burden on medical facilities and enable the provision of high-quality medical services.

[0145] The hardware used refers to smart glasses, and the software used includes the requests library, the BeautifulSoup library, and OpenAI's generative AI model (text-davinci-002 model).

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] The server accesses specified websites on the Internet to collect the latest paper information. It uses the requests library to retrieve the content of the webpage and the BeautifulSoup library to parse the HTML. It receives the URL of the specified website as input and extracts data including the paper title, abstract, and publication date as output.

[0149] Step 2:

[0150] The server analyzes the collected paper information and generates summaries. Here, it receives the collected paper abstracts as input and generates summaries using a generative AI model (OpenAI's text-davinci-002 model). Specifically, it creates a prompt sentence and asks the model to summarize. The output is the summarized text.

[0151] Step 3:

[0152] The server analyzes the generated summary and extracts new insights. It receives the summary generated in step 2 as input and again uses the generative AI model to extract new insights. Specifically, it creates a prompt sentence and asks the model to extract new insights. The output is the extracted new insights.

[0153] Step 4:

[0154] The server updates the database with the new findings extracted. It takes the new findings extracted in step 3 as input and stores them in the database. This keeps the database up to date. The output is the updated database.

[0155] Step 5:

[0156] A user accesses the system using smart glasses and inputs a question in natural language. The user's question is sent to the server through the smart glasses. The input is the user's natural language question, and the output is the question data sent to the server.

[0157] Step 6:

[0158] The server analyzes the user's question and searches the database. Using the question received in step 5 as input, it analyzes it using the generative AI model and searches for relevant information in the database. Specifically, it creates an appropriate prompt sentence and asks the model to generate the best answer. The output is the generated answer text.

[0159] Step 7:

[0160] The server sends the generated answer to the user's smart glasses. The answer generated in step 6 is received as input and displayed on the smart glasses. This allows the user to obtain the required information in real time. The output is the answer displayed on the user's glasses.

[0161] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0162] The present invention is a system that allows doctors to quickly access the latest medical knowledge, and further provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions.

[0163] The server first sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the most recent paper page. It then analyzes this HTML data to extract paper information (title, abstract, publication date), and saves only the most recent papers from the extracted data in a list.

[0164] The server then uses a generative AI model to concisely summarize the collected papers' abstracts. Based on this summarized information, a text classification model is applied to extract deeper insights. The extracted insights are stored in a database, updating the existing database. This ensures that the database always contains the latest medical knowledge.

[0165] When a doctor (user) enters a question into the system in natural language, the server analyzes the question. Using a question-answering generation model, it searches the database and generates the most relevant answer. Then, an emotion engine analyzes the emotion in the user's question and adjusts the answer based on the analysis results. For example, if the user is feeling anxious or impatient, the system can adjust its response to use a gentler tone.

[0166] The server provides the generated answer to the user. At this time, the emotion engine takes into account the user's current emotional state and adjusts the content and format of the response. For example, if the question is, "What is the latest anti-cancer drug treatment?", the emotion engine will sense the user's anxiety and respond in a reassuring tone. For example, it might say, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[0167] This system not only allows doctors to easily obtain the latest medical information, but also provides a better user experience by providing responses that take users' emotions into consideration, making it a powerful tool for reducing stress in medical settings and supporting quick and accurate decision-making.

[0168] The above is a specific embodiment for carrying out the present invention. It is expected that this system will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately.

[0169] The processing flow will be explained below.

[0170] Step 1:

[0171] The server sends an HTTP request to the designated medical paper provider site to obtain the HTML data of the latest paper page, thereby collecting the content of the web page containing paper information.

[0172] Step 2:

[0173] The server uses a library such as BeautifulSoup to parse the retrieved HTML data, extracting information such as the paper title, abstract, and publication date, and stores this data in a temporary list.

[0174] Step 3:

[0175] The server checks the publication date of the extracted paper information and determines whether it is the most recent publication date within the last 24 hours. Only the most recent paper information is kept in the list, and older ones are removed.

[0176] Step 4:

[0177] The server inputs the collected summaries into a generative AI model, such as T5 or BERT, to generate a concise summary, extracting the main points of the summaries and summarizing them briefly.

[0178] Step 5:

[0179] The server then inputs the generated summaries into a text classification model to extract new insights. The model identifies new medically important findings and conclusions from the summaries and converts them into a database-ready format.

[0180] Step 6:

[0181] The server stores the extracted new findings in a database and integrates them with existing data, ensuring that the database always maintains the latest medical knowledge.

[0182] Step 7:

[0183] The user (doctor) uses a terminal to input a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[0184] Step 8:

[0185] The server analyzes the user's question and generates an appropriate answer using a question-answering generation model, which searches a database and creates an answer based on the most relevant information.

[0186] Step 9:

[0187] The server uses an emotion engine to analyze emotions from the user's questions, for example, recognizing emotions when the user's input indicates impatience or anxiety.

[0188] Step 10:

[0189] The server adjusts the tone and content of the generated response based on the analysis results of the emotion engine. For example, it provides a response in a reassuring tone to a user who is feeling anxious.

[0190] Step 11:

[0191] The server then provides the final answer to the user via the terminal, allowing the user to quickly obtain the latest medical information in a manner that takes their feelings into consideration.

[0192] The above is the flow of specific processing steps of the program of this system.

[0193] Example 2

[0194] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0195] Conventional medical information systems have limitations in their ability to quickly and accurately provide the latest research information, and they lack the ability to respond in a way that takes users' feelings into consideration. This means that it takes time for medical professionals to obtain the information they need, which increases their stress.

[0196] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0197] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new knowledge based on the summaries, a means for updating the database with the extracted knowledge, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for analyzing the user's emotions and adjusting the answers, thereby enabling not only fast and accurate provision of medical information but also responses that correspond to the user's emotions.

[0198] "Paper information" refers to information about medical papers, such as the title, abstract, and publication date.

[0199] "Means of collection" refers to a combination of software and hardware used to obtain paper information from a specific website.

[0200] "Means for analysis" refers to the algorithms and software used to analyze the acquired paper information.

[0201] The "means for generating a summary" refers to software such as a generative AI model that concisely summarizes the gist of the collected and analyzed paper information.

[0202] "Insight extraction tools" are software such as text classification models that discover new insights from summarized information.

[0203] "Means for updating the database" refers to software and hardware for adding and updating the extracted new knowledge to the existing database.

[0204] "Means for searching a database in response to a question in natural language and generating an appropriate answer" refers to software such as a question-answering generation model that understands a question in natural language from a user, searches a database, and generates a relevant answer.

[0205] "Means for analyzing emotions and adjusting responses" refers to software such as an emotion engine that analyzes the content of the user's question and their emotional state and adjusts the response accordingly.

[0206] The present invention relates to a system for quickly and accurately acquiring medical information and generating a response that takes into consideration the user's feelings. The system is composed of a server, a terminal, and a user.

[0207] System Components

[0208] 1. Server

[0209] The server is responsible for collecting and analyzing paper information from medical paper websites. The server uses the following software and hardware:

[0210] Sending an HTTP request: Use the requests library to access a specific website and retrieve HTML data.

[0211] HTML Data Analysis: The obtained HTML data is analyzed using the Beautiful Soup library to extract the paper title, abstract, and publication date.

[0212] Generative AI models: Use generative AI models such as OpenAI GPT-4 to compactly summarize the collected key points.

[0213] Text classification models, such as BERT and RoBERTa, to extract deeper insights from summaries.

[0214] Database Management System (DBMS): For example, MySQL or PostgreSQL are used to store and update the extracted findings in a database.

[0215] 2. Terminal

[0216] The terminal provides the user interface and is the means by which users access the system and input questions. The terminal communicates with the server using a browser or dedicated application.

[0217] 3. Users

[0218] Users, primarily physicians, use the system to obtain the latest medical information and ask questions in natural language. Users access the system through terminals.

[0219] Specific examples of system operation

[0220] 1. The server sends an HTTP request to a medical article website to retrieve the HTML data for the latest article page. For example, use the requests library to access https: / / example-medical-site.com / latest-articles.

[0221] Example prompt: "Get the latest medical papers."

[0222] 2. The server analyzes the HTML data obtained using the Beautiful Soup library and extracts the necessary paper information (title, abstract, publication date).

[0223] Example prompt: "Extract paper information from HTML data."

[0224] 3. From the paper information extracted by the server, only the papers with the most recent publication dates are saved in the list.

[0225] 4. The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the extracted key points.

[0226] Example prompt: "Summarize the following abstract: [abstract text]"

[0227] 5. Apply text classification models, such as BERT or RoBERTa, to the summarized information to extract deeper insights.

[0228] 6. The server stores the extracted knowledge in a database such as MySQL or PostgreSQL and updates the existing database.

[0229] 7. A user uses a terminal to input a question into the system in natural language: "What is the latest anti-cancer drug treatment?"

[0230] 8. The server parses the user's question using a natural language processing library such as SpaCy or NLTK.

[0231] 9. The server uses the question-answering generation model to search the database and generate the most relevant answer.

[0232] Example prompt: "What is the latest treatment for cancer?"

[0233] 10. The server uses an emotion engine (for example, IBM Watson's natural language understanding service) to analyze the emotion from the user's question.

[0234] 11. The server adjusts the response based on the sentiment analysis results. For example, if the user is feeling anxious, the response will be gentler.

[0235] Example prompt: "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[0236] 12. The server provides the final adjusted answer to the user.

[0237] Through the above system configuration and processing procedures, the present invention enables doctors to quickly and accurately obtain the latest medical information and provides responses that take users' emotions into consideration, thereby reducing stress in medical settings and providing a better user experience.

[0238] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0239] Step 1:

[0240] The server sends an HTTP request to a medical research website.

[0241] Specifically, the server uses the requests library to access a specific medical article website (e.g., https: / / example-medical-site.com / latest-articles).

[0242] Input: Website URL

[0243] Output: HTML data of the latest paper page

[0244] The server retrieves the HTML data and proceeds to the next parsing step.

[0245] Step 2:

[0246] Parse the HTML data received by the server.

[0247] The server uses the Beautiful Soup library to convert the retrieved HTML data into a format that is easy to parse.

[0248] Input: Retrieved HTML data

[0249] Output: Parsable HTML tree structure

[0250] Specifically, the server analyzes the HTML tags and identifies the parts that contain the paper information.

[0251] Step 3:

[0252] The server extracts the paper information (title, abstract, publication date).

[0253] The server extracts specific information (title, abstract, publication date) from the parsed HTML tree structure.

[0254] Input: Parsed HTML tree structure

[0255] Output: Extracted paper information (title, abstract, publication date)

[0256] Specifically, the server identifies information using specific HTML tags or class names and retrieves the required data.

[0257] Step 4:

[0258] The server stores the latest papers in a list.

[0259] The server stores only the most recent publication dates from the extracted paper information in a list.

[0260] Input: Extracted paper information

[0261] Output: Latest paper information list

[0262] Specifically, the server compares the publication dates and filters out only the newest ones before adding them to the list.

[0263] Step 5:

[0264] The server uses a generative AI model to summarize the main points.

[0265] The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the collected information.

[0266] Input: Latest paper information (abstract)

[0267] Output: Abridged paper abstract

[0268] Specifically, the server sends a prompt to the generative AI model and obtains the generated summary.

[0269] Example prompt: "Summarize the following abstract: [abstract text]"

[0270] Step 6:

[0271] The server applies a text classification model to extract insights.

[0272] The server applies text classification models such as BERT and RoBERTa to extract deep insights from the summarized information.

[0273] Input: Abridged article abstract

[0274] Output: Extracted insights

[0275] Specifically, the server inputs the summary text into a text classification model and classifies it into specific findings or categories.

[0276] Step 7:

[0277] The server stores the findings in a database and updates the existing database.

[0278] The server stores the extracted knowledge in a MySQL or PostgreSQL database and updates the existing database as needed.

[0279] Input: Extracted knowledge

[0280] Output: Updated database

[0281] Specifically, the server executes SQL queries to insert or update new findings into the database.

[0282] Step 8:

[0283] The user types a question in natural language.

[0284] A user uses a terminal to input a question to the system in natural language.

[0285] Input: Natural language question

[0286] Output: User question data

[0287] Specifically, the user inputs a question into the terminal using a keyboard or mouse and sends it to the system.

[0288] Step 9:

[0289] The server analyzes the user's question.

[0290] The server uses natural language processing libraries such as SpaCy and NLTK to parse the user's questions.

[0291] Input: User question data

[0292] Output: Parsed question data

[0293] Specifically, the server tokenizes the question text and extracts key elements.

[0294] Step 10:

[0295] The server generates answers using a question-answering generation model.

[0296] The server uses a generative AI model to search the database and generate the most relevant answers.

[0297] Input: Parsed question data

[0298] Output: The generated answer

[0299] Specifically, the server asks questions to the generative AI model and creates an appropriate response.

[0300] Example prompt: "What is the latest treatment for cancer?"

[0301] Step 11:

[0302] The server uses an emotion engine to analyze the user's emotions.

[0303] The server uses natural language understanding services such as IBM Watson to analyze emotions from the content of the user's questions.

[0304] Input: User question data

[0305] Output: Parsed emotion data

[0306] Specifically, the server analyzes the question text to determine the user's emotional state.

[0307] Step 12:

[0308] The server adjusts the answer based on the analysis results.

[0309] Based on the emotion analysis results, the server adjusts the response according to the user's emotional state.

[0310] Input: Generated answers, parsed sentiment data

[0311] Output: Adjusted answer

[0312] Specifically, the server changes the tone and content of the response depending on the results of the sentiment analysis.

[0313] For example: If the user is feeling anxious, provide a gentle response such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[0314] Step 13:

[0315] The server provides the final answer to the user.

[0316] The server sends the final adjusted answer to the user's terminal.

[0317] Input: Adjusted Answer

[0318] Output: The final answer provided to the user

[0319] Specifically, the server displays the generated answer on the user's terminal so that the user can confirm the information.

[0320] (Application example 2)

[0321] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0322] Conventional systems have had difficulty in quickly acquiring the latest medical knowledge and making it easy for doctors to access. Furthermore, when a user asks a question to the system, the system does not provide a response that takes into account the user's emotions, resulting in a poor user experience. The present invention aims to provide a system that efficiently collects the latest medical knowledge, allows doctors to easily access it, analyzes the user's emotions, and provides appropriate answers accordingly.

[0323] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0324] In this invention, the server includes means for collecting paper information, means for analyzing the collected paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for recognizing emotions and adjusting answers in accordance with the user's emotions. This enables the latest medical knowledge to be quickly obtained, doctors to easily access that knowledge, and further improves the user experience by providing responses that take the user's emotions into consideration.

[0325] Key Word Definitions

[0326] "Paper information" refers to data such as the title, abstract, and publication date of medical and scientific papers collected from specific websites and databases.

[0327] "Means of collection" refers to the technical means of obtaining the required data from external sources using web crawlers or HTTP requests.

[0328] The "means for analyzing and generating a summary" refers to an artificial intelligence model or algorithm for analyzing the acquired text data and generating a summary that succinctly expresses its content.

[0329] "Means for extracting new knowledge" refers to data analysis techniques and text classification models that can be used to gain new discoveries and insights from summarized information.

[0330] "Means for updating the database" refers to the technology used to register new data obtained through collection and analysis into an existing database and keep it up to date.

[0331] A "natural language question" is a question that a user asks a system in human language, and is information that is input in text format.

[0332] A "means for searching a database and generating an appropriate answer" is an algorithm or system that searches information in a database in response to a user's question and generates the most relevant answer based on that information.

[0333] "Means for recognizing emotions and adjusting responses according to the user's emotions" refers to technology that analyzes emotions from the user's input and provides an appropriate response that corresponds to the emotions the user is feeling.

[0334] MODE FOR CARRYING OUT THE INVENTION

[0335] The present invention provides a system that allows doctors to quickly access the latest medical knowledge and provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions. The system includes the following means:

[0336] 1. How to collect information on papers

[0337] The server sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the latest paper pages. At this time, the server collects the data using the requests module.

[0338] 2. Summary generation means

[0339] The acquired HTML data is parsed using BeautifulSoup to extract paper information (title, abstract, publication date), and then a pipeline from the transformers library is used to concisely summarize the abstracts of the collected papers.

[0340] 3. Means of extracting new knowledge

[0341] Based on the summarized information, a text classification model is applied to extract deeper insights, which are then stored in a database to update the existing database.

[0342] 4. Natural Language Question-Answering Methods

[0343] When a doctor (user) enters a question into the system in natural language, the server analyzes the question and uses a question-answering generation model to search the database and generate the most relevant answer.

[0344] 5. Emotion recognition and response regulation measures

[0345] The emotion engine analyzes the user's emotions from the content of the question and adjusts the response accordingly. For example, if the user is feeling anxious or impatient, the system can adjust its response to be gentler.

[0346] Specific examples

[0347] For example, if a user asks, "What are the latest anti-cancer treatments?", the emotion engine can detect the user's anxiety and respond in a reassuring tone, such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[0348] Prompt Sentence Examples

[0349] An example of a prompt that might actually be entered into the system would be something like:

[0350] "I'd like to know more about the latest smartphone features."

[0351] Based on these prompts, the server searches the collected database, generates relevant information, and provides it to the user, analyzing the user's emotions and adjusting the response as necessary.

[0352] This will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately, while the user-friendly interface will also reduce stress in the medical field.

[0353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0354] Program processing steps

[0355] Step 1:

[0356] The server sends an HTTP request to a website that provides a specific medical paper. As input, it uses the website URL and necessary HTTP header information. As output, it obtains the HTML data of the latest paper page. In this case, it uses the requests module to obtain the data.

[0357] Step 2:

[0358] The server uses BeautifulSoup to analyze the HTML data and extract the paper information (title, abstract, publication date). The input is the HTML data obtained in step 1, and the output is a list of paper information. This list includes the title, abstract, and publication date of each paper.

[0359] Step 3:

[0360] The server uses a pipeline of the transformers library to concisely summarize the abstracts of the collected papers. The input is the paper information extracted in step 2, especially the abstracts. The output is a summarized text, which is more concise and easier to understand than the original data.

[0361] Step 4:

[0362] The server applies a text classification model to the summarized information to extract new insights. The input is the summary information obtained in step 3, and the output is the extracted insights. This classification model extracts specific medical insights and key points.

[0363] Step 5:

[0364] The server saves the extracted knowledge in the existing database and updates it to the latest state. The input is the new knowledge obtained in step 4, and the output is the updated database. This ensures that the database always contains the latest information.

[0365] Step 6:

[0366] A user uses a terminal to input a question in natural language into the system. The input is the question typed by the user, and the output is text in natural language format. For example, a question might be input: "What is the latest anti-cancer drug treatment?"

[0367] Step 7:

[0368] The server uses a question-answering generation model to search the database and generate the most relevant answer. The input is the user's question from step 6 and the updated database from step 5, and the output is the generated answer, which gives the user the information they are looking for.

[0369] Step 8:

[0370] The server uses an emotion engine to analyze the emotion from the user's question and adjusts the answer based on the analysis results. The input is the user's question in step 6 and the answer generated in step 7, and the output is a final answer that takes the emotion into consideration. For example, if the user expresses anxiety, the server will provide an answer in a gentle tone.

[0371] Step 9:

[0372] The server provides the final answer to the user. The input is the answer adjusted in step 8, and the output is the response message displayed on the terminal. This allows the user to get the appropriate answer to their question.

[0373] 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.

[0374] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0375] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0376] [Second embodiment]

[0377] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0378] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0379] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0380] 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.

[0381] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0382] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0383] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0384] 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.

[0385] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0386] 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.

[0387] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0388] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0389] This invention is a system that allows doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[0390] The server first accesses a designated website to collect paper information. Through this access, it obtains the content of the most recent paper page and saves it as data. Next, the server analyzes the obtained web page to extract the paper title, abstract, and publication date. From this extraction result, it saves information on the most recent papers published within the last 24 hours in a list.

[0391] The server analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper and extract new findings from the summaries, making it possible to automatically identify the new findings that are most important to physicians from a vast amount of information.

[0392] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, and always stores the latest knowledge. The database is updated automatically, so that the latest information is provided when doctors access it.

[0393] A user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question and searches the database to find the most relevant information. It uses a question-answering generation model to generate an appropriate answer and provides it to the user.

[0394] When a doctor wants to learn about new treatments or the latest research findings on a particular disease, this system allows them to access accurate information in a much shorter time than traditional manual searches. For example, the server collects and analyzes the latest research papers on the effectiveness of new anticancer drugs and stores the summaries and new findings in a database. Based on this data, the system generates specific answers, such as "New anticancer drugs are likely to be more effective than existing ones," and provides them to the user.

[0395] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[0396] The above is an embodiment of this system.

[0397] The processing flow will be explained below.

[0398] Step 1:

[0399] The server sends an HTTP request to the specified website to retrieve the HTML content of the latest paper page, which is then used for further analysis.

[0400] Step 2:

[0401] The server uses a library such as BeautifulSoup to parse the retrieved HTML content and extracts specific HTML elements containing paper information (title, abstract, publication date).

[0402] Step 3:

[0403] The server checks the publication date of the extracted paper information, determines that it is the most recent, and adds only the most recent papers to the list.

[0404] Step 4:

[0405] The server inputs the collected paper information into a generative AI model and processes it to generate a summary, which concisely presents the key points.

[0406] Step 5:

[0407] The server applies a text classification model to the generated summary to extract new insights, which are new discoveries or conclusions drawn from the content of the paper.

[0408] Step 6:

[0409] The server stores the extracted knowledge in a database and updates the existing database, ensuring that the database always contains the latest information.

[0410] Step 7:

[0411] The user (doctor) inputs a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[0412] Step 8:

[0413] The server analyzes the input question, searches the database, and generates the most relevant answer using a question-answering generation model.

[0414] Step 9:

[0415] The server then provides the generated answers to the user, allowing doctors to quickly obtain accurate information based on the latest medical knowledge.

[0416] The above is the flow of specific processing steps of the program of this system.

[0417] Example 1

[0418] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0419] In the medical field, new papers are published daily, making it difficult for doctors to quickly access the latest treatments and research results. Traditional manual paper searching and summarization takes time and effort, often interfering with medical practice. Furthermore, the sheer volume of information increases the likelihood of important findings being overlooked. Therefore, there is a need for a system that can quickly extract important new findings from the vast amount of paper information and provide appropriate answers.

[0420] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0421] In this invention, the server includes means for collecting research paper information, means for analyzing the collected research paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for providing the generated answers to users. This allows doctors to quickly and accurately access the latest knowledge in the medical field, significantly reducing the time and effort required for doctors to gather information.

[0422] "Paper information" refers to information on documents that describe academic research results, particularly those related to the medical field.

[0423] "Collection methods" refers to the processes and technologies used to automatically obtain the required data from designated sources.

[0424] "Means of analysis" refers to the processes and techniques used to organize collected data and extract useful information.

[0425] A "summary generator" refers to a technique or process that extracts the main points from detailed information and presents them in a concise form.

[0426] "New insight extraction" refers to techniques and processes for discovering new, previously unknown information from analyzed and summarized data.

[0427] "Means of updating the database" refers to the technology and process for adding new information acquired to an existing information aggregation system and keeping it up to date.

[0428] A "natural language question" refers to a human inquiry written in a common language and input in a form that can be understood by a computer system.

[0429] "Database search methods" refers to techniques and processes for searching within existing information aggregation systems to quickly find specific information.

[0430] "Means for generating appropriate answers" refers to techniques and processes that create the most appropriate response to a user's question based on information retrieved from a database.

[0431] A "generative model" refers to an algorithm or system that uses artificial intelligence or machine learning to generate new data and insights.

[0432] MODE FOR CARRYING OUT THE INVENTION

[0433] This invention is a system that enables doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[0434] First, the server accesses the specified website and collects the paper information. Specifically, the server runs a regularly scheduled job to retrieve and save the HTML content of the paper page by sending an HTTP request to the specified URL. For example, the data can be retrieved using the Python requests library.

[0435] The server then reads the saved HTML files and extracts the paper titles, abstracts, and publication dates using an HTML parsing library such as BeautifulSoup, which then stores the most recent papers published in the last 24 hours in a list.

[0436] The server then analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper. It then extracts new findings from the summaries. This process makes it possible to automatically identify the new findings that are most important to doctors from a vast amount of information.

[0437] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, so the latest knowledge is always stored. The database is updated automatically, so that the latest information is always available when doctors access it.

[0438] Next, the user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question, searches the database to find the most relevant information, and uses a question-answering generation model to generate an appropriate answer, which is then provided to the user.

[0439] For example, consider a case where a user asks, "I want to know the latest research results regarding the effectiveness of new anticancer drugs." The server accesses websites to collect the latest research papers, summarizes the main points of the papers using a generative AI model, and extracts new findings. The data is then stored in a database, and specific information such as "New anticancer drugs are likely to be more effective than conventional ones" is generated as an answer to the question and provided to the user.

[0440] This allows doctors to access the latest medical knowledge quickly and accurately, significantly reducing the time and effort required to gather information.

[0441] Here is an example prompt:

[0442] "Collect papers on recent anti-cancer drug research, summarize their key points, and store them in a database. Extract new findings and provide them to physicians as up-to-date information."

[0443] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[0444] The above is an embodiment of the present invention.

[0445] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0446] Step 1:

[0447] The server accesses the specified website and collects paper information. The server runs a periodically scheduled job, sending an HTTP request to the specified URL. The input is the specified URL and the request, and the output is the HTML content of the paper page. This content is saved as a file.

[0448] Step 2:

[0449] The server reads the saved HTML file and extracts the paper title, abstract, and publication date. The server uses an HTML parsing library such as BeautifulSoup to parse the specified HTML file. It has the HTML file to parse as input and gets the extracted paper title, abstract, and publication date as output. It saves this information in a temporary list.

[0450] Step 3:

[0451] The server filters the extracted paper data for the latest paper information published within the last 24 hours. The input is a list of extracted paper data, and the output is a filtered list of the latest papers. This information is used in the next step.

[0452] Step 4:

[0453] The server analyzes the filtered paper information and generates summaries using a generative AI model. The input is a list of the latest papers, and the output is a summary of each paper. A generative AI model (e.g., GPT-3) is used to create summaries of papers.

[0454] Step 5:

[0455] The server extracts new findings from the generated summaries. The input is the summarized paper information, and the output is the extraction of new findings. The server uses a generative AI model to identify and extract important findings.

[0456] Step 6:

[0457] The server updates the database with the extracted new knowledge. It takes new knowledge as input and gets an updated database as output. It integrates it with existing data and keeps it up to date.

[0458] Step 7:

[0459] A user (doctor) inputs a question in natural language into the system through a terminal. The user's question is the input, and the server receives the question text as the output.

[0460] Step 8:

[0461] The server analyzes the user's question and searches the database for relevant information. The input is the user's question and the contents of the database, and the output is a search for and retrieves highly relevant paper information.

[0462] Step 9:

[0463] The server uses a question-and-answer generation model to generate appropriate answers based on relevant information. The input is highly relevant paper information, and the output is generated answer text. The server uses the question-and-answer generation model to generate appropriate answers.

[0464] Step 10:

[0465] The server provides the generated answer to the user. The input is the generated answer text, and the output is the answer displayed on the user's terminal. The user can then confirm the answer on the terminal.

[0466] (Application example 1)

[0467] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] In medical settings and physical stores such as pharmacies, it is extremely important for doctors and pharmacists to quickly access the latest medical knowledge and research results. However, when searching manually, it takes a lot of time and effort to find the appropriate information from the vast amount of information, which can reduce the efficiency of medical treatment and medication provision. An effective solution to this problem is needed.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0470] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new findings based on the summaries, a means for updating the database with the extracted findings, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for providing information using smart glasses in a physical store, thereby enabling doctors and pharmacists to quickly and efficiently access the latest medical knowledge and research results.

[0471] "Means for collecting publication information" refers to the techniques and processes used to obtain the latest scientific publication information from designated websites on the Internet.

[0472] "Means for analyzing collected paper information and generating summaries" refers to the technology and process for automatically analyzing the content of acquired scientific papers, extracting important information, and summarizing it briefly.

[0473] "Means for extracting new knowledge from summaries" refers to techniques and processes for extracting new discoveries and important knowledge from the generated summaries.

[0474] "Means for updating the database with extracted knowledge" refers to the techniques and processes for periodically storing new extracted knowledge in a database and keeping the information up to date.

[0475] "Means for searching a database in response to a natural language question and generating an appropriate answer" refers to the technology or process for understanding a question entered by a user in natural language, searching a database for relevant information, and generating an appropriate answer.

[0476] "Means for providing information using smart glasses in physical stores" refers to the technology and process for displaying and providing the information required by users in real time through smart glasses.

[0477] This invention relates to a system that allows doctors and pharmacists in brick-and-mortar stores to quickly and efficiently access the latest medical knowledge and research results using smart glasses. The system collects and analyzes research paper information, updates the results to a database, and provides relevant, up-to-date information when users input questions in natural language.

[0478] The server first collects the latest paper information from websites, using the requests and BeautifulSoup libraries to retrieve information such as the paper title, abstract, and publication date from specified sites on the Internet.

[0479] Next, the server uses a generative AI model (e.g., OpenAI's text-davinci-002 model) to analyze the collected paper information and generate a summary. To extract new insights from this summary, the server asks the model to summarize using a prompt sentence.

[0480] For example, use the following prompt statement:

[0481] Please briefly summarize the following and extract any new findings:

[0482] (Abstract of the paper)

[0483] New findings are automatically added to the database, ensuring that it is always up-to-date.

[0484] When a user accesses the system using smart glasses, they can input a question in natural language, such as "What are the latest anti-cancer drug treatments?" This question is sent to the server, where it is analyzed using a generative AI model and relevant information is retrieved from a database.

[0485] The generated answers are displayed on the smart glasses, providing the user with the information they need in real time.

[0486] "Generate the best answer to the following questions:

[0487] Question: (User Question)

[0488] Database: (Article database)

[0489] This will enable doctors and pharmacists using smart glasses to quickly access the latest medical knowledge and significantly improve the efficiency of medical treatment and drug provision. This system will reduce the burden on medical facilities and enable the provision of high-quality medical services.

[0490] The hardware used refers to smart glasses, and the software used includes the requests library, the BeautifulSoup library, and OpenAI's generative AI model (text-davinci-002 model).

[0491] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0492] Step 1:

[0493] The server accesses specified websites on the Internet to collect the latest paper information. It uses the requests library to retrieve the content of the webpage and the BeautifulSoup library to parse the HTML. It receives the URL of the specified website as input and extracts data including the paper title, abstract, and publication date as output.

[0494] Step 2:

[0495] The server analyzes the collected paper information and generates summaries. Here, it receives the collected paper abstracts as input and generates summaries using a generative AI model (OpenAI's text-davinci-002 model). Specifically, it creates a prompt sentence and asks the model to summarize. The output is the summarized text.

[0496] Step 3:

[0497] The server analyzes the generated summary and extracts new insights. It receives the summary generated in step 2 as input and again uses the generative AI model to extract new insights. Specifically, it creates a prompt sentence and asks the model to extract new insights. The output is the extracted new insights.

[0498] Step 4:

[0499] The server updates the database with the new findings extracted. It takes the new findings extracted in step 3 as input and stores them in the database. This keeps the database up to date. The output is the updated database.

[0500] Step 5:

[0501] A user accesses the system using smart glasses and inputs a question in natural language. The user's question is sent to the server through the smart glasses. The input is the user's natural language question, and the output is the question data sent to the server.

[0502] Step 6:

[0503] The server analyzes the user's question and searches the database. Using the question received in step 5 as input, it analyzes it using the generative AI model and searches for relevant information in the database. Specifically, it creates an appropriate prompt sentence and asks the model to generate the best answer. The output is the generated answer text.

[0504] Step 7:

[0505] The server sends the generated answer to the user's smart glasses. The answer generated in step 6 is received as input and displayed on the smart glasses. This allows the user to obtain the required information in real time. The output is the answer displayed on the user's glasses.

[0506] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0507] The present invention is a system that allows doctors to quickly access the latest medical knowledge, and further provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions.

[0508] The server first sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the most recent paper page. It then analyzes this HTML data to extract paper information (title, abstract, publication date), and saves only the most recent papers from the extracted data in a list.

[0509] The server then uses a generative AI model to concisely summarize the collected papers' abstracts. Based on this summarized information, a text classification model is applied to extract deeper insights. The extracted insights are stored in a database, updating the existing database. This ensures that the database always contains the latest medical knowledge.

[0510] When a doctor (user) enters a question into the system in natural language, the server analyzes the question. Using a question-answering generation model, it searches the database and generates the most relevant answer. Then, an emotion engine analyzes the emotion in the user's question and adjusts the answer based on the analysis results. For example, if the user is feeling anxious or impatient, the system can adjust its response to use a gentler tone.

[0511] The server provides the generated answer to the user. At this time, the emotion engine takes into account the user's current emotional state and adjusts the content and format of the response. For example, if the question is, "What is the latest anti-cancer drug treatment?", the emotion engine will sense the user's anxiety and respond in a reassuring tone. For example, it might say, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[0512] This system not only allows doctors to easily obtain the latest medical information, but also provides a better user experience by providing responses that take users' emotions into consideration, making it a powerful tool for reducing stress in medical settings and supporting quick and accurate decision-making.

[0513] The above is a specific embodiment for carrying out the present invention. It is expected that this system will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately.

[0514] The processing flow will be explained below.

[0515] Step 1:

[0516] The server sends an HTTP request to the designated medical paper provider site to obtain the HTML data of the latest paper page, thereby collecting the content of the web page containing paper information.

[0517] Step 2:

[0518] The server uses a library such as BeautifulSoup to parse the retrieved HTML data, extracting information such as the paper title, abstract, and publication date, and stores this data in a temporary list.

[0519] Step 3:

[0520] The server checks the publication date of the extracted paper information and determines whether it is the most recent publication date within the last 24 hours. Only the most recent paper information is kept in the list, and older ones are removed.

[0521] Step 4:

[0522] The server inputs the collected summaries into a generative AI model, such as T5 or BERT, to generate a concise summary, extracting the main points of the summaries and summarizing them briefly.

[0523] Step 5:

[0524] The server then inputs the generated summaries into a text classification model to extract new insights. The model identifies new medically important findings and conclusions from the summaries and converts them into a database-ready format.

[0525] Step 6:

[0526] The server stores the extracted new findings in a database and integrates them with existing data, ensuring that the database always maintains the latest medical knowledge.

[0527] Step 7:

[0528] The user (doctor) uses a terminal to input a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[0529] Step 8:

[0530] The server analyzes the user's question and generates an appropriate answer using a question-answering generation model, which searches a database and creates an answer based on the most relevant information.

[0531] Step 9:

[0532] The server uses an emotion engine to analyze emotions from the user's questions, for example, recognizing emotions when the user's input indicates impatience or anxiety.

[0533] Step 10:

[0534] The server adjusts the tone and content of the generated response based on the analysis results of the emotion engine. For example, it provides a response in a reassuring tone to a user who is feeling anxious.

[0535] Step 11:

[0536] The server then provides the final answer to the user via the terminal, allowing the user to quickly obtain the latest medical information in a manner that takes their feelings into consideration.

[0537] The above is the flow of specific processing steps of the program of this system.

[0538] Example 2

[0539] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0540] Conventional medical information systems have limitations in their ability to quickly and accurately provide the latest research information, and they lack the ability to respond in a way that takes users' feelings into consideration. This means that it takes time for medical professionals to obtain the information they need, which increases their stress.

[0541] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0542] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new knowledge based on the summaries, a means for updating the database with the extracted knowledge, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for analyzing the user's emotions and adjusting the answers, thereby enabling not only fast and accurate provision of medical information but also responses that correspond to the user's emotions.

[0543] "Paper information" refers to information about medical papers, such as the title, abstract, and publication date.

[0544] "Means of collection" refers to a combination of software and hardware used to obtain paper information from a specific website.

[0545] "Means for analysis" refers to the algorithms and software used to analyze the acquired paper information.

[0546] The "means for generating a summary" refers to software such as a generative AI model that concisely summarizes the gist of the collected and analyzed paper information.

[0547] "Insight extraction tools" are software such as text classification models that discover new insights from summarized information.

[0548] "Means for updating the database" refers to software and hardware for adding and updating the extracted new knowledge to the existing database.

[0549] "Means for searching a database in response to a question in natural language and generating an appropriate answer" refers to software such as a question-answering generation model that understands a question in natural language from a user, searches a database, and generates a relevant answer.

[0550] "Means for analyzing emotions and adjusting responses" refers to software such as an emotion engine that analyzes the content of the user's question and their emotional state and adjusts the response accordingly.

[0551] The present invention relates to a system for quickly and accurately acquiring medical information and generating a response that takes into consideration the user's feelings. The system is composed of a server, a terminal, and a user.

[0552] System Components

[0553] 1. Server

[0554] The server is responsible for collecting and analyzing paper information from medical paper websites. The server uses the following software and hardware:

[0555] Sending an HTTP request: Use the requests library to access a specific website and retrieve HTML data.

[0556] HTML Data Analysis: The obtained HTML data is analyzed using the Beautiful Soup library to extract the paper title, abstract, and publication date.

[0557] Generative AI models: Use generative AI models such as OpenAI GPT-4 to compactly summarize the collected key points.

[0558] Text classification models, such as BERT and RoBERTa, to extract deeper insights from summaries.

[0559] Database Management System (DBMS): For example, MySQL or PostgreSQL are used to store and update the extracted findings in a database.

[0560] 2. Terminal

[0561] The terminal provides the user interface and is the means by which users access the system and input questions. The terminal communicates with the server using a browser or dedicated application.

[0562] 3. Users

[0563] Users, primarily physicians, use the system to obtain the latest medical information and ask questions in natural language. Users access the system through terminals.

[0564] Specific examples of system operation

[0565] 1. The server sends an HTTP request to a medical article website to retrieve the HTML data for the latest article page. For example, use the requests library to access https: / / example-medical-site.com / latest-articles.

[0566] Example prompt: "Get the latest medical papers."

[0567] 2. The server analyzes the HTML data obtained using the Beautiful Soup library and extracts the necessary paper information (title, abstract, publication date).

[0568] Example prompt: "Extract paper information from HTML data."

[0569] 3. From the paper information extracted by the server, only the papers with the most recent publication dates are saved in the list.

[0570] 4. The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the extracted key points.

[0571] Example prompt: "Summarize the following abstract: [abstract text]"

[0572] 5. Apply text classification models, such as BERT or RoBERTa, to the summarized information to extract deeper insights.

[0573] 6. The server stores the extracted knowledge in a database such as MySQL or PostgreSQL and updates the existing database.

[0574] 7. A user uses a terminal to input a question into the system in natural language: "What is the latest anti-cancer drug treatment?"

[0575] 8. The server parses the user's question using a natural language processing library such as SpaCy or NLTK.

[0576] 9. The server uses the question-answering generation model to search the database and generate the most relevant answer.

[0577] Example prompt: "What is the latest treatment for cancer?"

[0578] 10. The server uses an emotion engine (for example, IBM Watson's natural language understanding service) to analyze the emotion from the user's question.

[0579] 11. The server adjusts the response based on the sentiment analysis results. For example, if the user is feeling anxious, the response will be gentler.

[0580] Example prompt: "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[0581] 12. The server provides the final adjusted answer to the user.

[0582] Through the above system configuration and processing procedures, the present invention enables doctors to quickly and accurately obtain the latest medical information and provides responses that take users' emotions into consideration, thereby reducing stress in medical settings and providing a better user experience.

[0583] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0584] Step 1:

[0585] The server sends an HTTP request to a medical research website.

[0586] Specifically, the server uses the requests library to access a specific medical article website (e.g., https: / / example-medical-site.com / latest-articles).

[0587] Input: Website URL

[0588] Output: HTML data of the latest paper page

[0589] The server retrieves the HTML data and proceeds to the next parsing step.

[0590] Step 2:

[0591] Parse the HTML data received by the server.

[0592] The server uses the Beautiful Soup library to convert the retrieved HTML data into a format that is easy to parse.

[0593] Input: Retrieved HTML data

[0594] Output: Parsable HTML tree structure

[0595] Specifically, the server analyzes the HTML tags and identifies the parts that contain the paper information.

[0596] Step 3:

[0597] The server extracts the paper information (title, abstract, publication date).

[0598] The server extracts specific information (title, abstract, publication date) from the parsed HTML tree structure.

[0599] Input: Parsed HTML tree structure

[0600] Output: Extracted paper information (title, abstract, publication date)

[0601] Specifically, the server identifies information using specific HTML tags or class names and retrieves the required data.

[0602] Step 4:

[0603] The server stores the latest papers in a list.

[0604] The server stores only the most recent publication dates from the extracted paper information in a list.

[0605] Input: Extracted paper information

[0606] Output: Latest paper information list

[0607] Specifically, the server compares the publication dates and filters out only the newest ones before adding them to the list.

[0608] Step 5:

[0609] The server uses a generative AI model to summarize the main points.

[0610] The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the collected information.

[0611] Input: Latest paper information (abstract)

[0612] Output: Abridged paper abstract

[0613] Specifically, the server sends a prompt to the generative AI model and obtains the generated summary.

[0614] Example prompt: "Summarize the following abstract: [abstract text]"

[0615] Step 6:

[0616] The server applies a text classification model to extract insights.

[0617] The server applies text classification models such as BERT and RoBERTa to extract deep insights from the summarized information.

[0618] Input: Abridged article abstract

[0619] Output: Extracted insights

[0620] Specifically, the server inputs the summary text into a text classification model and classifies it into specific findings or categories.

[0621] Step 7:

[0622] The server stores the findings in a database and updates the existing database.

[0623] The server stores the extracted knowledge in a MySQL or PostgreSQL database and updates the existing database as needed.

[0624] Input: Extracted knowledge

[0625] Output: Updated database

[0626] Specifically, the server executes SQL queries to insert or update new findings into the database.

[0627] Step 8:

[0628] The user types a question in natural language.

[0629] A user uses a terminal to input a question to the system in natural language.

[0630] Input: Natural language question

[0631] Output: User question data

[0632] Specifically, the user inputs a question into the terminal using a keyboard or mouse and sends it to the system.

[0633] Step 9:

[0634] The server analyzes the user's question.

[0635] The server uses natural language processing libraries such as SpaCy and NLTK to parse the user's questions.

[0636] Input: User question data

[0637] Output: Parsed question data

[0638] Specifically, the server tokenizes the question text and extracts key elements.

[0639] Step 10:

[0640] The server generates answers using a question-answering generation model.

[0641] The server uses a generative AI model to search the database and generate the most relevant answers.

[0642] Input: Parsed question data

[0643] Output: The generated answer

[0644] Specifically, the server asks questions to the generative AI model and creates an appropriate response.

[0645] Example prompt: "What is the latest treatment for cancer?"

[0646] Step 11:

[0647] The server uses an emotion engine to analyze the user's emotions.

[0648] The server uses natural language understanding services such as IBM Watson to analyze emotions from the content of the user's questions.

[0649] Input: User question data

[0650] Output: Parsed emotion data

[0651] Specifically, the server analyzes the question text to determine the user's emotional state.

[0652] Step 12:

[0653] The server adjusts the answer based on the analysis results.

[0654] Based on the emotion analysis results, the server adjusts the response according to the user's emotional state.

[0655] Input: Generated answers, parsed sentiment data

[0656] Output: Adjusted answer

[0657] Specifically, the server changes the tone and content of the response depending on the results of the sentiment analysis.

[0658] For example: If the user is feeling anxious, provide a gentle response such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[0659] Step 13:

[0660] The server provides the final answer to the user.

[0661] The server sends the final adjusted answer to the user's terminal.

[0662] Input: Adjusted Answer

[0663] Output: The final answer provided to the user

[0664] Specifically, the server displays the generated answer on the user's terminal so that the user can confirm the information.

[0665] (Application example 2)

[0666] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0667] Conventional systems have had difficulty in quickly acquiring the latest medical knowledge and making it easy for doctors to access. Furthermore, when a user asks a question to the system, the system does not provide a response that takes into account the user's emotions, resulting in a poor user experience. The present invention aims to provide a system that efficiently collects the latest medical knowledge, allows doctors to easily access it, analyzes the user's emotions, and provides appropriate answers accordingly.

[0668] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0669] In this invention, the server includes means for collecting paper information, means for analyzing the collected paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for recognizing emotions and adjusting answers in accordance with the user's emotions. This enables the latest medical knowledge to be quickly obtained, doctors to easily access that knowledge, and further improves the user experience by providing responses that take the user's emotions into consideration.

[0670] Key Word Definitions

[0671] "Paper information" refers to data such as the title, abstract, and publication date of medical and scientific papers collected from specific websites and databases.

[0672] "Means of collection" refers to the technical means of obtaining the required data from external sources using web crawlers or HTTP requests.

[0673] The "means for analyzing and generating a summary" refers to an artificial intelligence model or algorithm for analyzing the acquired text data and generating a summary that succinctly expresses its content.

[0674] "Means for extracting new knowledge" refers to data analysis techniques and text classification models that can be used to gain new discoveries and insights from summarized information.

[0675] "Means for updating the database" refers to the technology used to register new data obtained through collection and analysis into an existing database and keep it up to date.

[0676] A "natural language question" is a question that a user asks a system in human language, and is information that is input in text format.

[0677] A "means for searching a database and generating an appropriate answer" is an algorithm or system that searches information in a database in response to a user's question and generates the most relevant answer based on that information.

[0678] "Means for recognizing emotions and adjusting responses according to the user's emotions" refers to technology that analyzes emotions from the user's input and provides an appropriate response that corresponds to the emotions the user is feeling.

[0679] MODE FOR CARRYING OUT THE INVENTION

[0680] The present invention provides a system that allows doctors to quickly access the latest medical knowledge and provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions. The system includes the following means:

[0681] 1. How to collect information on papers

[0682] The server sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the latest paper pages. At this time, the server collects the data using the requests module.

[0683] 2. Summary generation means

[0684] The acquired HTML data is parsed using BeautifulSoup to extract paper information (title, abstract, publication date), and then a pipeline from the transformers library is used to concisely summarize the abstracts of the collected papers.

[0685] 3. Means of extracting new knowledge

[0686] Based on the summarized information, a text classification model is applied to extract deeper insights, which are then stored in a database to update the existing database.

[0687] 4. Natural Language Question-Answering Methods

[0688] When a doctor (user) enters a question into the system in natural language, the server analyzes the question and uses a question-answering generation model to search the database and generate the most relevant answer.

[0689] 5. Emotion recognition and response regulation measures

[0690] The emotion engine analyzes the user's emotions from the content of the question and adjusts the response accordingly. For example, if the user is feeling anxious or impatient, the system can adjust its response to be gentler.

[0691] Specific examples

[0692] For example, if a user asks, "What are the latest anti-cancer treatments?", the emotion engine can detect the user's anxiety and respond in a reassuring tone, such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[0693] Prompt Sentence Examples

[0694] An example of a prompt that might actually be entered into the system would be something like:

[0695] "I'd like to know more about the latest smartphone features."

[0696] Based on these prompts, the server searches the collected database, generates relevant information, and provides it to the user, analyzing the user's emotions and adjusting the response as necessary.

[0697] This will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately, while the user-friendly interface will also reduce stress in the medical field.

[0698] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0699] Program processing steps

[0700] Step 1:

[0701] The server sends an HTTP request to a website that provides a specific medical paper. As input, it uses the website URL and necessary HTTP header information. As output, it obtains the HTML data of the latest paper page. In this case, it uses the requests module to obtain the data.

[0702] Step 2:

[0703] The server uses BeautifulSoup to analyze the HTML data and extract the paper information (title, abstract, publication date). The input is the HTML data obtained in step 1, and the output is a list of paper information. This list includes the title, abstract, and publication date of each paper.

[0704] Step 3:

[0705] The server uses a pipeline of the transformers library to concisely summarize the abstracts of the collected papers. The input is the paper information extracted in step 2, especially the abstracts. The output is a summarized text, which is more concise and easier to understand than the original data.

[0706] Step 4:

[0707] The server applies a text classification model to the summarized information to extract new insights. The input is the summary information obtained in step 3, and the output is the extracted insights. This classification model extracts specific medical insights and key points.

[0708] Step 5:

[0709] The server saves the extracted knowledge in the existing database and updates it to the latest state. The input is the new knowledge obtained in step 4, and the output is the updated database. This ensures that the database always contains the latest information.

[0710] Step 6:

[0711] A user uses a terminal to input a question in natural language into the system. The input is the question typed by the user, and the output is text in natural language format. For example, a question might be input: "What is the latest anti-cancer drug treatment?"

[0712] Step 7:

[0713] The server uses a question-answering generation model to search the database and generate the most relevant answer. The input is the user's question from step 6 and the updated database from step 5, and the output is the generated answer, which gives the user the information they are looking for.

[0714] Step 8:

[0715] The server uses an emotion engine to analyze the emotion from the user's question and adjusts the answer based on the analysis results. The input is the user's question in step 6 and the answer generated in step 7, and the output is a final answer that takes the emotion into consideration. For example, if the user expresses anxiety, the server will provide an answer in a gentle tone.

[0716] Step 9:

[0717] The server provides the final answer to the user. The input is the answer adjusted in step 8, and the output is the response message displayed on the terminal. This allows the user to get the appropriate answer to their question.

[0718] 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.

[0719] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0721] [Third embodiment]

[0722] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0723] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0724] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0725] 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.

[0726] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0727] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0728] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0729] 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.

[0730] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0731] 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.

[0732] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0733] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0734] This invention is a system that allows doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[0735] The server first accesses a designated website to collect paper information. Through this access, it obtains the content of the most recent paper page and saves it as data. Next, the server analyzes the obtained web page to extract the paper title, abstract, and publication date. From this extraction result, it saves information on the most recent papers published within the last 24 hours in a list.

[0736] The server analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper and extract new findings from the summaries, making it possible to automatically identify the new findings that are most important to physicians from a vast amount of information.

[0737] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, and always stores the latest knowledge. The database is updated automatically, so that the latest information is provided when doctors access it.

[0738] A user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question and searches the database to find the most relevant information. It uses a question-answering generation model to generate an appropriate answer and provides it to the user.

[0739] When a doctor wants to learn about new treatments or the latest research findings on a particular disease, this system allows them to access accurate information in a much shorter time than traditional manual searches. For example, the server collects and analyzes the latest research papers on the effectiveness of new anticancer drugs and stores the summaries and new findings in a database. Based on this data, the system generates specific answers, such as "New anticancer drugs are likely to be more effective than existing ones," and provides them to the user.

[0740] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[0741] The above is an embodiment of this system.

[0742] The processing flow will be explained below.

[0743] Step 1:

[0744] The server sends an HTTP request to the specified website to retrieve the HTML content of the latest paper page, which is then used for further analysis.

[0745] Step 2:

[0746] The server uses a library such as BeautifulSoup to parse the retrieved HTML content and extracts specific HTML elements containing paper information (title, abstract, publication date).

[0747] Step 3:

[0748] The server checks the publication date of the extracted paper information, determines that it is the most recent, and adds only the most recent papers to the list.

[0749] Step 4:

[0750] The server inputs the collected paper information into a generative AI model and processes it to generate a summary, which concisely presents the key points.

[0751] Step 5:

[0752] The server applies a text classification model to the generated summary to extract new insights, which are new discoveries or conclusions drawn from the content of the paper.

[0753] Step 6:

[0754] The server stores the extracted knowledge in a database and updates the existing database, ensuring that the database always contains the latest information.

[0755] Step 7:

[0756] The user (doctor) inputs a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[0757] Step 8:

[0758] The server analyzes the input question, searches the database, and generates the most relevant answer using a question-answering generation model.

[0759] Step 9:

[0760] The server then provides the generated answers to the user, allowing doctors to quickly obtain accurate information based on the latest medical knowledge.

[0761] The above is the flow of specific processing steps of the program of this system.

[0762] Example 1

[0763] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0764] In the medical field, new papers are published daily, making it difficult for doctors to quickly access the latest treatments and research results. Traditional manual paper searching and summarization takes time and effort, often interfering with medical practice. Furthermore, the sheer volume of information increases the likelihood of important findings being overlooked. Therefore, there is a need for a system that can quickly extract important new findings from the vast amount of paper information and provide appropriate answers.

[0765] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0766] In this invention, the server includes means for collecting research paper information, means for analyzing the collected research paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for providing the generated answers to users. This allows doctors to quickly and accurately access the latest knowledge in the medical field, significantly reducing the time and effort required for doctors to gather information.

[0767] "Paper information" refers to information on documents that describe academic research results, particularly those related to the medical field.

[0768] "Collection methods" refers to the processes and technologies used to automatically obtain the required data from designated sources.

[0769] "Means of analysis" refers to the processes and techniques used to organize collected data and extract useful information.

[0770] A "summary generator" refers to a technique or process that extracts the main points from detailed information and presents them in a concise form.

[0771] "New insight extraction" refers to techniques and processes for discovering new, previously unknown information from analyzed and summarized data.

[0772] "Means of updating the database" refers to the technology and process for adding new information acquired to an existing information aggregation system and keeping it up to date.

[0773] A "natural language question" refers to a human inquiry written in a common language and input in a form that can be understood by a computer system.

[0774] "Database search methods" refers to techniques and processes for searching within existing information aggregation systems to quickly find specific information.

[0775] "Means for generating appropriate answers" refers to techniques and processes that create the most appropriate response to a user's question based on information retrieved from a database.

[0776] A "generative model" refers to an algorithm or system that uses artificial intelligence or machine learning to generate new data and insights.

[0777] MODE FOR CARRYING OUT THE INVENTION

[0778] This invention is a system that enables doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[0779] First, the server accesses the specified website and collects the paper information. Specifically, the server runs a regularly scheduled job to retrieve and save the HTML content of the paper page by sending an HTTP request to the specified URL. For example, the data can be retrieved using the Python requests library.

[0780] The server then reads the saved HTML files and extracts the paper titles, abstracts, and publication dates using an HTML parsing library such as BeautifulSoup, which then stores the most recent papers published in the last 24 hours in a list.

[0781] The server then analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper. It then extracts new findings from the summaries. This process makes it possible to automatically identify the new findings that are most important to doctors from a vast amount of information.

[0782] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, so the latest knowledge is always stored. The database is updated automatically, so that the latest information is always available when doctors access it.

[0783] Next, the user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question, searches the database to find the most relevant information, and uses a question-answering generation model to generate an appropriate answer, which is then provided to the user.

[0784] For example, consider a case where a user asks, "I want to know the latest research results regarding the effectiveness of new anticancer drugs." The server accesses websites to collect the latest research papers, summarizes the main points of the papers using a generative AI model, and extracts new findings. The data is then stored in a database, and specific information such as "New anticancer drugs are likely to be more effective than conventional ones" is generated as an answer to the question and provided to the user.

[0785] This allows doctors to access the latest medical knowledge quickly and accurately, significantly reducing the time and effort required to gather information.

[0786] Here is an example prompt:

[0787] "Collect papers on recent anti-cancer drug research, summarize their key points, and store them in a database. Extract new findings and provide them to physicians as up-to-date information."

[0788] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[0789] The above is an embodiment of the present invention.

[0790] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0791] Step 1:

[0792] The server accesses the specified website and collects paper information. The server runs a periodically scheduled job, sending an HTTP request to the specified URL. The input is the specified URL and the request, and the output is the HTML content of the paper page. This content is saved as a file.

[0793] Step 2:

[0794] The server reads the saved HTML file and extracts the paper title, abstract, and publication date. The server uses an HTML parsing library such as BeautifulSoup to parse the specified HTML file. It has the HTML file to parse as input and gets the extracted paper title, abstract, and publication date as output. It saves this information in a temporary list.

[0795] Step 3:

[0796] The server filters the extracted paper data for the latest paper information published within the last 24 hours. The input is a list of extracted paper data, and the output is a filtered list of the latest papers. This information is used in the next step.

[0797] Step 4:

[0798] The server analyzes the filtered paper information and generates summaries using a generative AI model. The input is a list of the latest papers, and the output is a summary of each paper. A generative AI model (e.g., GPT-3) is used to create summaries of papers.

[0799] Step 5:

[0800] The server extracts new findings from the generated summaries. The input is the summarized paper information, and the output is the extraction of new findings. The server uses a generative AI model to identify and extract important findings.

[0801] Step 6:

[0802] The server updates the database with the extracted new knowledge. It takes new knowledge as input and gets an updated database as output. It integrates it with existing data and keeps it up to date.

[0803] Step 7:

[0804] A user (doctor) inputs a question in natural language into the system through a terminal. The user's question is the input, and the server receives the question text as the output.

[0805] Step 8:

[0806] The server analyzes the user's question and searches the database for relevant information. The input is the user's question and the contents of the database, and the output is a search for and retrieves highly relevant paper information.

[0807] Step 9:

[0808] The server uses a question-and-answer generation model to generate appropriate answers based on relevant information. The input is highly relevant paper information, and the output is generated answer text. The server uses the question-and-answer generation model to generate appropriate answers.

[0809] Step 10:

[0810] The server provides the generated answer to the user. The input is the generated answer text, and the output is the answer displayed on the user's terminal. The user can then confirm the answer on the terminal.

[0811] (Application example 1)

[0812] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0813] In medical settings and physical stores such as pharmacies, it is extremely important for doctors and pharmacists to quickly access the latest medical knowledge and research results. However, when searching manually, it takes a lot of time and effort to find the appropriate information from the vast amount of information, which can reduce the efficiency of medical treatment and medication provision. An effective solution to this problem is needed.

[0814] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0815] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new findings based on the summaries, a means for updating the database with the extracted findings, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for providing information using smart glasses in a physical store, thereby enabling doctors and pharmacists to quickly and efficiently access the latest medical knowledge and research results.

[0816] "Means for collecting publication information" refers to the techniques and processes used to obtain the latest scientific publication information from designated websites on the Internet.

[0817] "Means for analyzing collected paper information and generating summaries" refers to the technology and process for automatically analyzing the content of acquired scientific papers, extracting important information, and summarizing it briefly.

[0818] "Means for extracting new knowledge from summaries" refers to techniques and processes for extracting new discoveries and important knowledge from the generated summaries.

[0819] "Means for updating the database with extracted knowledge" refers to the techniques and processes for periodically storing new extracted knowledge in a database and keeping the information up to date.

[0820] "Means for searching a database in response to a natural language question and generating an appropriate answer" refers to the technology or process for understanding a question entered by a user in natural language, searching a database for relevant information, and generating an appropriate answer.

[0821] "Means for providing information using smart glasses in physical stores" refers to the technology and process for displaying and providing the information required by users in real time through smart glasses.

[0822] This invention relates to a system that allows doctors and pharmacists in brick-and-mortar stores to quickly and efficiently access the latest medical knowledge and research results using smart glasses. The system collects and analyzes research paper information, updates the results to a database, and provides relevant, up-to-date information when users input questions in natural language.

[0823] The server first collects the latest paper information from websites, using the requests and BeautifulSoup libraries to retrieve information such as the paper title, abstract, and publication date from specified sites on the Internet.

[0824] Next, the server uses a generative AI model (e.g., OpenAI's text-davinci-002 model) to analyze the collected paper information and generate a summary. To extract new insights from this summary, the server asks the model to summarize using a prompt sentence.

[0825] For example, use the following prompt statement:

[0826] Please briefly summarize the following and extract any new findings:

[0827] (Abstract of the paper)

[0828] New findings are automatically added to the database, ensuring that it is always up-to-date.

[0829] When a user accesses the system using smart glasses, they can input a question in natural language, such as "What are the latest anti-cancer drug treatments?" This question is sent to the server, where it is analyzed using a generative AI model and relevant information is retrieved from a database.

[0830] The generated answers are displayed on the smart glasses, providing the user with the information they need in real time.

[0831] "Generate the best answer to the following questions:

[0832] Question: (User Question)

[0833] Database: (Article database)

[0834] This will enable doctors and pharmacists using smart glasses to quickly access the latest medical knowledge and significantly improve the efficiency of medical treatment and drug provision. This system will reduce the burden on medical facilities and enable the provision of high-quality medical services.

[0835] The hardware used refers to smart glasses, and the software used includes the requests library, the BeautifulSoup library, and OpenAI's generative AI model (text-davinci-002 model).

[0836] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0837] Step 1:

[0838] The server accesses specified websites on the Internet to collect the latest paper information. It uses the requests library to retrieve the content of the webpage and the BeautifulSoup library to parse the HTML. It receives the URL of the specified website as input and extracts data including the paper title, abstract, and publication date as output.

[0839] Step 2:

[0840] The server analyzes the collected paper information and generates summaries. Here, it receives the collected paper abstracts as input and generates summaries using a generative AI model (OpenAI's text-davinci-002 model). Specifically, it creates a prompt sentence and asks the model to summarize. The output is the summarized text.

[0841] Step 3:

[0842] The server analyzes the generated summary and extracts new insights. It receives the summary generated in step 2 as input and again uses the generative AI model to extract new insights. Specifically, it creates a prompt sentence and asks the model to extract new insights. The output is the extracted new insights.

[0843] Step 4:

[0844] The server updates the database with the new findings extracted. It takes the new findings extracted in step 3 as input and stores them in the database. This keeps the database up to date. The output is the updated database.

[0845] Step 5:

[0846] A user accesses the system using smart glasses and inputs a question in natural language. The user's question is sent to the server through the smart glasses. The input is the user's natural language question, and the output is the question data sent to the server.

[0847] Step 6:

[0848] The server analyzes the user's question and searches the database. Using the question received in step 5 as input, it analyzes it using the generative AI model and searches for relevant information in the database. Specifically, it creates an appropriate prompt sentence and asks the model to generate the best answer. The output is the generated answer text.

[0849] Step 7:

[0850] The server sends the generated answer to the user's smart glasses. The answer generated in step 6 is received as input and displayed on the smart glasses. This allows the user to obtain the required information in real time. The output is the answer displayed on the user's glasses.

[0851] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0852] The present invention is a system that allows doctors to quickly access the latest medical knowledge, and further provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions.

[0853] The server first sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the most recent paper page. It then analyzes this HTML data to extract paper information (title, abstract, publication date), and saves only the most recent papers from the extracted data in a list.

[0854] The server then uses a generative AI model to concisely summarize the collected papers' abstracts. Based on this summarized information, a text classification model is applied to extract deeper insights. The extracted insights are stored in a database, updating the existing database. This ensures that the database always contains the latest medical knowledge.

[0855] When a doctor (user) enters a question into the system in natural language, the server analyzes the question. Using a question-answering generation model, it searches the database and generates the most relevant answer. Then, an emotion engine analyzes the emotion in the user's question and adjusts the answer based on the analysis results. For example, if the user is feeling anxious or impatient, the system can adjust its response to use a gentler tone.

[0856] The server provides the generated answer to the user. At this time, the emotion engine takes into account the user's current emotional state and adjusts the content and format of the response. For example, if the question is, "What is the latest anti-cancer drug treatment?", the emotion engine will sense the user's anxiety and respond in a reassuring tone. For example, it might say, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[0857] This system not only allows doctors to easily obtain the latest medical information, but also provides a better user experience by providing responses that take users' emotions into consideration, making it a powerful tool for reducing stress in medical settings and supporting quick and accurate decision-making.

[0858] The above is a specific embodiment for carrying out the present invention. It is expected that this system will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately.

[0859] The processing flow will be explained below.

[0860] Step 1:

[0861] The server sends an HTTP request to the designated medical paper provider site to obtain the HTML data of the latest paper page, thereby collecting the content of the web page containing paper information.

[0862] Step 2:

[0863] The server uses a library such as BeautifulSoup to parse the retrieved HTML data, extracting information such as the paper title, abstract, and publication date, and stores this data in a temporary list.

[0864] Step 3:

[0865] The server checks the publication date of the extracted paper information and determines whether it is the most recent publication date within the last 24 hours. Only the most recent paper information is kept in the list, and older ones are removed.

[0866] Step 4:

[0867] The server inputs the collected summaries into a generative AI model, such as T5 or BERT, to generate a concise summary, extracting the main points of the summaries and summarizing them briefly.

[0868] Step 5:

[0869] The server then inputs the generated summaries into a text classification model to extract new insights. The model identifies new medically important findings and conclusions from the summaries and converts them into a database-ready format.

[0870] Step 6:

[0871] The server stores the extracted new findings in a database and integrates them with existing data, ensuring that the database always maintains the latest medical knowledge.

[0872] Step 7:

[0873] The user (doctor) uses a terminal to input a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[0874] Step 8:

[0875] The server analyzes the user's question and generates an appropriate answer using a question-answering generation model, which searches a database and creates an answer based on the most relevant information.

[0876] Step 9:

[0877] The server uses an emotion engine to analyze emotions from the user's questions, for example, recognizing emotions when the user's input indicates impatience or anxiety.

[0878] Step 10:

[0879] The server adjusts the tone and content of the generated response based on the analysis results of the emotion engine. For example, it provides a response in a reassuring tone to a user who is feeling anxious.

[0880] Step 11:

[0881] The server then provides the final answer to the user via the terminal, allowing the user to quickly obtain the latest medical information in a manner that takes their feelings into consideration.

[0882] The above is the flow of specific processing steps of the program of this system.

[0883] Example 2

[0884] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0885] Conventional medical information systems have limitations in their ability to quickly and accurately provide the latest research information, and they lack the ability to respond in a way that takes users' feelings into consideration. This means that it takes time for medical professionals to obtain the information they need, which increases their stress.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0887] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new knowledge based on the summaries, a means for updating the database with the extracted knowledge, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for analyzing the user's emotions and adjusting the answers, thereby enabling not only fast and accurate provision of medical information but also responses that correspond to the user's emotions.

[0888] "Paper information" refers to information about medical papers, such as the title, abstract, and publication date.

[0889] "Means of collection" refers to a combination of software and hardware used to obtain paper information from a specific website.

[0890] "Means for analysis" refers to the algorithms and software used to analyze the acquired paper information.

[0891] The "means for generating a summary" refers to software such as a generative AI model that concisely summarizes the gist of the collected and analyzed paper information.

[0892] "Insight extraction tools" are software such as text classification models that discover new insights from summarized information.

[0893] "Means for updating the database" refers to software and hardware for adding and updating the extracted new knowledge to the existing database.

[0894] "Means for searching a database in response to a question in natural language and generating an appropriate answer" refers to software such as a question-answering generation model that understands a question in natural language from a user, searches a database, and generates a relevant answer.

[0895] "Means for analyzing emotions and adjusting responses" refers to software such as an emotion engine that analyzes the content of the user's question and their emotional state and adjusts the response accordingly.

[0896] The present invention relates to a system for quickly and accurately acquiring medical information and generating a response that takes into consideration the user's feelings. The system is composed of a server, a terminal, and a user.

[0897] System Components

[0898] 1. Server

[0899] The server is responsible for collecting and analyzing paper information from medical paper websites. The server uses the following software and hardware:

[0900] Sending an HTTP request: Use the requests library to access a specific website and retrieve HTML data.

[0901] HTML Data Analysis: The obtained HTML data is analyzed using the Beautiful Soup library to extract the paper title, abstract, and publication date.

[0902] Generative AI models: Use generative AI models such as OpenAI GPT-4 to compactly summarize the collected key points.

[0903] Text classification models, such as BERT and RoBERTa, to extract deeper insights from summaries.

[0904] Database Management System (DBMS): For example, MySQL or PostgreSQL are used to store and update the extracted findings in a database.

[0905] 2. Terminal

[0906] The terminal provides the user interface and is the means by which users access the system and input questions. The terminal communicates with the server using a browser or dedicated application.

[0907] 3. Users

[0908] Users, primarily physicians, use the system to obtain the latest medical information and ask questions in natural language. Users access the system through terminals.

[0909] Specific examples of system operation

[0910] 1. The server sends an HTTP request to a medical article website to retrieve the HTML data for the latest article page. For example, use the requests library to access https: / / example-medical-site.com / latest-articles.

[0911] Example prompt: "Get the latest medical papers."

[0912] 2. The server analyzes the HTML data obtained using the Beautiful Soup library and extracts the necessary paper information (title, abstract, publication date).

[0913] Example prompt: "Extract paper information from HTML data."

[0914] 3. From the paper information extracted by the server, only the papers with the most recent publication dates are saved in the list.

[0915] 4. The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the extracted key points.

[0916] Example prompt: "Summarize the following abstract: [abstract text]"

[0917] 5. Apply text classification models, such as BERT or RoBERTa, to the summarized information to extract deeper insights.

[0918] 6. The server stores the extracted knowledge in a database such as MySQL or PostgreSQL and updates the existing database.

[0919] 7. A user uses a terminal to input a question into the system in natural language: "What is the latest anti-cancer drug treatment?"

[0920] 8. The server parses the user's question using a natural language processing library such as SpaCy or NLTK.

[0921] 9. The server uses the question-answering generation model to search the database and generate the most relevant answer.

[0922] Example prompt: "What is the latest treatment for cancer?"

[0923] 10. The server uses an emotion engine (for example, IBM Watson's natural language understanding service) to analyze the emotion from the user's question.

[0924] 11. The server adjusts the response based on the sentiment analysis results. For example, if the user is feeling anxious, the response will be gentler.

[0925] Example prompt: "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[0926] 12. The server provides the final adjusted answer to the user.

[0927] Through the above system configuration and processing procedures, the present invention enables doctors to quickly and accurately obtain the latest medical information and provides responses that take users' emotions into consideration, thereby reducing stress in medical settings and providing a better user experience.

[0928] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0929] Step 1:

[0930] The server sends an HTTP request to a medical research website.

[0931] Specifically, the server uses the requests library to access a specific medical article website (e.g., https: / / example-medical-site.com / latest-articles).

[0932] Input: Website URL

[0933] Output: HTML data of the latest paper page

[0934] The server retrieves the HTML data and proceeds to the next parsing step.

[0935] Step 2:

[0936] Parse the HTML data received by the server.

[0937] The server uses the Beautiful Soup library to convert the retrieved HTML data into a format that is easy to parse.

[0938] Input: Retrieved HTML data

[0939] Output: Parsable HTML tree structure

[0940] Specifically, the server analyzes the HTML tags and identifies the parts that contain the paper information.

[0941] Step 3:

[0942] The server extracts the paper information (title, abstract, publication date).

[0943] The server extracts specific information (title, abstract, publication date) from the parsed HTML tree structure.

[0944] Input: Parsed HTML tree structure

[0945] Output: Extracted paper information (title, abstract, publication date)

[0946] Specifically, the server identifies information using specific HTML tags or class names and retrieves the required data.

[0947] Step 4:

[0948] The server stores the latest papers in a list.

[0949] The server stores only the most recent publication dates from the extracted paper information in a list.

[0950] Input: Extracted paper information

[0951] Output: Latest paper information list

[0952] Specifically, the server compares the publication dates and filters out only the newest ones before adding them to the list.

[0953] Step 5:

[0954] The server uses a generative AI model to summarize the main points.

[0955] The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the collected information.

[0956] Input: Latest paper information (abstract)

[0957] Output: Abridged paper abstract

[0958] Specifically, the server sends a prompt to the generative AI model and obtains the generated summary.

[0959] Example prompt: "Summarize the following abstract: [abstract text]"

[0960] Step 6:

[0961] The server applies a text classification model to extract insights.

[0962] The server applies text classification models such as BERT and RoBERTa to extract deep insights from the summarized information.

[0963] Input: Abridged article abstract

[0964] Output: Extracted insights

[0965] Specifically, the server inputs the summary text into a text classification model and classifies it into specific findings or categories.

[0966] Step 7:

[0967] The server stores the findings in a database and updates the existing database.

[0968] The server stores the extracted knowledge in a MySQL or PostgreSQL database and updates the existing database as needed.

[0969] Input: Extracted knowledge

[0970] Output: Updated database

[0971] Specifically, the server executes SQL queries to insert or update new findings into the database.

[0972] Step 8:

[0973] The user types a question in natural language.

[0974] A user uses a terminal to input a question to the system in natural language.

[0975] Input: Natural language question

[0976] Output: User question data

[0977] Specifically, the user inputs a question into the terminal using a keyboard or mouse and sends it to the system.

[0978] Step 9:

[0979] The server analyzes the user's question.

[0980] The server uses natural language processing libraries such as SpaCy and NLTK to parse the user's questions.

[0981] Input: User question data

[0982] Output: Parsed question data

[0983] Specifically, the server tokenizes the question text and extracts key elements.

[0984] Step 10:

[0985] The server generates answers using a question-answering generation model.

[0986] The server uses a generative AI model to search the database and generate the most relevant answers.

[0987] Input: Parsed question data

[0988] Output: The generated answer

[0989] Specifically, the server asks questions to the generative AI model and creates an appropriate response.

[0990] Example prompt: "What is the latest treatment for cancer?"

[0991] Step 11:

[0992] The server uses an emotion engine to analyze the user's emotions.

[0993] The server uses natural language understanding services such as IBM Watson to analyze emotions from the content of the user's questions.

[0994] Input: User question data

[0995] Output: Parsed emotion data

[0996] Specifically, the server analyzes the question text to determine the user's emotional state.

[0997] Step 12:

[0998] The server adjusts the answer based on the analysis results.

[0999] Based on the emotion analysis results, the server adjusts the response according to the user's emotional state.

[1000] Input: Generated answers, parsed sentiment data

[1001] Output: Adjusted answer

[1002] Specifically, the server changes the tone and content of the response depending on the results of the sentiment analysis.

[1003] For example: If the user is feeling anxious, provide a gentle response such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[1004] Step 13:

[1005] The server provides the final answer to the user.

[1006] The server sends the final adjusted answer to the user's terminal.

[1007] Input: Adjusted Answer

[1008] Output: The final answer provided to the user

[1009] Specifically, the server displays the generated answer on the user's terminal so that the user can confirm the information.

[1010] (Application example 2)

[1011] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1012] Conventional systems have had difficulty in quickly acquiring the latest medical knowledge and making it easy for doctors to access. Furthermore, when a user asks a question to the system, the system does not provide a response that takes into account the user's emotions, resulting in a poor user experience. The present invention aims to provide a system that efficiently collects the latest medical knowledge, allows doctors to easily access it, analyzes the user's emotions, and provides appropriate answers accordingly.

[1013] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1014] In this invention, the server includes means for collecting paper information, means for analyzing the collected paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for recognizing emotions and adjusting answers in accordance with the user's emotions. This enables the latest medical knowledge to be quickly obtained, doctors to easily access that knowledge, and further improves the user experience by providing responses that take the user's emotions into consideration.

[1015] Key Word Definitions

[1016] "Paper information" refers to data such as the title, abstract, and publication date of medical and scientific papers collected from specific websites and databases.

[1017] "Means of collection" refers to the technical means of obtaining the required data from external sources using web crawlers or HTTP requests.

[1018] The "means for analyzing and generating a summary" refers to an artificial intelligence model or algorithm for analyzing the acquired text data and generating a summary that succinctly expresses its content.

[1019] "Means for extracting new knowledge" refers to data analysis techniques and text classification models that can be used to gain new discoveries and insights from summarized information.

[1020] "Means for updating the database" refers to the technology used to register new data obtained through collection and analysis into an existing database and keep it up to date.

[1021] A "natural language question" is a question that a user asks a system in human language, and is information that is input in text format.

[1022] A "means for searching a database and generating an appropriate answer" is an algorithm or system that searches information in a database in response to a user's question and generates the most relevant answer based on that information.

[1023] "Means for recognizing emotions and adjusting responses according to the user's emotions" refers to technology that analyzes emotions from the user's input and provides an appropriate response that corresponds to the emotions the user is feeling.

[1024] MODE FOR CARRYING OUT THE INVENTION

[1025] The present invention provides a system that allows doctors to quickly access the latest medical knowledge and provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions. The system includes the following means:

[1026] 1. How to collect information on papers

[1027] The server sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the latest paper pages. At this time, the server collects the data using the requests module.

[1028] 2. Summary generation means

[1029] The acquired HTML data is parsed using BeautifulSoup to extract paper information (title, abstract, publication date), and then a pipeline from the transformers library is used to concisely summarize the abstracts of the collected papers.

[1030] 3. Means of extracting new knowledge

[1031] Based on the summarized information, a text classification model is applied to extract deeper insights, which are then stored in a database to update the existing database.

[1032] 4. Natural Language Question-Answering Methods

[1033] When a doctor (user) enters a question into the system in natural language, the server analyzes the question and uses a question-answering generation model to search the database and generate the most relevant answer.

[1034] 5. Emotion recognition and response regulation measures

[1035] The emotion engine analyzes the user's emotions from the content of the question and adjusts the response accordingly. For example, if the user is feeling anxious or impatient, the system can adjust its response to be gentler.

[1036] Specific examples

[1037] For example, if a user asks, "What are the latest anti-cancer treatments?", the emotion engine can detect the user's anxiety and respond in a reassuring tone, such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[1038] Prompt Sentence Examples

[1039] An example of a prompt that might actually be entered into the system would be something like:

[1040] "I'd like to know more about the latest smartphone features."

[1041] Based on these prompts, the server searches the collected database, generates relevant information, and provides it to the user, analyzing the user's emotions and adjusting the response as necessary.

[1042] This will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately, while the user-friendly interface will also reduce stress in the medical field.

[1043] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1044] Program processing steps

[1045] Step 1:

[1046] The server sends an HTTP request to a website that provides a specific medical paper. As input, it uses the website URL and necessary HTTP header information. As output, it obtains the HTML data of the latest paper page. In this case, it uses the requests module to obtain the data.

[1047] Step 2:

[1048] The server uses BeautifulSoup to analyze the HTML data and extract the paper information (title, abstract, publication date). The input is the HTML data obtained in step 1, and the output is a list of paper information. This list includes the title, abstract, and publication date of each paper.

[1049] Step 3:

[1050] The server uses a pipeline of the transformers library to concisely summarize the abstracts of the collected papers. The input is the paper information extracted in step 2, especially the abstracts. The output is a summarized text, which is more concise and easier to understand than the original data.

[1051] Step 4:

[1052] The server applies a text classification model to the summarized information to extract new insights. The input is the summary information obtained in step 3, and the output is the extracted insights. This classification model extracts specific medical insights and key points.

[1053] Step 5:

[1054] The server saves the extracted knowledge in the existing database and updates it to the latest state. The input is the new knowledge obtained in step 4, and the output is the updated database. This ensures that the database always contains the latest information.

[1055] Step 6:

[1056] A user uses a terminal to input a question in natural language into the system. The input is the question typed by the user, and the output is text in natural language format. For example, a question might be input: "What is the latest anti-cancer drug treatment?"

[1057] Step 7:

[1058] The server uses a question-answering generation model to search the database and generate the most relevant answer. The input is the user's question from step 6 and the updated database from step 5, and the output is the generated answer, which gives the user the information they are looking for.

[1059] Step 8:

[1060] The server uses an emotion engine to analyze the emotion from the user's question and adjusts the answer based on the analysis results. The input is the user's question in step 6 and the answer generated in step 7, and the output is a final answer that takes the emotion into consideration. For example, if the user expresses anxiety, the server will provide an answer in a gentle tone.

[1061] Step 9:

[1062] The server provides the final answer to the user. The input is the answer adjusted in step 8, and the output is the response message displayed on the terminal. This allows the user to get the appropriate answer to their question.

[1063] 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.

[1064] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1065] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1066] [Fourth embodiment]

[1067] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1068] 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.

[1069] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1070] 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.

[1071] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1072] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1073] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1074] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1075] 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.

[1076] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1077] 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.

[1078] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1079] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1080] This invention is a system that allows doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[1081] The server first accesses a designated website to collect paper information. Through this access, it obtains the content of the most recent paper page and saves it as data. Next, the server analyzes the obtained web page to extract the paper title, abstract, and publication date. From this extraction result, it saves information on the most recent papers published within the last 24 hours in a list.

[1082] The server analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper and extract new findings from the summaries, making it possible to automatically identify the new findings that are most important to physicians from a vast amount of information.

[1083] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, and always stores the latest knowledge. The database is updated automatically, so that the latest information is provided when doctors access it.

[1084] A user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question and searches the database to find the most relevant information. It uses a question-answering generation model to generate an appropriate answer and provides it to the user.

[1085] When a doctor wants to learn about new treatments or the latest research findings on a particular disease, this system allows them to access accurate information in a much shorter time than traditional manual searches. For example, the server collects and analyzes the latest research papers on the effectiveness of new anticancer drugs and stores the summaries and new findings in a database. Based on this data, the system generates specific answers, such as "New anticancer drugs are likely to be more effective than existing ones," and provides them to the user.

[1086] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[1087] The above is an embodiment of this system.

[1088] The processing flow will be explained below.

[1089] Step 1:

[1090] The server sends an HTTP request to the specified website to retrieve the HTML content of the latest paper page, which is then used for further analysis.

[1091] Step 2:

[1092] The server uses a library such as BeautifulSoup to parse the retrieved HTML content and extracts specific HTML elements containing paper information (title, abstract, publication date).

[1093] Step 3:

[1094] The server checks the publication date of the extracted paper information, determines that it is the most recent, and adds only the most recent papers to the list.

[1095] Step 4:

[1096] The server inputs the collected paper information into a generative AI model and processes it to generate a summary, which concisely presents the key points.

[1097] Step 5:

[1098] The server applies a text classification model to the generated summary to extract new insights, which are new discoveries or conclusions drawn from the content of the paper.

[1099] Step 6:

[1100] The server stores the extracted knowledge in a database and updates the existing database, ensuring that the database always contains the latest information.

[1101] Step 7:

[1102] The user (doctor) inputs a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[1103] Step 8:

[1104] The server analyzes the input question, searches the database, and generates the most relevant answer using a question-answering generation model.

[1105] Step 9:

[1106] The server then provides the generated answers to the user, allowing doctors to quickly obtain accurate information based on the latest medical knowledge.

[1107] The above is the flow of specific processing steps of the program of this system.

[1108] Example 1

[1109] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1110] In the medical field, new papers are published daily, making it difficult for doctors to quickly access the latest treatments and research results. Traditional manual paper searching and summarization takes time and effort, often interfering with medical practice. Furthermore, the sheer volume of information increases the likelihood of important findings being overlooked. Therefore, there is a need for a system that can quickly extract important new findings from the vast amount of paper information and provide appropriate answers.

[1111] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1112] In this invention, the server includes means for collecting research paper information, means for analyzing the collected research paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for providing the generated answers to users. This allows doctors to quickly and accurately access the latest knowledge in the medical field, significantly reducing the time and effort required for doctors to gather information.

[1113] "Paper information" refers to information on documents that describe academic research results, particularly those related to the medical field.

[1114] "Collection methods" refers to the processes and technologies used to automatically obtain the required data from designated sources.

[1115] "Means of analysis" refers to the processes and techniques used to organize collected data and extract useful information.

[1116] A "summary generator" refers to a technique or process that extracts the main points from detailed information and presents them in a concise form.

[1117] "New insight extraction" refers to techniques and processes for discovering new, previously unknown information from analyzed and summarized data.

[1118] "Means of updating the database" refers to the technology and process for adding new information acquired to an existing information aggregation system and keeping it up to date.

[1119] A "natural language question" refers to a human inquiry written in a common language and input in a form that can be understood by a computer system.

[1120] "Database search methods" refers to techniques and processes for searching within existing information aggregation systems to quickly find specific information.

[1121] "Means for generating appropriate answers" refers to techniques and processes that create the most appropriate response to a user's question based on information retrieved from a database.

[1122] A "generative model" refers to an algorithm or system that uses artificial intelligence or machine learning to generate new data and insights.

[1123] MODE FOR CARRYING OUT THE INVENTION

[1124] This invention is a system that enables doctors in the medical field to quickly access the latest medical knowledge. Below, we will explain the program processing and specific examples of this system.

[1125] First, the server accesses the specified website and collects the paper information. Specifically, the server runs a regularly scheduled job to retrieve and save the HTML content of the paper page by sending an HTTP request to the specified URL. For example, the data can be retrieved using the Python requests library.

[1126] The server then reads the saved HTML files and extracts the paper titles, abstracts, and publication dates using an HTML parsing library such as BeautifulSoup, which then stores the most recent papers published in the last 24 hours in a list.

[1127] The server then analyzes the collected paper information and uses a generative AI model to concisely summarize the main points of the paper. It then extracts new findings from the summaries. This process makes it possible to automatically identify the new findings that are most important to doctors from a vast amount of information.

[1128] Based on the analysis results, the server updates the database with new findings. This database also includes previous information, so the latest knowledge is always stored. The database is updated automatically, so that the latest information is always available when doctors access it.

[1129] Next, the user (doctor) inputs a question to the system in natural language. For example, "What is the latest anti-cancer drug treatment?" The server analyzes the question, searches the database to find the most relevant information, and uses a question-answering generation model to generate an appropriate answer, which is then provided to the user.

[1130] For example, consider a case where a user asks, "I want to know the latest research results regarding the effectiveness of new anticancer drugs." The server accesses websites to collect the latest research papers, summarizes the main points of the papers using a generative AI model, and extracts new findings. The data is then stored in a database, and specific information such as "New anticancer drugs are likely to be more effective than conventional ones" is generated as an answer to the question and provided to the user.

[1131] This allows doctors to access the latest medical knowledge quickly and accurately, significantly reducing the time and effort required to gather information.

[1132] Here is an example prompt:

[1133] "Collect papers on recent anti-cancer drug research, summarize their key points, and store them in a database. Extract new findings and provide them to physicians as up-to-date information."

[1134] The system's unique feature is its ability to automatically collect and analyze information, with the latest papers being published daily. This allows it to support medical treatment based on cutting-edge knowledge at all times. It also significantly reduces the time and effort required for doctors to gather information by providing accurate answers to questions in natural language.

[1135] The above is an embodiment of the present invention.

[1136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1137] Step 1:

[1138] The server accesses the specified website and collects paper information. The server runs a periodically scheduled job, sending an HTTP request to the specified URL. The input is the specified URL and the request, and the output is the HTML content of the paper page. This content is saved as a file.

[1139] Step 2:

[1140] The server reads the saved HTML file and extracts the paper title, abstract, and publication date. The server uses an HTML parsing library such as BeautifulSoup to parse the specified HTML file. It has the HTML file to parse as input and gets the extracted paper title, abstract, and publication date as output. It saves this information in a temporary list.

[1141] Step 3:

[1142] The server filters the extracted paper data for the latest paper information published within the last 24 hours. The input is a list of extracted paper data, and the output is a filtered list of the latest papers. This information is used in the next step.

[1143] Step 4:

[1144] The server analyzes the filtered paper information and generates summaries using a generative AI model. The input is a list of the latest papers, and the output is a summary of each paper. A generative AI model (e.g., GPT-3) is used to create summaries of papers.

[1145] Step 5:

[1146] The server extracts new findings from the generated summaries. The input is the summarized paper information, and the output is the extraction of new findings. The server uses a generative AI model to identify and extract important findings.

[1147] Step 6:

[1148] The server updates the database with the extracted new knowledge. It takes new knowledge as input and gets an updated database as output. It integrates it with existing data and keeps it up to date.

[1149] Step 7:

[1150] A user (doctor) inputs a question in natural language into the system through a terminal. The user's question is the input, and the server receives the question text as the output.

[1151] Step 8:

[1152] The server analyzes the user's question and searches the database for relevant information. The input is the user's question and the contents of the database, and the output is a search for and retrieves highly relevant paper information.

[1153] Step 9:

[1154] The server uses a question-and-answer generation model to generate appropriate answers based on relevant information. The input is highly relevant paper information, and the output is generated answer text. The server uses the question-and-answer generation model to generate appropriate answers.

[1155] Step 10:

[1156] The server provides the generated answer to the user. The input is the generated answer text, and the output is the answer displayed on the user's terminal. The user can then confirm the answer on the terminal.

[1157] (Application example 1)

[1158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1159] In medical settings and physical stores such as pharmacies, it is extremely important for doctors and pharmacists to quickly access the latest medical knowledge and research results. However, when searching manually, it takes a lot of time and effort to find the appropriate information from the vast amount of information, which can reduce the efficiency of medical treatment and medication provision. An effective solution to this problem is needed.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1161] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new findings based on the summaries, a means for updating the database with the extracted findings, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for providing information using smart glasses in a physical store, thereby enabling doctors and pharmacists to quickly and efficiently access the latest medical knowledge and research results.

[1162] "Means for collecting publication information" refers to the techniques and processes used to obtain the latest scientific publication information from designated websites on the Internet.

[1163] "Means for analyzing collected paper information and generating summaries" refers to the technology and process for automatically analyzing the content of acquired scientific papers, extracting important information, and summarizing it briefly.

[1164] "Means for extracting new knowledge from summaries" refers to techniques and processes for extracting new discoveries and important knowledge from the generated summaries.

[1165] "Means for updating the database with extracted knowledge" refers to the techniques and processes for periodically storing new extracted knowledge in a database and keeping the information up to date.

[1166] "Means for searching a database in response to a natural language question and generating an appropriate answer" refers to the technology or process for understanding a question entered by a user in natural language, searching a database for relevant information, and generating an appropriate answer.

[1167] "Means for providing information using smart glasses in physical stores" refers to the technology and process for displaying and providing the information required by users in real time through smart glasses.

[1168] This invention relates to a system that allows doctors and pharmacists in brick-and-mortar stores to quickly and efficiently access the latest medical knowledge and research results using smart glasses. The system collects and analyzes research paper information, updates the results to a database, and provides relevant, up-to-date information when users input questions in natural language.

[1169] The server first collects the latest paper information from websites, using the requests and BeautifulSoup libraries to retrieve information such as the paper title, abstract, and publication date from specified sites on the Internet.

[1170] Next, the server uses a generative AI model (e.g., OpenAI's text-davinci-002 model) to analyze the collected paper information and generate a summary. To extract new insights from this summary, the server asks the model to summarize using a prompt sentence.

[1171] For example, use the following prompt statement:

[1172] Please briefly summarize the following and extract any new findings:

[1173] (Abstract of the paper)

[1174] New findings are automatically added to the database, ensuring that it is always up-to-date.

[1175] When a user accesses the system using smart glasses, they can input a question in natural language, such as "What are the latest anti-cancer drug treatments?" This question is sent to the server, where it is analyzed using a generative AI model and relevant information is retrieved from a database.

[1176] The generated answers are displayed on the smart glasses, providing the user with the information they need in real time.

[1177] "Generate the best answer to the following questions:

[1178] Question: (User Question)

[1179] Database: (Article database)

[1180] This will enable doctors and pharmacists using smart glasses to quickly access the latest medical knowledge and significantly improve the efficiency of medical treatment and drug provision. This system will reduce the burden on medical facilities and enable the provision of high-quality medical services.

[1181] The hardware used refers to smart glasses, and the software used includes the requests library, the BeautifulSoup library, and OpenAI's generative AI model (text-davinci-002 model).

[1182] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1183] Step 1:

[1184] The server accesses specified websites on the Internet to collect the latest paper information. It uses the requests library to retrieve the content of the webpage and the BeautifulSoup library to parse the HTML. It receives the URL of the specified website as input and extracts data including the paper title, abstract, and publication date as output.

[1185] Step 2:

[1186] The server analyzes the collected paper information and generates summaries. Here, it receives the collected paper abstracts as input and generates summaries using a generative AI model (OpenAI's text-davinci-002 model). Specifically, it creates a prompt sentence and asks the model to summarize. The output is the summarized text.

[1187] Step 3:

[1188] The server analyzes the generated summary and extracts new insights. It receives the summary generated in step 2 as input and again uses the generative AI model to extract new insights. Specifically, it creates a prompt sentence and asks the model to extract new insights. The output is the extracted new insights.

[1189] Step 4:

[1190] The server updates the database with the new findings extracted. It takes the new findings extracted in step 3 as input and stores them in the database. This keeps the database up to date. The output is the updated database.

[1191] Step 5:

[1192] A user accesses the system using smart glasses and inputs a question in natural language. The user's question is sent to the server through the smart glasses. The input is the user's natural language question, and the output is the question data sent to the server.

[1193] Step 6:

[1194] The server analyzes the user's question and searches the database. Using the question received in step 5 as input, it analyzes it using the generative AI model and searches for relevant information in the database. Specifically, it creates an appropriate prompt sentence and asks the model to generate the best answer. The output is the generated answer text.

[1195] Step 7:

[1196] The server sends the generated answer to the user's smart glasses. The answer generated in step 6 is received as input and displayed on the smart glasses. This allows the user to obtain the required information in real time. The output is the answer displayed on the user's glasses.

[1197] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1198] The present invention is a system that allows doctors to quickly access the latest medical knowledge, and further provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions.

[1199] The server first sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the most recent paper page. It then analyzes this HTML data to extract paper information (title, abstract, publication date), and saves only the most recent papers from the extracted data in a list.

[1200] The server then uses a generative AI model to concisely summarize the collected papers' abstracts. Based on this summarized information, a text classification model is applied to extract deeper insights. The extracted insights are stored in a database, updating the existing database. This ensures that the database always contains the latest medical knowledge.

[1201] When a doctor (user) enters a question into the system in natural language, the server analyzes the question. Using a question-answering generation model, it searches the database and generates the most relevant answer. Then, an emotion engine analyzes the emotion in the user's question and adjusts the answer based on the analysis results. For example, if the user is feeling anxious or impatient, the system can adjust its response to use a gentler tone.

[1202] The server provides the generated answer to the user. At this time, the emotion engine takes into account the user's current emotional state and adjusts the content and format of the response. For example, if the question is, "What is the latest anti-cancer drug treatment?", the emotion engine will sense the user's anxiety and respond in a reassuring tone. For example, it might say, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[1203] This system not only allows doctors to easily obtain the latest medical information, but also provides a better user experience by providing responses that take users' emotions into consideration, making it a powerful tool for reducing stress in medical settings and supporting quick and accurate decision-making.

[1204] The above is a specific embodiment for carrying out the present invention. It is expected that this system will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately.

[1205] The processing flow will be explained below.

[1206] Step 1:

[1207] The server sends an HTTP request to the designated medical paper provider site to obtain the HTML data of the latest paper page, thereby collecting the content of the web page containing paper information.

[1208] Step 2:

[1209] The server uses a library such as BeautifulSoup to parse the retrieved HTML data, extracting information such as the paper title, abstract, and publication date, and stores this data in a temporary list.

[1210] Step 3:

[1211] The server checks the publication date of the extracted paper information and determines whether it is the most recent publication date within the last 24 hours. Only the most recent paper information is kept in the list, and older ones are removed.

[1212] Step 4:

[1213] The server inputs the collected summaries into a generative AI model, such as T5 or BERT, to generate a concise summary, extracting the main points of the summaries and summarizing them briefly.

[1214] Step 5:

[1215] The server then inputs the generated summaries into a text classification model to extract new insights. The model identifies new medically important findings and conclusions from the summaries and converts them into a database-ready format.

[1216] Step 6:

[1217] The server stores the extracted new findings in a database and integrates them with existing data, ensuring that the database always maintains the latest medical knowledge.

[1218] Step 7:

[1219] The user (doctor) uses a terminal to input a question into the system in natural language, such as "What is the latest anti-cancer drug treatment?"

[1220] Step 8:

[1221] The server analyzes the user's question and generates an appropriate answer using a question-answering generation model, which searches a database and creates an answer based on the most relevant information.

[1222] Step 9:

[1223] The server uses an emotion engine to analyze emotions from the user's questions, for example, recognizing emotions when the user's input indicates impatience or anxiety.

[1224] Step 10:

[1225] The server adjusts the tone and content of the generated response based on the analysis results of the emotion engine. For example, it provides a response in a reassuring tone to a user who is feeling anxious.

[1226] Step 11:

[1227] The server then provides the final answer to the user via the terminal, allowing the user to quickly obtain the latest medical information in a manner that takes their feelings into consideration.

[1228] The above is the flow of specific processing steps of the program of this system.

[1229] Example 2

[1230] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1231] Conventional medical information systems have limitations in their ability to quickly and accurately provide the latest research information, and they lack the ability to respond in a way that takes users' feelings into consideration. This means that it takes time for medical professionals to obtain the information they need, which increases their stress.

[1232] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1233] In this invention, the server includes a means for collecting research paper information, a means for analyzing the collected research paper information and generating summaries, a means for extracting new knowledge based on the summaries, a means for updating the database with the extracted knowledge, a means for searching the database in response to questions in natural language and generating appropriate answers, and a means for analyzing the user's emotions and adjusting the answers, thereby enabling not only fast and accurate provision of medical information but also responses that correspond to the user's emotions.

[1234] "Paper information" refers to information about medical papers, such as the title, abstract, and publication date.

[1235] "Means of collection" refers to a combination of software and hardware used to obtain paper information from a specific website.

[1236] "Means for analysis" refers to the algorithms and software used to analyze the acquired paper information.

[1237] The "means for generating a summary" refers to software such as a generative AI model that concisely summarizes the gist of the collected and analyzed paper information.

[1238] "Insight extraction tools" are software such as text classification models that discover new insights from summarized information.

[1239] "Means for updating the database" refers to software and hardware for adding and updating the extracted new knowledge to the existing database.

[1240] "Means for searching a database in response to a question in natural language and generating an appropriate answer" refers to software such as a question-answering generation model that understands a question in natural language from a user, searches a database, and generates a relevant answer.

[1241] "Means for analyzing emotions and adjusting responses" refers to software such as an emotion engine that analyzes the content of the user's question and their emotional state and adjusts the response accordingly.

[1242] The present invention relates to a system for quickly and accurately acquiring medical information and generating a response that takes into consideration the user's feelings. The system is composed of a server, a terminal, and a user.

[1243] System Components

[1244] 1. Server

[1245] The server is responsible for collecting and analyzing paper information from medical paper websites. The server uses the following software and hardware:

[1246] Sending an HTTP request: Use the requests library to access a specific website and retrieve HTML data.

[1247] HTML Data Analysis: The obtained HTML data is analyzed using the Beautiful Soup library to extract the paper title, abstract, and publication date.

[1248] Generative AI models: Use generative AI models such as OpenAI GPT-4 to compactly summarize the collected key points.

[1249] Text classification models, such as BERT and RoBERTa, to extract deeper insights from summaries.

[1250] Database Management System (DBMS): For example, MySQL or PostgreSQL are used to store and update the extracted findings in a database.

[1251] 2. Terminal

[1252] The terminal provides the user interface and is the means by which users access the system and input questions. The terminal communicates with the server using a browser or dedicated application.

[1253] 3. Users

[1254] Users, primarily physicians, use the system to obtain the latest medical information and ask questions in natural language. Users access the system through terminals.

[1255] Specific examples of system operation

[1256] 1. The server sends an HTTP request to a medical article website to retrieve the HTML data for the latest article page. For example, use the requests library to access https: / / example-medical-site.com / latest-articles.

[1257] Example prompt: "Get the latest medical papers."

[1258] 2. The server analyzes the HTML data obtained using the Beautiful Soup library and extracts the necessary paper information (title, abstract, publication date).

[1259] Example prompt: "Extract paper information from HTML data."

[1260] 3. From the paper information extracted by the server, only the papers with the most recent publication dates are saved in the list.

[1261] 4. The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the extracted key points.

[1262] Example prompt: "Summarize the following abstract: [abstract text]"

[1263] 5. Apply text classification models, such as BERT or RoBERTa, to the summarized information to extract deeper insights.

[1264] 6. The server stores the extracted knowledge in a database such as MySQL or PostgreSQL and updates the existing database.

[1265] 7. A user uses a terminal to input a question into the system in natural language: "What is the latest anti-cancer drug treatment?"

[1266] 8. The server parses the user's question using a natural language processing library such as SpaCy or NLTK.

[1267] 9. The server uses the question-answering generation model to search the database and generate the most relevant answer.

[1268] Example prompt: "What is the latest treatment for cancer?"

[1269] 10. The server uses an emotion engine (for example, IBM Watson's natural language understanding service) to analyze the emotion from the user's question.

[1270] 11. The server adjusts the response based on the sentiment analysis results. For example, if the user is feeling anxious, the response will be gentler.

[1271] Example prompt: "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[1272] 12. The server provides the final adjusted answer to the user.

[1273] Through the above system configuration and processing procedures, the present invention enables doctors to quickly and accurately obtain the latest medical information and provides responses that take users' emotions into consideration, thereby reducing stress in medical settings and providing a better user experience.

[1274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1275] Step 1:

[1276] The server sends an HTTP request to a medical research website.

[1277] Specifically, the server uses the requests library to access a specific medical article website (e.g., https: / / example-medical-site.com / latest-articles).

[1278] Input: Website URL

[1279] Output: HTML data of the latest paper page

[1280] The server retrieves the HTML data and proceeds to the next parsing step.

[1281] Step 2:

[1282] Parse the HTML data received by the server.

[1283] The server uses the Beautiful Soup library to convert the retrieved HTML data into a format that is easy to parse.

[1284] Input: Retrieved HTML data

[1285] Output: Parsable HTML tree structure

[1286] Specifically, the server analyzes the HTML tags and identifies the parts that contain the paper information.

[1287] Step 3:

[1288] The server extracts the paper information (title, abstract, publication date).

[1289] The server extracts specific information (title, abstract, publication date) from the parsed HTML tree structure.

[1290] Input: Parsed HTML tree structure

[1291] Output: Extracted paper information (title, abstract, publication date)

[1292] Specifically, the server identifies information using specific HTML tags or class names and retrieves the required data.

[1293] Step 4:

[1294] The server stores the latest papers in a list.

[1295] The server stores only the most recent publication dates from the extracted paper information in a list.

[1296] Input: Extracted paper information

[1297] Output: Latest paper information list

[1298] Specifically, the server compares the publication dates and filters out only the newest ones before adding them to the list.

[1299] Step 5:

[1300] The server uses a generative AI model to summarize the main points.

[1301] The server uses a generative AI model such as OpenAI GPT-4 to concisely summarize the collected information.

[1302] Input: Latest paper information (abstract)

[1303] Output: Abridged paper abstract

[1304] Specifically, the server sends a prompt to the generative AI model and obtains the generated summary.

[1305] Example prompt: "Summarize the following abstract: [abstract text]"

[1306] Step 6:

[1307] The server applies a text classification model to extract insights.

[1308] The server applies text classification models such as BERT and RoBERTa to extract deep insights from the summarized information.

[1309] Input: Abridged article abstract

[1310] Output: Extracted insights

[1311] Specifically, the server inputs the summary text into a text classification model and classifies it into specific findings or categories.

[1312] Step 7:

[1313] The server stores the findings in a database and updates the existing database.

[1314] The server stores the extracted knowledge in a MySQL or PostgreSQL database and updates the existing database as needed.

[1315] Input: Extracted knowledge

[1316] Output: Updated database

[1317] Specifically, the server executes SQL queries to insert or update new findings into the database.

[1318] Step 8:

[1319] The user types a question in natural language.

[1320] A user uses a terminal to input a question to the system in natural language.

[1321] Input: Natural language question

[1322] Output: User question data

[1323] Specifically, the user inputs a question into the terminal using a keyboard or mouse and sends it to the system.

[1324] Step 9:

[1325] The server analyzes the user's question.

[1326] The server uses natural language processing libraries such as SpaCy and NLTK to parse the user's questions.

[1327] Input: User question data

[1328] Output: Parsed question data

[1329] Specifically, the server tokenizes the question text and extracts key elements.

[1330] Step 10:

[1331] The server generates answers using a question-answering generation model.

[1332] The server uses a generative AI model to search the database and generate the most relevant answers.

[1333] Input: Parsed question data

[1334] Output: The generated answer

[1335] Specifically, the server asks questions to the generative AI model and creates an appropriate response.

[1336] Example prompt: "What is the latest treatment for cancer?"

[1337] Step 11:

[1338] The server uses an emotion engine to analyze the user's emotions.

[1339] The server uses natural language understanding services such as IBM Watson to analyze emotions from the content of the user's questions.

[1340] Input: User question data

[1341] Output: Parsed emotion data

[1342] Specifically, the server analyzes the question text to determine the user's emotional state.

[1343] Step 12:

[1344] The server adjusts the answer based on the analysis results.

[1345] Based on the emotion analysis results, the server adjusts the response according to the user's emotional state.

[1346] Input: Generated answers, parsed sentiment data

[1347] Output: Adjusted answer

[1348] Specifically, the server changes the tone and content of the response depending on the results of the sentiment analysis.

[1349] For example: If the user is feeling anxious, provide a gentle response such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Don't worry."

[1350] Step 13:

[1351] The server provides the final answer to the user.

[1352] The server sends the final adjusted answer to the user's terminal.

[1353] Input: Adjusted Answer

[1354] Output: The final answer provided to the user

[1355] Specifically, the server displays the generated answer on the user's terminal so that the user can confirm the information.

[1356] (Application example 2)

[1357] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1358] Conventional systems have had difficulty in quickly acquiring the latest medical knowledge and making it easy for doctors to access. Furthermore, when a user asks a question to the system, the system does not provide a response that takes into account the user's emotions, resulting in a poor user experience. The present invention aims to provide a system that efficiently collects the latest medical knowledge, allows doctors to easily access it, analyzes the user's emotions, and provides appropriate answers accordingly.

[1359] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1360] In this invention, the server includes means for collecting paper information, means for analyzing the collected paper information and generating summaries, means for extracting new knowledge based on the summaries, means for updating the database with the extracted knowledge, means for searching the database in response to questions in natural language and generating appropriate answers, and means for recognizing emotions and adjusting answers in accordance with the user's emotions. This enables the latest medical knowledge to be quickly obtained, doctors to easily access that knowledge, and further improves the user experience by providing responses that take the user's emotions into consideration.

[1361] Key Word Definitions

[1362] "Paper information" refers to data such as the title, abstract, and publication date of medical and scientific papers collected from specific websites and databases.

[1363] "Means of collection" refers to the technical means of obtaining the required data from external sources using web crawlers or HTTP requests.

[1364] The "means for analyzing and generating a summary" refers to an artificial intelligence model or algorithm for analyzing the acquired text data and generating a summary that succinctly expresses its content.

[1365] "Means for extracting new knowledge" refers to data analysis techniques and text classification models that can be used to gain new discoveries and insights from summarized information.

[1366] "Means for updating the database" refers to the technology used to register new data obtained through collection and analysis into an existing database and keep it up to date.

[1367] A "natural language question" is a question that a user asks a system in human language, and is information that is input in text format.

[1368] A "means for searching a database and generating an appropriate answer" is an algorithm or system that searches information in a database in response to a user's question and generates the most relevant answer based on that information.

[1369] "Means for recognizing emotions and adjusting responses according to the user's emotions" refers to technology that analyzes emotions from the user's input and provides an appropriate response that corresponds to the emotions the user is feeling.

[1370] MODE FOR CARRYING OUT THE INVENTION

[1371] The present invention provides a system that allows doctors to quickly access the latest medical knowledge and provides a user-friendly interface by combining it with an emotion engine that recognizes the user's emotions. The system includes the following means:

[1372] 1. How to collect information on papers

[1373] The server sends an HTTP request to a website that provides specific medical papers and retrieves the HTML data of the latest paper pages. At this time, the server collects the data using the requests module.

[1374] 2. Summary generation means

[1375] The acquired HTML data is parsed using BeautifulSoup to extract paper information (title, abstract, publication date), and then a pipeline from the transformers library is used to concisely summarize the abstracts of the collected papers.

[1376] 3. Means of extracting new knowledge

[1377] Based on the summarized information, a text classification model is applied to extract deeper insights, which are then stored in a database to update the existing database.

[1378] 4. Natural Language Question-Answering Methods

[1379] When a doctor (user) enters a question into the system in natural language, the server analyzes the question and uses a question-answering generation model to search the database and generate the most relevant answer.

[1380] 5. Emotion recognition and response regulation measures

[1381] The emotion engine analyzes the user's emotions from the content of the question and adjusts the response accordingly. For example, if the user is feeling anxious or impatient, the system can adjust its response to be gentler.

[1382] Specific examples

[1383] For example, if a user asks, "What are the latest anti-cancer treatments?", the emotion engine can detect the user's anxiety and respond in a reassuring tone, such as, "Recent research shows that new anti-cancer drugs are more effective than conventional treatments. Rest assured."

[1384] Prompt Sentence Examples

[1385] An example of a prompt that might actually be entered into the system would be something like:

[1386] "I'd like to know more about the latest smartphone features."

[1387] Based on these prompts, the server searches the collected database, generates relevant information, and provides it to the user, analyzing the user's emotions and adjusting the response as necessary.

[1388] This will enable doctors to keep their knowledge up to date and respond to patients more quickly and accurately, while the user-friendly interface will also reduce stress in the medical field.

[1389] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1390] Program processing steps

[1391] Step 1:

[1392] The server sends an HTTP request to a website that provides a specific medical paper. As input, it uses the website URL and necessary HTTP header information. As output, it obtains the HTML data of the latest paper page. In this case, it uses the requests module to obtain the data.

[1393] Step 2:

[1394] The server uses BeautifulSoup to analyze the HTML data and extract the paper information (title, abstract, publication date). The input is the HTML data obtained in step 1, and the output is a list of paper information. This list includes the title, abstract, and publication date of each paper.

[1395] Step 3:

[1396] The server uses a pipeline of the transformers library to concisely summarize the abstracts of the collected papers. The input is the paper information extracted in step 2, especially the abstracts. The output is a summarized text, which is more concise and easier to understand than the original data.

[1397] Step 4:

[1398] The server applies a text classification model to the summarized information to extract new insights. The input is the summary information obtained in step 3, and the output is the extracted insights. This classification model extracts specific medical insights and key points.

[1399] Step 5:

[1400] The server saves the extracted knowledge in the existing database and updates it to the latest state. The input is the new knowledge obtained in step 4, and the output is the updated database. This ensures that the database always contains the latest information.

[1401] Step 6:

[1402] A user uses a terminal to input a question in natural language into the system. The input is the question typed by the user, and the output is text in natural language format. For example, a question might be input: "What is the latest anti-cancer drug treatment?"

[1403] Step 7:

[1404] The server uses a question-answering generation model to search the database and generate the most relevant answer. The input is the user's question from step 6 and the updated database from step 5, and the output is the generated answer, which gives the user the information they are looking for.

[1405] Step 8:

[1406] The server uses an emotion engine to analyze the emotion from the user's question and adjusts the answer based on the analysis results. The input is the user's question in step 6 and the answer generated in step 7, and the output is a final answer that takes the emotion into consideration. For example, if the user expresses anxiety, the server will provide an answer in a gentle tone.

[1407] Step 9:

[1408] The server provides the final answer to the user. The input is the answer adjusted in step 8, and the output is the response message displayed on the terminal. This allows the user to get the appropriate answer to their question.

[1409] 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.

[1410] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1411] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1412] 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.

[1413] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1414] 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.

[1415] 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).

[1416] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1417] 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."

[1418] 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.

[1419] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1420] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1421] 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.

[1422] 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.

[1423] 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.

[1424] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1425] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1426] 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.

[1427] 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.

[1428] 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, in order to avoid confusion and to 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.

[1429] 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.

[1430] The following is further disclosed regarding the above embodiment.

[1431] (Claim 1)

[1432] A means of collecting information on papers,

[1433] A means for analyzing collected paper information and generating summaries;

[1434] A means of extracting new knowledge based on summaries;

[1435] A means for updating the extracted knowledge into a database;

[1436] a means for searching a database in response to a natural language question and generating an appropriate answer;

[1437] A system including:

[1438] (Claim 2)

[1439] The system of claim 1, wherein the collected paper information is verified to be up to date.

[1440] (Claim 3)

[1441] 10. The system of claim 1, wherein the system uses a generative model to extract deep insights from summarized information.

[1442] "Example 1"

[1443] (Claim 1)

[1444] A means of collecting information on papers,

[1445] A means for analyzing collected paper information and generating summaries;

[1446] A means of extracting new knowledge based on summaries;

[1447] A means for updating the extracted knowledge into a database;

[1448] a means for searching a database in response to a natural language question and generating an appropriate answer;

[1449] means for providing the generated answer to the user;

[1450] A system including:

[1451] (Claim 2)

[1452] The system of claim 1, wherein the collected paper information is verified to be up to date.

[1453] (Claim 3)

[1454] 10. The system of claim 1, wherein the system uses a generative model to extract deep insights from summarized information.

[1455] "Application Example 1"

[1456] (Claim 1)

[1457] A means of collecting information on papers,

[1458] A means for analyzing collected paper information and generating summaries;

[1459] A means of extracting new knowledge based on summaries;

[1460] A means for updating the extracted knowledge into a database;

[1461] a means for searching a database in response to a natural language question and generating an appropriate answer;

[1462] A means for providing information using smart glasses in a physical store;

[1463] A system including:

[1464] (Claim 2)

[1465] The system of claim 1, wherein the collected paper information is verified to be up to date.

[1466] (Claim 3)

[1467] 10. The system of claim 1, wherein the system uses a generative model to extract deep insights from summarized information.

[1468] "Example 2: Combining Emotion Engines"

[1469] (Claim 1)

[1470] A means of collecting information on papers,

[1471] A means for analyzing collected paper information and generating summaries;

[1472] A means of extracting new knowledge based on summaries;

[1473] A means for updating the extracted knowledge into a database;

[1474] a means for searching a database in response to a natural language question and generating an appropriate answer;

[1475] A means for analyzing user sentiment and adjusting responses;

[1476] A system including:

[1477] (Claim 2)

[1478] The system of claim 1, wherein the collected paper information is verified to be up to date.

[1479] (Claim 3)

[1480] 10. The system of claim 1, wherein the system uses a generative model to extract deep insights from summarized information.

[1481] (Claim 4)

[1482] 10. The system of claim 1, wherein the system uses an emotion engine to analyze emotions from user input and tailor responses.

[1483] "Application example 2 when combining emotion engines"

[1484] New Claims

[1485] (Claim 1)

[1486] A means of collecting information on papers,

[1487] A means for analyzing collected paper information and generating summaries;

[1488] A means of extracting new knowledge based on summaries;

[1489] A means for updating the extracted knowledge into a database;

[1490] a means for searching a database in response to a natural language question and generating an appropriate answer;

[1491] means for recognizing emotions and tailoring responses according to the user's emotions;

[1492] A system including:

[1493] (Claim 2)

[1494] The system of claim 1, wherein the collected paper information is verified to be up to date.

[1495] (Claim 3)

[1496] 10. The system of claim 1, wherein the system uses a generative model to extract deep insights from summarized information. [Explanation of symbols]

[1497] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting information on papers, A means for analyzing collected paper information and generating summaries; A means of extracting new knowledge based on summaries; A means for updating the extracted knowledge into a database; a means for searching a database in response to a natural language question and generating an appropriate answer; A system including:

2. The system of claim 1, wherein the collected paper information is confirmed to be up-to-date.

3. The system of claim 1 , which uses a generative model to extract deep insights from summarized information.

Images