System

Abstract

A system is provided.SOLUTION: A system comprising: means for providing a user interface for entering a retrieval query; server means for receiving and analyzing the entered retrieval query; generation and AI means for retrieving relevant medical articles from a database based on the analyzed retrieval query; generation and AI means for automatically generating summaries from the retrieved articles; and means for transmitting the generated summaries from the server for display on the user interface.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] Because it is difficult for medical professionals to quickly and accurately obtain the information they need from the numerous medical papers, efficient information search and understanding is required. Medical papers contain a large amount of specialized information, and understanding them requires a great deal of time and effort. This reduces the efficiency of medical professionals' clinical practice and research activities, and there is a risk of delays in decision-making in situations where a rapid response is required. [Means for solving the problem]

[0005] The present invention provides a system including: a means for providing a user interface for inputting a search query; a server means for receiving and analyzing the input search query; a generation AI means for searching a database for relevant medical papers based on the analyzed search query; a generation AI means for automatically generating summaries from the retrieved papers; and a means for transmitting data from the server to display the generated summaries on the user interface. This allows medical professionals to efficiently and quickly access relevant medical information and easily understand it through concise summaries. The system includes a generation AI means for analyzing the search query and generating search parameters for the papers, and a generation AI means for retrieving the full text of the retrieved papers from the database and extracting key content based on the full text.

[0006] A "user interface" is an interface that allows a user to perform operations and input data to a system.

[0007] A "server" is a computer system that provides data and services over a network, and is responsible for receiving requests from clients and processing them appropriately.

[0008] A "search query" is a keyword or phrase that a user enters to search for specific information.

[0009] "Analysis" is the process of analyzing input data or information in detail and extracting meaning and patterns for a specific purpose.

[0010] "Generative AI" is a system that uses artificial intelligence techniques to generate, analyze, or process data.

[0011] A "medical paper" is an academic document that details research results and findings in the medical field.

[0012] A "database" is a collection of information organized for efficient management, searching, and retrieval of a particular type of information.

[0013] A "summary" is a shortened summary of the main content of an original document or data.

[0014] "Transmission" is the process of moving data or information from one place to another.

[0015] A "client" is a device or software that sends requests to a server and receives services or data. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] Overall system overview

[0038] This system allows medical professionals to efficiently search medical papers and quickly obtain their summaries. The system mainly consists of the following components: a user interface, a server, a generative AI, and a database.

[0039] Functions of each component

[0040] User Interface

[0041] The user interface provides a search form for the healthcare professional to enter a search query, enter a specific keyword or phrase, and click a search button, which sends the query to the server.

[0042] server

[0043] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface.

[0044] Generation AI

[0045] The generative AI searches medical databases based on the search query passed from the server. The generative AI searches for relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0046] Database

[0047] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0048] Program Operation

[0049] 1. User operations

[0050] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[0051] 2. Device Operation

[0052] The terminal sends the entered query to the server, which checks that the query is in the correct format.

[0053] 3. Server Operation

[0054] The server receives the query and passes the search parameters to the AI ​​generator, which then searches the database and selects relevant papers, up to a maximum of eight of the most relevant papers.

[0055] 4. Controlling the Generative AI

[0056] The generative AI takes the full text of the selected papers and automatically generates a summary for each one, including the main points, conclusions, and key data.

[0057] 5. Server Operation

[0058] The server formats the received data and sends it to the terminal in order to return the generated summary to the user interface.

[0059] 6. Device Operation

[0060] The terminal receives the response from the server and displays it on the user interface. Tanaka can check the displayed summaries, select the paper that interests him, and read it in more detail.

[0061] 7. User Usage

[0062] Tanaka can view the displayed summary and, if necessary, click on a link to the original text to view more detailed information. For example, if he needs more detailed data based on the summarized information, he can download the original text and read it.

[0063] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[0067] Step 2:

[0068] The device validates the entered search query, checking whether the query is properly formed and displaying an error message to the user if it is not.

[0069] Step 3:

[0070] The device sends the verified search query to the server, generating an API request and sending it to the server's specified endpoint.

[0071] Step 4:

[0072] The server receives the search query from the device, analyzes the query, and based on the analysis results, generates search parameters that require further processing by the generation AI.

[0073] Step 5:

[0074] The server passes the generated search parameters to the generation AI, which uses these parameters to search for relevant medical papers.

[0075] Step 6:

[0076] The generative AI runs search queries against medical databases to retrieve relevant papers, then selects up to eight of the most relevant papers.

[0077] Step 7:

[0078] The AI ​​takes the full text of the selected papers and automatically generates a summary for each one, including the paper's main points, conclusions, and key data.

[0079] Step 8:

[0080] The server receives the summary returned by the generation AI, formats the data for display in the user interface, and sends the formatted data back to the device in a specific format (e.g., JSON).

[0081] Step 9:

[0082] The device receives the response from the server, parses the data, and converts the formatted data into a format for display in the user interface.

[0083] Step 10:

[0084] The terminal displays the paper title, author, publication year, and abstract on the screen in a format that is easy for the user to see.

[0085] Step 11:

[0086] Users can check the displayed abstracts and click on the abstract of the paper they are interested in to view more detailed information. If necessary, they can click on the link to the original article to view more detailed information.

[0087] This series of processes allows users, who are medical professionals, to access the latest medical information quickly and efficiently, which can be useful in clinical practice and research activities.

[0088] Example 1

[0089] 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."

[0090] In today's medical field, many medical professionals are required to quickly access vast amounts of academic materials and efficiently understand their contents. However, with existing systems, the process of entering a search query, retrieving relevant materials, and generating summaries is time-consuming and laborious. Furthermore, these operations are often cumbersome and require specialized medical knowledge. This makes it difficult for medical professionals to quickly and efficiently refer to the latest medical information.

[0091] 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.

[0092] In this invention, the server includes: means for providing an operation unit for inputting a search query; control unit means for receiving and analyzing the input search query; generation AI means for searching an information storage device for relevant academic materials based on the analyzed search query; generation AI means for automatically generating summaries from the searched materials; and means for transmitting data from the control unit to display the generated summaries on the operation unit. This enables relevant academic materials to be quickly obtained based on a search query input by a medical professional, and their summaries to be automatically generated and displayed. This allows medical professionals to efficiently access the latest medical information and effectively utilize it in their daily clinical practice and research activities.

[0093] A "search query" is a keyword or phrase that a user enters to search for specific information.

[0094] The "operation unit" is a user interface that allows the user to input information and perform operations such as searches.

[0095] "Controller means" refers to a server or computer system for receiving and analyzing input search queries.

[0096] A "generative AI means" is a type of artificial intelligence that has the function of searching an information storage device based on a received search query, selecting relevant academic materials, and automatically generating a summary.

[0097] An "information storage device" is a database system that stores a huge amount of academic materials and data.

[0098] The "means for transmitting data" is a communication function for transmitting data from the control device in order to display the generated summary data on the operation unit.

[0099] "Academic materials" refers to literature related to specialized fields, such as medical papers and research reports.

[0100] A "summary" is a text that concisely summarizes the main content, conclusions, and important data of academic material.

[0101] This system allows medical professionals to efficiently search for academic materials and quickly obtain their summaries. The system mainly consists of the following components: an operating unit, a control unit, a generation AI, and an information storage unit.

[0102] Operation section

[0103] The operation unit provides a user interface for users to enter search queries. When a user enters a specific keyword or phrase into the operation unit's search form and clicks the search button, the query is sent to the control device. For example, a user might enter "COVID-19 vaccine effectiveness."

[0104] Control device

[0105] The control device receives and analyzes the search query sent from the operation unit. This analysis includes properly formatting the received search query and passing it to the generation AI. It also receives the summary results returned by the generation AI and sends the data to the operation unit. Specifically, the control device packs the data in JSON format and sends and receives the data via HTTP requests and responses.

[0106] Generation AI

[0107] The generative AI searches the information storage device based on a search query passed from the control device. It typically uses an artificial intelligence model and implements advanced natural language processing algorithms. It selects relevant academic materials and extracts up to eight of the most relevant papers. It then automatically generates a summary for each paper, including the paper's main idea, conclusions, and key data.

[0108] Information Storage Device

[0109] The information storage device is a database system that stores a vast amount of academic materials. The generative AI queries the database based on the search query to retrieve relevant materials.

[0110] Specific examples

[0111] Dr. Tanaka enters "COVID-19 vaccine effectiveness" into the search form on the control unit and clicks the search button. The query is sent to the control unit, which then sends it to the generation AI. The generation AI searches the information storage device, extracts up to eight relevant papers, and generates a summary of each paper. The summaries are sent back to the control unit, and the formatted data is displayed on the control unit. Dr. Tanaka can review the displayed summaries and select papers of interest for further reading.

[0112] Prompt Sentence Examples

[0113] "Please find and provide a summary of the latest academic literature on the effectiveness of COVID-19 vaccines."

[0114] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0116] Step 1:

[0117] A user enters a query into the search form on the control panel and clicks the search button. For example, a doctor enters "COVID-19 vaccine effectiveness."

[0118] Input: Search query "COVID-19 vaccine effectiveness"

[0119] Output: Search button click action

[0120] Specific action: The user enters a query into the search form and clicks the search button.

[0121] Step 2:

[0122] The terminal receives the entered search query, verifies that the query is properly formatted, and then transmits the query to the control device.

[0123] Input: Search query "COVID-19 vaccine effectiveness"

[0124] Output: Search query sent in HTTP request format

[0125] Specific operation: The terminal packs the query in JSON format and sends it to the control device via an HTTP request.

[0126] Step 3:

[0127] The server (controller) analyzes the received query and passes it to the generation AI as search parameters. Analysis includes understanding the content of the query and formatting it appropriately.

[0128] Input: Search query in HTTP request format

[0129] Output: Search parameters for the generation AI

[0130] What happens: The server parses the query and sends parameters to the generator AI in the following format:

[0131] json

[0132] {

[0133] "query": "COVID-19 vaccine effectiveness",

[0134] "maximum_results": 8

[0135] }

[0136] Step 4:

[0137] The generation AI receives search parameters from the server, searches the specified information storage device, selects relevant academic materials, and extracts up to eight of the most relevant materials from among them.

[0138] Input: Search parameters (query "COVID-19 vaccine effectiveness", maximum results 8)

[0139] Output: Metadata and full text of associated material

[0140] Specific operation: The generating AI searches the information storage device (database) and extracts relevant materials.

[0141] Step 5:

[0142] The generative AI takes the full text of the selected documents and automatically generates a summary for each document, including the main idea, conclusion, and key data.

[0143] Input: Metadata and full text of relevant material

[0144] Output: Summary of the material

[0145] How it works: Generative AI uses natural language processing algorithms to generate summaries of materials.

[0146] Step 6:

[0147] The server (controller) receives the summary results returned by the generation AI, formats them, and sends them to the terminal. Formatting includes converting the data into a format that is easy for users to view.

[0148] Input: Summary of material from generative AI

[0149] Output: Summary data in HTTP response format

[0150] Specific operation: The server analyzes and formats the summary results returned by the generation AI and sends them to the terminal as an HTTP response.

[0151] Step 7:

[0152] The terminal receives the summary information sent from the server and displays it on the user interface. The user can then check the displayed summaries, select the paper of interest, and view it in more detail.

[0153] Input: Summary data in HTTP response format

[0154] Output: Summary information displayed in the user interface

[0155] Specific operation: The terminal analyzes the received summary data and displays it in list format on the user interface.

[0156] This concretely shows the flow of the entire system, clarifies the input and output of each step, and allows you to understand how data is processed or calculated.

[0157] (Application example 1)

[0158] 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."

[0159] Modern factories lack a means to quickly and efficiently retrieve technical literature and research papers related to manufacturing processes and review their summaries. This results in workers spending a great deal of time and effort to obtain the necessary information, resulting in reduced productivity. Furthermore, delays in retrieving and interpreting information hinder efficient factory operations and rapid problem resolution. Therefore, there is a need for a system that allows factory workers to easily search for technical literature and quickly retrieve its summaries.

[0160] 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.

[0161] In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, means for generating AI to search a database for relevant documents based on the analyzed search query, means for automatically generating summaries from the retrieved documents, means for transmitting data to display the generated summaries on the user interface, and means for reviewing the summarized documents and providing links to display detailed information, thereby enabling factory workers to efficiently search for relevant technical documents and quickly review their summaries.

[0162] A "search query" refers to a keyword or phrase entered by a user to retrieve related literature information.

[0163] "User Interface" refers to the screen or interactive means by which a user enters a search query and interacts with the system.

[0164] "Server" refers to the computer system responsible for analyzing the received search query and passing the search parameters to the generation AI.

[0165] "Generative AI" refers to an artificial intelligence model that searches for relevant literature based on a received search query and automatically generates a summary of it.

[0166] "Database" refers to a repository that stores a vast amount of relevant bibliographic information.

[0167] An "abstract" refers to information that concisely summarizes the main points, conclusions, and important data of a document.

[0168] "Link" refers to an associated URL or reference point for further information after reviewing the abstracted literature.

[0169] The system that realizes this invention aims to enable factory workers to efficiently search technical literature and quickly obtain summaries. The system consists of the following main components: a user interface, a server, a generative AI, and a database.

[0170] Hardware and Software

[0171] Hardware

[0172] Factory robots

[0173] Embedded computers (e.g., NVIDIA Jetson Nano)

[0174] software

[0175] Operating System: Linux

[0176] Programming language: Python

[0177] Web server: Flask

[0178] Database: PostgreSQL

[0179] Generative AI model: GPT-4 (OpenAI API)

[0180] Data processing and calculation flow

[0181] 1. User operations

[0182] Factory workers use the robot's on-board touchscreen to input queries for specific technical information or research papers, such as "properties of new materials."

[0183] 2. Device Operation

[0184] The entered query is sent via a user interface to the server, which verifies that the received query is well-formed and parses it appropriately.

[0185] 3. Server Operation

[0186] The server passes the query analysis results to the generation AI, which then searches the database for relevant literature and selects the most relevant literature.

[0187] 4. Controlling the Generative AI

[0188] The generation AI retrieves the full text of the selected documents and extracts the main points, conclusions, and important data from each document to generate a summary.

[0189] 5. Server Operation

[0190] The server sends the formatted data to the terminal in order to return the generated summary to the user interface.

[0191] 6. User Interface Operation

[0192] Factory workers can view summaries via touchscreen panels and click on links to view more detailed information about documents that interest them.

[0193] Specific examples

[0194] If a factory worker wants to research the properties of a new material, he or she can enter "properties of new material" into the robot's search form. The system will then search the database for relevant technical literature and display its summary. For example,

[0195] "Research into the properties and applications of new material X"

[0196] "Heat resistance of new materials and their potential uses"

[0197] "Improved product strength through the use of new materials"

[0198] Workers can view the summary and, if they want to learn more about "Improving product strength through the use of new materials," they can click on a link to view the full text.

[0199] Prompt Sentence Examples

[0200] "Find relevant technical literature and generate summaries of them based on the following query: 'properties of new materials'. For each publication, include the main points, conclusions, and key data."

[0201] This invention allows factory workers to quickly search and obtain summaries of relevant technical literature, which can contribute to improving manufacturing processes and resolving problems.

[0202] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0203] Step 1:

[0204] User query input

[0205] Factory workers use the robot's touchscreen to input queries for specific technical information or research papers, such as "properties of a new material." Input is received from the user interface and transmitted to the server.

[0206] Step 2:

[0207] Query analysis by the server

[0208] The server parses the search query received from the user interface. First, it checks whether the received data is in the correct format, and then it parses the query to generate appropriate search parameters. The input is the query "properties of new materials," and the output is the parsed search parameters.

[0209] Step 3:

[0210] Literature search using generative AI

[0211] The server passes the generated search parameters to the generation AI, which then searches the database for relevant literature based on the search parameters. The AI ​​model (e.g., GPT-4) searches for literature according to the prompt. The input is the search parameters, and the output is a list of matching literature.

[0212] Step 4:

[0213] Full-text document acquisition and summary generation

[0214] Generative AI takes the full text of the documents retrieved through the search and generates a summary for each document. The summary includes the main idea, conclusion, and important data. The input is the full text of the document, and the output is the summarized information. Generative AI extracts the main idea, conclusion, and important data from the document and generates a summary.

[0215] Step 5:

[0216] Data formatting and transmission by the server

[0217] The server formats the summary received from the generation AI and converts it into a data format for sending back to the user interface. The server then sends the formatted data to the user interface. The input is the summarized bibliographic information, and the output is the formatted summary data.

[0218] Step 6:

[0219] Summary display in the user interface

[0220] The user interface displays the summaries received from the server on a touch panel. Factory workers check the displayed summaries and click on links for more information. The input is the summarized literature information, and the output is the summary displayed on the user interface. Clicking on a link also displays the full text of the literature for more information.

[0221] Step 7:

[0222] View user details

[0223] A factory worker clicks on a link to view detailed information about a document of interest. This displays the full text of the document, enabling deeper understanding and analysis. The input is the user's request for more information, and the output is the full text of the document.

[0224] The above processing steps allow factory personnel to efficiently search technical literature, quickly review summaries, and obtain further details.

[0225] 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.

[0226] Overall system overview

[0227] This system allows medical professionals to efficiently search for medical papers and quickly obtain their summaries. It incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on those emotions. The system mainly consists of the following components: user interface, server, generative AI, database, and emotion engine.

[0228] Functions of each component

[0229] User Interface

[0230] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[0231] server

[0232] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[0233] Generation AI

[0234] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0235] Database

[0236] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0237] Emotion Engine

[0238] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[0239] Program Operation

[0240] 1. User operations

[0241] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[0242] 2. Device Operation

[0243] The device sends the collected emotion data along with the input query to the server, which verifies that the query and emotion data are in the correct format.

[0244] 3. Server Operation

[0245] The server receives the query and emotion data, analyzes the query and the emotion data, and based on the analysis results, generates search parameters and emotion data that need further processing by the generative AI and emotion engine.

[0246] 4. Controlling the Generative AI

[0247] The generative AI uses analytical parameters to search medical databases, select relevant literature, and automatically generate summaries.

[0248] 5. Manipulating the Emotion Engine

[0249] The emotion engine complements, modifies, and optimizes generated summaries and search results based on the user's emotions. For example, if the user is feeling stressed, the emotion engine will provide a simpler and more understandable summary.

[0250] 6. Server Operation

[0251] It receives summaries returned by the generative AI and emotion engine, formats the data for display in the user interface, and sends the formatted data to the device in a specific format (e.g., JSON).

[0252] 7. Device Operation

[0253] The device receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[0254] 8. Display and Use

[0255] The user's device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the summaries and click on the paper that interests him to view detailed information. Using the summarized information, he can quickly and efficiently obtain the information he needs.

[0256] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[0257] The processing flow will be explained below.

[0258] Step 1:

[0259] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[0260] Step 2:

[0261] The device validates the entered search query and collected sentiment data to ensure they are in the proper format, and then generates an API request to send to the server.

[0262] Step 3:

[0263] The device then sends the generated API request to the server, which includes the search query and sentiment data.

[0264] Step 4:

[0265] The server receives search queries and emotion data from the device, analyzes the received data, and passes the search parameters and emotion data to the generation AI and emotion engine.

[0266] Step 5:

[0267] The generation AI uses search parameters provided by the server to search the database for relevant medical papers, selecting up to eight highly relevant papers.

[0268] Step 6:

[0269] The AI ​​retrieves the full text of the selected papers, extracts key content, and automatically generates a summary for each paper, including the main points, conclusions, and key data.

[0270] Step 7:

[0271] The emotion engine analyzes the user's emotional data and complements, corrects, and optimizes the generated summaries and search results based on that data. For example, if the user is feeling stressed, it will provide a simpler and easier-to-understand summary.

[0272] Step 8:

[0273] The server receives the summaries returned by the generative AI and emotion engine and formats the data for display in the user interface in a specific format, such as JSON.

[0274] Step 9:

[0275] The terminal receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[0276] Step 10:

[0277] The device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the abstracts and click to view more information about the paper that interests her.

[0278] Step 11:

[0279] Users can quickly obtain important information based on the optimized summary and, if necessary, click on a link to the original text to view more detailed information.

[0280] This will enable healthcare professionals, who are users, to quickly and efficiently access the latest medical information that is optimized using emotional data.

[0281] Example 2

[0282] 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."

[0283] Conventional medical paper search systems make it difficult for medical professionals to efficiently obtain the information they need. In particular, they provide uniform results without considering the user's emotional state, which can cause stress and waste time. This creates a high demand for a system that can quickly and effectively search and summarize medical papers.

[0284] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, generation AI means for searching a database for related documents based on the analyzed search query, generation AI means for automatically generating a summary from the retrieved documents, means for transmitting data from the server to display the generated summary on the user interface, and emotion engine means for recognizing user emotion data and complementing, correcting, and optimizing the summary based on the emotion. This enables more efficient and appropriate information provision while taking the user's emotional state into consideration.

[0285] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0286] A "user interface" is an interface that provides a screen or input form for a user to interact with a system.

[0287] A "server" is a computer system that receives requests from users, analyzes them, and passes appropriate data to the generative AI or emotion engine.

[0288] "Generative AI" is an artificial intelligence technology that searches for relevant literature from a database based on a search query, extracts important content from each document, and generates a summary.

[0289] A "database" is a system for storing and managing vast amounts of bibliographic information.

[0290] An "emotion engine" is a system that analyzes emotional data obtained from a user's facial expressions, voice, etc., and complements, corrects, and optimizes search results and summaries based on those emotions.

[0291] A "summary" is a compact summary that extracts the main points, conclusions, important data, etc. of a document.

[0292] "Emotion data" is information collected from facial expressions and voice to understand the user's emotional state.

[0293] MODE FOR CARRYING OUT THE INVENTION

[0294] The present invention relates to a system for medical professionals to efficiently search medical papers and quickly obtain their summaries. The system incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on the emotions. Specific embodiments of the system are described below.

[0295] System Components

[0296] The system mainly consists of the following components:

[0297] User Interface

[0298] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[0299] server

[0300] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[0301] Generation AI

[0302] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0303] Database

[0304] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0305] Emotion Engine

[0306] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[0307] System Operation

[0308] When a user enters a query into the search form, the system sends the query along with the user's emotional data to the server. The server analyzes this data and passes appropriate search parameters to the generation AI. The generation AI searches the database and generates summaries of relevant literature. The emotion engine complements, corrects, and optimizes the generated summaries and search results based on the user's emotions. The final search results and summaries are displayed on the user interface via the server.

[0309] For example, if a doctor enters a query such as "COVID-19 vaccine effectiveness" and clicks the search button, the query and the acquired emotion data are sent to the server. The server analyzes the query and emotion data and passes appropriate search parameters to the generation AI. The generation AI searches for relevant papers and generates a summary. The emotion engine analyzes the summary and optimizes it based on the user's emotion. The summarized content is then displayed in the user interface.

[0310] Prompt Sentence Examples

[0311] Below is an example of a prompt sentence to input to the generative AI model.

[0312] User query: "COVID-19 vaccine effectiveness"

[0313] User sentiment: "Tension: High"

[0314] To search for relevant medical articles and generate summaries of:

[0315] Purpose of the paper

[0316] conclusion

[0317] Important Data

[0318] Concise and easy-to-understand expression

[0319] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[0320] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0321] Step 1:

[0322] User query input and sentiment data collection

[0323] A user enters a query into a search form on their device and clicks the search button. This action causes the device to collect emotional data from facial expressions and voice using the user's camera and microphone. For example, a doctor may enter a search query such as "COVID-19 vaccine effectiveness," and emotional data may be recorded from facial expressions and tone of voice.

[0324] Input: User search query and emotional data (e.g., facial expressions, voice)

[0325] Output: Collected search queries and sentiment data

[0326] Step 2:

[0327] Sending data from the device to the server

[0328] The device checks the query entered by the user and the format of the collected emotion data, converts it into an appropriate format (e.g., JSON), and sends it to the server. For example, data is sent in the following JSON format:

[0329] json

[0330] {

[0331] "query": "COVID-19 vaccine effectiveness",

[0332] "emotion_data": {

[0333] "stress": 0.8,

[0334] "anxiety": 0.7

[0335] }

[0336] }

[0337] Input: User search query and sentiment data

[0338] Output: JSON format data sent to the server

[0339] Step 3:

[0340] Server-side query and sentiment analysis

[0341] The server analyzes the data received from the device. First, it decomposes and analyzes the query to generate search parameters. It also analyzes the emotional data to evaluate the user's emotional state, and based on the results, generates data for the generation AI and emotion engine.

[0342] Input: JSON format data sent from the terminal

[0343] Output: Parsed data to feed into generative AI and emotion engines

[0344] Step 4:

[0345] Paper search and summary generation using generative AI

[0346] The generation AI searches a database of medical papers using search parameters provided by the server. It selects relevant papers, extracts the gist, conclusions, and important data from each paper, and generates a summary. For example, it searches for multiple papers on "COVID-19 vaccine effectiveness" and generates a summary for each.

[0347] Input: Search parameters provided by the server

[0348] Output: Abstracted bibliographic information

[0349] Step 5:

[0350] Summarization optimization using emotion engine

[0351] The emotion engine analyzes the summary received from the generative AI and optimizes it based on the user's emotional state. For example, if the user is feeling stressed, it will modify the summary to make it more concise and easy to understand.

[0352] Input: Summary provided by the generative AI and user sentiment data

[0353] Output: Optimized summary information

[0354] Step 6:

[0355] Formatting and sending data from the server to the terminal

[0356] The server receives the optimized summary and formats it for display in the user interface. This formatted data might be in JSON format, for example:

[0357] json

[0358] {

[0359] "title": "COVID-19 Vaccine Effectiveness",

[0360] "authors": ["Author 1", "Author 2"],

[0361] "published_year": 2021,

[0362] "summary": "This paper is a study examining the effectiveness of COVID-19 vaccines, and its main conclusion is XXX. Key data is YYY."

[0363] }

[0364] This data is sent to the terminal.

[0365] Input: Optimized summary provided by the sentiment engine

[0366] Output: Data formatted to send to the terminal

[0367] Step 7:

[0368] Data parsing and display on the device

[0369] The device parses the data received from the server, converts it into a human-readable format, and displays it in a user interface, using HTML and CSS to format the search results so that the title, author, publication year, and abstract are easily readable.

[0370] Input: Formatted data sent from the server

[0371] Output: Search results displayed in the user interface

[0372] Step 8:

[0373] User review and use of information

[0374] Users can check the abstracts and titles of papers displayed on their devices and click on the paper they are interested in to view detailed information, allowing them to quickly and efficiently obtain the information they need and use it in their clinical practice and research activities.

[0375] Input: Search results displayed in the user interface

[0376] Output: Specific paper information that the user retrieves

[0377] (Application example 2)

[0378] 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."

[0379] Conventional information search systems have the problem of not being able to quickly provide optimal information that users desire because they do not take into account the emotional state of the user. Furthermore, the lack of emotion-based information optimization makes it difficult to improve user satisfaction. The purpose of this invention is to solve these problems.

[0380] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing emotion data along with an input search query, generation AI means for searching a database for related information based on the analyzed search query and emotion data, generation AI means for automatically generating a summary from the searched information, and means for transmitting data from the server to display information optimized based on the generated summary and emotions on a user interface. This makes it possible to quickly and efficiently provide information optimized based on the user's emotional state.

[0381] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0382] A "user interface" is an interface through which a user interacts with a system or application.

[0383] The "server means" is a computer system that has the function of receiving and analyzing information input from a user interface.

[0384] "Emotion data" is data that indicates the user's emotional state, collected from the user's facial expressions, voice, etc.

[0385] A "generative AI means" is a system that uses artificial intelligence to analyze data, extract relevant information, and generate summaries.

[0386] A "database" is a repository of vast amounts of information that can be used to retrieve relevant information based on a search query.

[0387] "Search parameters" are specific indicators or conditions for extracting related information that are generated by combining a search query and emotion data.

[0388] A "summary" is a shortened version of the main content of the retrieved information.

[0389] "Optimization" is the process of tailoring information based on the user's emotional data to present it in a more useful way.

[0390] This invention provides an information retrieval system that optimizes information based on the user's emotional state. Specifically, it analyzes the user's emotional data in addition to the search query entered by the user, and presents optimized information.

[0391] Overall system overview

[0392] The system consists of the following main components: user interface, server, generative AI, database, and emotion engine.

[0393] User Interface

[0394] The user interface is the interface through which users enter search queries. Specifically, they can enter keywords or phrases into a search form using devices such as smartphones or smart glasses. At this time, the user's emotional data is also collected using a camera and microphone.

[0395] Server Means

[0396] The server receives the search query and sentiment data sent from the user interface and analyzes them appropriately. After analysis, it passes the search parameters to the generation AI. It also returns the search results and summaries returned by the generation AI to the user interface for display.

[0397] Generation AI means

[0398] Generative AI has the ability to search a database based on a search query and sentiment data, find relevant information, automatically extract key content from each piece of information, and generate a summary that includes the gist, conclusion, and key data of the information.

[0399] Database

[0400] The database is a repository that stores a vast amount of information. The generative AI queries the database based on the search query and sentiment data to retrieve relevant information.

[0401] Emotion Engine

[0402] The emotion engine analyzes emotion data collected from the user's device to complete or modify search queries and optimize the summaries displayed. For example, if the user is feeling stressed, the emotion engine will provide a simpler and easier-to-understand summary.

[0403] Explanation of program processing

[0404] The server receives and analyzes the search query and sentiment data sent by the user. Natural language processing (NLP) and machine learning algorithms are used for the analysis. The analyzed search query and sentiment data are used as database search parameters by the generative AI.

[0405] Hardware and software used

[0406] Camera and microphone: Used to collect user emotional data.

[0407] OpenCV: Used for face recognition and facial expression analysis.

[0408] Keras: A deep learning library used to build emotion recognition models.

[0409] Flask: A web framework used for server-side API processing.

[0410] Specific examples

[0411] For example, if a user enters "advertising" as a search query and their facial expression is captured by the camera, the system will analyze the emotional data and recognize that the user is feeling "joy." Based on this, the generative AI will search for related advertisements and provide advertising information optimized for that emotion.

[0412] Prompt Sentence Examples

[0413] "Generate the optimal ad to show when the user has a happy expression."

[0414] This method allows for quick and efficient provision of information optimized based on the user's emotional state.

[0415] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0416] Step 1:

[0417] The user enters a search query into the device's user interface. Specifically, they enter a keyword or phrase into the search form on their smartphone or smart glasses and click the search button. At this time, the user's facial expressions and voice are collected using a camera and microphone. Input: Search query, emotion data. Output: Search query, collected emotion data.

[0418] Step 2:

[0419] The device sends the entered search query and emotion data to the server. This includes a process to ensure that the query and emotion data are in the appropriate format. For example, the query is in text format, and the emotion data is in image and audio data. Input: Search query, emotion data. Output: Data formatted in JSON format.

[0420] Step 3:

[0421] The server analyzes the received search query and emotion data. Here, it uses natural language processing (NLP) to analyze the query and machine learning algorithms to analyze the emotion data. For example, OpenCV and Keras are used to classify emotions from facial expressions. Input: Data in JSON format. Output: Analyzed search query, analyzed emotion data.

[0422] Step 4:

[0423] Based on the analysis results, the server passes search parameters to the generation AI. The generation AI uses these parameters to search the database. As a specific example, the generation AI uses libraries such as TensorFlow or PyTorch to retrieve information related to the query from the database. Input: Parsed search query, parsed emotion data. Output: List of related information.

[0424] Step 5:

[0425] Generative AI extracts key content from retrieved information and automatically generates a summary. This uses information summarization algorithms to extract the gist and important data. Input: List of relevant information. Output: Automatically generated summary.

[0426] Step 6:

[0427] The emotion engine optimizes the generated summary. For example, if the user is feeling stressed, the summary is converted into a simple and easy-to-understand format. Input: Automatically generated summary, analyzed emotion data. Output: Optimized summary.

[0428] Step 7:

[0429] The server formats the data to display an optimized summary in the user interface. The data is sent to the device in a specific format (e.g. JSON). Input: Optimized summary. Output: Data formatted in a form that can be displayed in the user interface.

[0430] Step 8:

[0431] The device receives the formatted data from the server, parses it, and displays it in the user interface. The user can review the generated summary and related information and click to view more information. Input: Formatted data. Output: Optimized summary displayed in the user interface.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] [Second embodiment]

[0436] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0437] 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.

[0438] 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).

[0439] 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.

[0440] 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.

[0441] 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).

[0442] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0443] 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.

[0444] 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.

[0445] 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.

[0446] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0447] 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."

[0448] Overall system overview

[0449] This system allows medical professionals to efficiently search medical papers and quickly obtain their summaries. The system mainly consists of the following components: a user interface, a server, a generative AI, and a database.

[0450] Functions of each component

[0451] User Interface

[0452] The user interface provides a search form for the healthcare professional to enter a search query, enter a specific keyword or phrase, and click a search button, which sends the query to the server.

[0453] server

[0454] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface.

[0455] Generation AI

[0456] The generative AI searches medical databases based on the search query passed from the server. The generative AI searches for relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0457] Database

[0458] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0459] Program Operation

[0460] 1. User operations

[0461] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[0462] 2. Device Operation

[0463] The terminal sends the entered query to the server, which checks that the query is in the correct format.

[0464] 3. Server Operation

[0465] The server receives the query and passes the search parameters to the AI ​​generator, which then searches the database and selects relevant papers, up to a maximum of eight of the most relevant papers.

[0466] 4. Controlling the Generative AI

[0467] The generative AI takes the full text of the selected papers and automatically generates a summary for each one, including the main points, conclusions, and key data.

[0468] 5. Server Operation

[0469] The server formats the received data and sends it to the terminal in order to return the generated summary to the user interface.

[0470] 6. Device Operation

[0471] The terminal receives the response from the server and displays it on the user interface. Tanaka can check the displayed summaries, select the paper that interests him, and read it in more detail.

[0472] 7. User Usage

[0473] Tanaka can view the displayed summary and, if necessary, click on a link to the original text to view more detailed information. For example, if he needs more detailed data based on the summarized information, he can download the original text and read it.

[0474] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[0475] The processing flow will be explained below.

[0476] Step 1:

[0477] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[0478] Step 2:

[0479] The device validates the entered search query, checking whether the query is properly formed and displaying an error message to the user if it is not.

[0480] Step 3:

[0481] The device sends the verified search query to the server, generating an API request and sending it to the server's specified endpoint.

[0482] Step 4:

[0483] The server receives the search query from the device, analyzes the query, and based on the analysis results, generates search parameters that require further processing by the generation AI.

[0484] Step 5:

[0485] The server passes the generated search parameters to the generation AI, which uses these parameters to search for relevant medical papers.

[0486] Step 6:

[0487] The generative AI runs search queries against medical databases to retrieve relevant papers, then selects up to eight of the most relevant papers.

[0488] Step 7:

[0489] The AI ​​takes the full text of the selected papers and automatically generates a summary for each one, including the paper's main points, conclusions, and key data.

[0490] Step 8:

[0491] The server receives the summary returned by the generation AI, formats the data for display in the user interface, and sends the formatted data back to the device in a specific format (e.g., JSON).

[0492] Step 9:

[0493] The device receives the response from the server, parses the data, and converts the formatted data into a format for display in the user interface.

[0494] Step 10:

[0495] The terminal displays the paper title, author, publication year, and abstract on the screen in a format that is easy for the user to see.

[0496] Step 11:

[0497] Users can check the displayed abstracts and click on the abstract of the paper they are interested in to view more detailed information. If necessary, they can click on the link to the original article to view more detailed information.

[0498] This series of processes allows users, who are medical professionals, to access the latest medical information quickly and efficiently, which can be useful in clinical practice and research activities.

[0499] Example 1

[0500] 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."

[0501] In today's medical field, many medical professionals are required to quickly access vast amounts of academic materials and efficiently understand their contents. However, with existing systems, the process of entering a search query, retrieving relevant materials, and generating summaries is time-consuming and laborious. Furthermore, these operations are often cumbersome and require specialized medical knowledge. This makes it difficult for medical professionals to quickly and efficiently refer to the latest medical information.

[0502] 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.

[0503] In this invention, the server includes: means for providing an operation unit for inputting a search query; control unit means for receiving and analyzing the input search query; generation AI means for searching an information storage device for relevant academic materials based on the analyzed search query; generation AI means for automatically generating summaries from the searched materials; and means for transmitting data from the control unit to display the generated summaries on the operation unit. This enables relevant academic materials to be quickly obtained based on a search query input by a medical professional, and their summaries to be automatically generated and displayed. This allows medical professionals to efficiently access the latest medical information and effectively utilize it in their daily clinical practice and research activities.

[0504] A "search query" is a keyword or phrase that a user enters to search for specific information.

[0505] The "operation unit" is a user interface that allows the user to input information and perform operations such as searches.

[0506] "Controller means" refers to a server or computer system for receiving and analyzing input search queries.

[0507] A "generative AI means" is a type of artificial intelligence that has the function of searching an information storage device based on a received search query, selecting relevant academic materials, and automatically generating a summary.

[0508] An "information storage device" is a database system that stores a huge amount of academic materials and data.

[0509] The "means for transmitting data" is a communication function for transmitting data from the control device in order to display the generated summary data on the operation unit.

[0510] "Academic materials" refers to literature related to specialized fields, such as medical papers and research reports.

[0511] A "summary" is a text that concisely summarizes the main content, conclusions, and important data of academic material.

[0512] This system allows medical professionals to efficiently search for academic materials and quickly obtain their summaries. The system mainly consists of the following components: an operating unit, a control unit, a generation AI, and an information storage unit.

[0513] Operation section

[0514] The operation unit provides a user interface for users to enter search queries. When a user enters a specific keyword or phrase into the operation unit's search form and clicks the search button, the query is sent to the control device. For example, a user might enter "COVID-19 vaccine effectiveness."

[0515] control device

[0516] The control device receives and analyzes the search query sent from the operation unit. This analysis includes properly formatting the received search query and passing it to the generation AI. It also receives the summary results returned by the generation AI and sends the data to the operation unit. Specifically, the control device packs the data in JSON format and sends and receives the data via HTTP requests and responses.

[0517] Generation AI

[0518] The generative AI searches the information storage device based on a search query passed from the control device. It typically uses an artificial intelligence model and implements advanced natural language processing algorithms. It selects relevant academic materials and extracts up to eight of the most relevant papers. It then automatically generates a summary for each paper, including the paper's main idea, conclusions, and key data.

[0519] Information Storage Device

[0520] The information storage device is a database system that stores a vast amount of academic materials. The generative AI queries the database based on the search query to retrieve relevant materials.

[0521] Specific examples

[0522] Dr. Tanaka enters "COVID-19 vaccine effectiveness" into the search form on the control unit and clicks the search button. The query is sent to the control unit, which then sends it to the generation AI. The generation AI searches the information storage device, extracts up to eight relevant papers, and generates a summary of each paper. The summaries are sent back to the control unit, and the formatted data is displayed on the control unit. Dr. Tanaka can review the displayed summaries and select papers of interest for further reading.

[0523] Prompt Sentence Examples

[0524] "Please find and provide a summary of the latest academic literature on the effectiveness of COVID-19 vaccines."

[0525] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[0526] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0527] Step 1:

[0528] A user enters a query into the search form on the control panel and clicks the search button. For example, a doctor enters "COVID-19 vaccine effectiveness."

[0529] Input: Search query "COVID-19 vaccine effectiveness"

[0530] Output: Search button click action

[0531] Specific action: The user enters a query into the search form and clicks the search button.

[0532] Step 2:

[0533] The terminal receives the entered search query, verifies that the query is properly formatted, and then transmits the query to the control device.

[0534] Input: Search query "COVID-19 vaccine effectiveness"

[0535] Output: Search query sent in HTTP request format

[0536] Specific operation: The terminal packs the query in JSON format and sends it to the control device via an HTTP request.

[0537] Step 3:

[0538] The server (controller) analyzes the received query and passes it to the generation AI as search parameters. Analysis includes understanding the content of the query and formatting it appropriately.

[0539] Input: Search query in HTTP request format

[0540] Output: Search parameters for the generation AI

[0541] What happens: The server parses the query and sends parameters to the generator AI in the following format:

[0542] json

[0543] {

[0544] "query": "COVID-19 vaccine effectiveness",

[0545] "maximum_results": 8

[0546] }

[0547] Step 4:

[0548] The generation AI receives search parameters from the server, searches the specified information storage device, selects relevant academic materials, and extracts up to eight of the most relevant materials from among them.

[0549] Input: Search parameters (query "COVID-19 vaccine effectiveness", maximum results 8)

[0550] Output: Metadata and full text of associated material

[0551] Specific operation: The generating AI searches the information storage device (database) and extracts relevant materials.

[0552] Step 5:

[0553] The generative AI takes the full text of the selected documents and automatically generates a summary for each document, including the main idea, conclusion, and key data.

[0554] Input: Metadata and full text of relevant material

[0555] Output: Summary of the material

[0556] How it works: Generative AI uses natural language processing algorithms to generate summaries of materials.

[0557] Step 6:

[0558] The server (controller) receives the summary results returned by the generation AI, formats them, and sends them to the terminal. Formatting includes converting the data into a format that is easy for users to view.

[0559] Input: Summary of material from generative AI

[0560] Output: Summary data in HTTP response format

[0561] Specific operation: The server analyzes and formats the summary results returned by the generation AI and sends them to the terminal as an HTTP response.

[0562] Step 7:

[0563] The terminal receives the summary information sent from the server and displays it on the user interface. The user can then check the displayed summaries, select the paper of interest, and view it in more detail.

[0564] Input: Summary data in HTTP response format

[0565] Output: Summary information displayed in the user interface

[0566] Specific operation: The terminal analyzes the received summary data and displays it in list format on the user interface.

[0567] This concretely shows the flow of the entire system, clarifies the input and output of each step, and allows you to understand how data is processed or calculated.

[0568] (Application example 1)

[0569] 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."

[0570] Modern factories lack a means to quickly and efficiently retrieve technical literature and research papers related to manufacturing processes and review their summaries. This results in workers spending a great deal of time and effort to obtain the necessary information, resulting in reduced productivity. Furthermore, delays in retrieving and interpreting information hinder efficient factory operations and rapid problem resolution. Therefore, there is a need for a system that allows factory workers to easily search for technical literature and quickly retrieve its summaries.

[0571] 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.

[0572] In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, means for generating AI to search a database for relevant documents based on the analyzed search query, means for automatically generating summaries from the retrieved documents, means for transmitting data to display the generated summaries on the user interface, and means for reviewing the summarized documents and providing links to display detailed information, thereby enabling factory workers to efficiently search for relevant technical documents and quickly review their summaries.

[0573] A "search query" refers to a keyword or phrase entered by a user to retrieve related literature information.

[0574] "User Interface" refers to the screen or interactive means by which a user enters a search query and interacts with the system.

[0575] "Server" refers to the computer system responsible for analyzing the received search query and passing the search parameters to the generation AI.

[0576] "Generative AI" refers to an artificial intelligence model that searches for relevant literature based on a received search query and automatically generates a summary of it.

[0577] "Database" refers to a repository that stores a vast amount of relevant bibliographic information.

[0578] An "abstract" refers to information that concisely summarizes the main points, conclusions, and important data of a document.

[0579] "Link" refers to an associated URL or reference point for further information after reviewing the abstracted literature.

[0580] The system that realizes this invention aims to enable factory workers to efficiently search technical literature and quickly obtain summaries. The system consists of the following main components: a user interface, a server, a generative AI, and a database.

[0581] Hardware and Software

[0582] Hardware

[0583] Factory robots

[0584] Embedded computers (e.g., NVIDIA Jetson Nano)

[0585] software

[0586] Operating System: Linux

[0587] Programming language: Python

[0588] Web server: Flask

[0589] Database: PostgreSQL

[0590] Generative AI model: GPT-4 (OpenAI API)

[0591] Data processing and calculation flow

[0592] 1. User operations

[0593] Factory workers use the robot's on-board touchscreen to input queries for specific technical information or research papers, such as "properties of new materials."

[0594] 2. Device Operation

[0595] The entered query is sent via a user interface to the server, which verifies that the received query is well-formed and parses it appropriately.

[0596] 3. Server Operation

[0597] The server passes the query analysis results to the generation AI, which then searches the database for relevant literature and selects the most relevant literature.

[0598] 4. Controlling the Generative AI

[0599] The generation AI retrieves the full text of the selected documents and extracts the main points, conclusions, and important data from each document to generate a summary.

[0600] 5. Server Operation

[0601] The server sends the formatted data to the terminal in order to return the generated summary to the user interface.

[0602] 6. User Interface Operation

[0603] Factory workers can view summaries via touchscreen panels and click on links to view more detailed information about documents that interest them.

[0604] Specific examples

[0605] If a factory worker wants to research the properties of a new material, he or she can enter "properties of new material" into the robot's search form. The system will then search the database for relevant technical literature and display its summary. For example,

[0606] "Research into the properties and applications of new material X"

[0607] "Heat resistance of new materials and their potential uses"

[0608] "Improved product strength through the use of new materials"

[0609] Workers can view the summary and, if they want to learn more about "Improving product strength through the use of new materials," they can click on a link to view the full text.

[0610] Prompt Sentence Examples

[0611] "Find relevant technical literature and generate summaries of them based on the following query: 'properties of new materials'. For each publication, include the main points, conclusions, and key data."

[0612] This invention allows factory workers to quickly search and obtain summaries of relevant technical literature, which can contribute to improving manufacturing processes and resolving problems.

[0613] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0614] Step 1:

[0615] User query input

[0616] Factory workers use the robot's touchscreen to input queries for specific technical information or research papers, such as "properties of a new material." Input is received from the user interface and transmitted to the server.

[0617] Step 2:

[0618] Query analysis by the server

[0619] The server parses the search query received from the user interface. First, it checks whether the received data is in the correct format, and then it parses the query to generate appropriate search parameters. The input is the query "properties of new materials," and the output is the parsed search parameters.

[0620] Step 3:

[0621] Literature search using generative AI

[0622] The server passes the generated search parameters to the generation AI, which then searches the database for relevant literature based on the search parameters. The AI ​​model (e.g., GPT-4) searches for literature according to the prompt. The input is the search parameters, and the output is a list of matching literature.

[0623] Step 4:

[0624] Full-text document acquisition and summary generation

[0625] Generative AI takes the full text of the documents retrieved through the search and generates a summary for each document. The summary includes the main idea, conclusion, and important data. The input is the full text of the document, and the output is the summarized information. Generative AI extracts the main idea, conclusion, and important data from the document and generates a summary.

[0626] Step 5:

[0627] Data formatting and transmission by the server

[0628] The server formats the summary received from the generation AI and converts it into a data format for sending back to the user interface. The server then sends the formatted data to the user interface. The input is the summarized bibliographic information, and the output is the formatted summary data.

[0629] Step 6:

[0630] Summary display in the user interface

[0631] The user interface displays the summaries received from the server on a touch panel. Factory workers check the displayed summaries and click on links for more information. The input is the summarized literature information, and the output is the summary displayed on the user interface. Clicking on a link also displays the full text of the literature for more information.

[0632] Step 7:

[0633] View user details

[0634] A factory worker clicks on a link to view detailed information about a document of interest. This displays the full text of the document, enabling deeper understanding and analysis. The input is the user's request for more information, and the output is the full text of the document.

[0635] The above processing steps allow factory personnel to efficiently search technical literature, quickly review summaries, and obtain further details.

[0636] 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.

[0637] Overall system overview

[0638] This system allows medical professionals to efficiently search for medical papers and quickly obtain their summaries. It incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on those emotions. The system mainly consists of the following components: user interface, server, generative AI, database, and emotion engine.

[0639] Functions of each component

[0640] User Interface

[0641] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[0642] server

[0643] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[0644] Generation AI

[0645] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0646] Database

[0647] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0648] Emotion Engine

[0649] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[0650] Program Operation

[0651] 1. User operations

[0652] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[0653] 2. Device Operation

[0654] The device sends the collected emotion data along with the input query to the server, which verifies that the query and emotion data are in the correct format.

[0655] 3. Server Operation

[0656] The server receives the query and emotion data, analyzes the query and the emotion data, and based on the analysis results, generates search parameters and emotion data that need further processing by the generative AI and emotion engine.

[0657] 4. Controlling the Generative AI

[0658] The generative AI uses analytical parameters to search medical databases, select relevant literature, and automatically generate summaries.

[0659] 5. Manipulating the Emotion Engine

[0660] The emotion engine complements, modifies, and optimizes generated summaries and search results based on the user's emotions. For example, if the user is feeling stressed, the emotion engine will provide a simpler and more understandable summary.

[0661] 6. Server Operation

[0662] It receives summaries returned by the generative AI and emotion engine, formats the data for display in the user interface, and sends the formatted data to the device in a specific format (e.g., JSON).

[0663] 7. Device Operation

[0664] The device receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[0665] 8. Display and Use

[0666] The user's device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the summaries and click on the paper that interests him to view detailed information. Using the summarized information, he can quickly and efficiently obtain the information he needs.

[0667] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[0668] The processing flow will be explained below.

[0669] Step 1:

[0670] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[0671] Step 2:

[0672] The device validates the entered search query and collected sentiment data to ensure they are in the proper format, and then generates an API request to send to the server.

[0673] Step 3:

[0674] The device then sends the generated API request to the server, which includes the search query and sentiment data.

[0675] Step 4:

[0676] The server receives search queries and emotion data from the device, analyzes the received data, and passes the search parameters and emotion data to the generation AI and emotion engine.

[0677] Step 5:

[0678] The generation AI uses search parameters provided by the server to search the database for relevant medical papers, selecting up to eight highly relevant papers.

[0679] Step 6:

[0680] The AI ​​retrieves the full text of the selected papers, extracts key content, and automatically generates a summary for each paper, including the main points, conclusions, and key data.

[0681] Step 7:

[0682] The emotion engine analyzes the user's emotional data and complements, corrects, and optimizes the generated summaries and search results based on that data. For example, if the user is feeling stressed, it will provide a simpler and easier-to-understand summary.

[0683] Step 8:

[0684] The server receives the summaries returned by the generative AI and emotion engine and formats the data for display in the user interface in a specific format, such as JSON.

[0685] Step 9:

[0686] The terminal receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[0687] Step 10:

[0688] The device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the abstracts and click to view more information about papers that interest him.

[0689] Step 11:

[0690] Users can quickly obtain important information based on the optimized summary and, if necessary, click on a link to the original text to view more detailed information.

[0691] This will enable healthcare professionals, who are users, to quickly and efficiently access the latest medical information that is optimized using emotional data.

[0692] Example 2

[0693] 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."

[0694] Conventional medical paper search systems make it difficult for medical professionals to efficiently obtain the information they need. In particular, they provide uniform results without considering the user's emotional state, which can cause stress and waste time. This creates a high demand for a system that can quickly and effectively search and summarize medical papers.

[0695] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, generation AI means for searching a database for related documents based on the analyzed search query, generation AI means for automatically generating a summary from the retrieved documents, means for transmitting data from the server to display the generated summary on the user interface, and emotion engine means for recognizing user emotion data and complementing, correcting, and optimizing the summary based on the emotion. This enables more efficient and appropriate information provision while taking the user's emotional state into consideration.

[0696] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0697] A "user interface" is an interface that provides a screen or input form for a user to interact with a system.

[0698] A "server" is a computer system that receives requests from users, analyzes them, and passes appropriate data to the generative AI or emotion engine.

[0699] "Generative AI" is an artificial intelligence technology that searches for relevant literature from a database based on a search query, extracts important content from each document, and generates a summary.

[0700] A "database" is a system for storing and managing vast amounts of bibliographic information.

[0701] An "emotion engine" is a system that analyzes emotional data obtained from a user's facial expressions, voice, etc., and complements, corrects, and optimizes search results and summaries based on those emotions.

[0702] A "summary" is a compact summary that extracts the main points, conclusions, important data, etc. of a document.

[0703] "Emotion data" is information collected from facial expressions and voice to understand the user's emotional state.

[0704] MODE FOR CARRYING OUT THE INVENTION

[0705] The present invention relates to a system for medical professionals to efficiently search medical papers and quickly obtain their summaries. The system incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on the emotions. Specific embodiments of the system are described below.

[0706] System Components

[0707] The system mainly consists of the following components:

[0708] User Interface

[0709] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[0710] server

[0711] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[0712] Generation AI

[0713] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0714] Database

[0715] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0716] Emotion Engine

[0717] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[0718] System Operation

[0719] When a user enters a query into the search form, the system sends the query along with the user's emotional data to the server. The server analyzes this data and passes appropriate search parameters to the generation AI. The generation AI searches the database and generates summaries of relevant literature. The emotion engine complements, corrects, and optimizes the generated summaries and search results based on the user's emotions. The final search results and summaries are displayed on the user interface via the server.

[0720] For example, if a doctor enters a query such as "COVID-19 vaccine effectiveness" and clicks the search button, the query and the acquired emotion data are sent to the server. The server analyzes the query and emotion data and passes appropriate search parameters to the generation AI. The generation AI searches for relevant papers and generates a summary. The emotion engine analyzes the summary and optimizes it based on the user's emotion. The summarized content is then displayed in the user interface.

[0721] Prompt Sentence Examples

[0722] Below is an example of a prompt sentence to input to the generative AI model.

[0723] User query: "COVID-19 vaccine effectiveness"

[0724] User sentiment: "Tension: High"

[0725] To search for relevant medical articles and generate summaries of:

[0726] Purpose of the paper

[0727] conclusion

[0728] Important Data

[0729] Concise and easy-to-understand expression

[0730] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[0731] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0732] Step 1:

[0733] User query input and sentiment data collection

[0734] A user enters a query into a search form on their device and clicks the search button. This action causes the device to collect emotional data from facial expressions and voice using the user's camera and microphone. For example, a doctor may enter a search query such as "COVID-19 vaccine effectiveness," and emotional data may be recorded from facial expressions and tone of voice.

[0735] Input: User search query and emotional data (e.g., facial expressions, voice)

[0736] Output: Collected search queries and sentiment data

[0737] Step 2:

[0738] Sending data from the device to the server

[0739] The device checks the query entered by the user and the format of the collected emotion data, converts it into an appropriate format (e.g., JSON), and sends it to the server. For example, data is sent in the following JSON format:

[0740] json

[0741] {

[0742] "query": "COVID-19 vaccine effectiveness",

[0743] "emotion_data": {

[0744] "stress": 0.8,

[0745] "anxiety": 0.7

[0746] }

[0747] }

[0748] Input: User search query and sentiment data

[0749] Output: JSON format data sent to the server

[0750] Step 3:

[0751] Server-side query and sentiment analysis

[0752] The server analyzes the data received from the device. First, it decomposes and analyzes the query to generate search parameters. It also analyzes the emotional data to evaluate the user's emotional state, and based on the results, generates data for the generation AI and emotion engine.

[0753] Input: JSON format data sent from the terminal

[0754] Output: Parsed data to feed into generative AI and emotion engines

[0755] Step 4:

[0756] Paper search and summary generation using generative AI

[0757] The generation AI searches a database of medical papers using search parameters provided by the server. It selects relevant papers, extracts the gist, conclusions, and important data from each paper, and generates a summary. For example, it searches for multiple papers on "COVID-19 vaccine effectiveness" and generates a summary for each.

[0758] Input: Search parameters provided by the server

[0759] Output: Abstracted bibliographic information

[0760] Step 5:

[0761] Summarization optimization using emotion engine

[0762] The emotion engine analyzes the summary received from the generative AI and optimizes it based on the user's emotional state. For example, if the user is feeling stressed, it will modify the summary to make it more concise and easy to understand.

[0763] Input: Summary provided by the generative AI and user sentiment data

[0764] Output: Optimized summary information

[0765] Step 6:

[0766] Formatting and sending data from the server to the terminal

[0767] The server receives the optimized summary and formats it for display in the user interface. This formatted data might be in JSON format, for example:

[0768] json

[0769] {

[0770] "title": "COVID-19 Vaccine Effectiveness",

[0771] "authors": ["Author 1", "Author 2"],

[0772] "published_year": 2021,

[0773] "summary": "This paper is a study examining the effectiveness of COVID-19 vaccines, and its main conclusion is XXX. Key data is YYY."

[0774] }

[0775] This data is sent to the terminal.

[0776] Input: Optimized summary provided by the sentiment engine

[0777] Output: Data formatted to send to the terminal

[0778] Step 7:

[0779] Data parsing and display on the device

[0780] The device parses the data received from the server, converts it into a human-readable format, and displays it in a user interface, using HTML and CSS to format the search results so that the title, author, publication year, and abstract are easily readable.

[0781] Input: Formatted data sent from the server

[0782] Output: Search results displayed in the user interface

[0783] Step 8:

[0784] User review and use of information

[0785] Users can check the abstracts and titles of papers displayed on their devices and click on the paper they are interested in to view detailed information, allowing them to quickly and efficiently obtain the information they need and use it in their clinical practice and research activities.

[0786] Input: Search results displayed in the user interface

[0787] Output: Specific paper information that the user retrieves

[0788] (Application example 2)

[0789] 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."

[0790] Conventional information search systems have the problem of not being able to quickly provide optimal information that users desire because they do not take into account the emotional state of the user. Furthermore, the lack of emotion-based information optimization makes it difficult to improve user satisfaction. The purpose of this invention is to solve these problems.

[0791] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing emotion data along with an input search query, generation AI means for searching a database for related information based on the analyzed search query and emotion data, generation AI means for automatically generating a summary from the searched information, and means for transmitting data from the server to display information optimized based on the generated summary and emotions on a user interface. This makes it possible to quickly and efficiently provide information optimized based on the user's emotional state.

[0792] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[0793] A "user interface" is an interface through which a user interacts with a system or application.

[0794] The "server means" is a computer system that has the function of receiving and analyzing information input from a user interface.

[0795] "Emotion data" is data that indicates the user's emotional state, collected from the user's facial expressions, voice, etc.

[0796] A "generative AI means" is a system that uses artificial intelligence to analyze data, extract relevant information, and generate summaries.

[0797] A "database" is a repository of vast amounts of information that can be used to retrieve relevant information based on a search query.

[0798] "Search parameters" are specific indicators or conditions for extracting related information that are generated by combining a search query and emotion data.

[0799] A "summary" is a shortened version of the main content of the retrieved information.

[0800] "Optimization" is the process of tailoring information based on the user's emotional data to present it in a more useful way.

[0801] This invention provides an information retrieval system that optimizes information based on the user's emotional state. Specifically, it analyzes the user's emotional data in addition to the search query entered by the user, and presents optimized information.

[0802] Overall system overview

[0803] The system consists of the following main components: user interface, server, generative AI, database, and emotion engine.

[0804] User Interface

[0805] The user interface is the interface through which users enter search queries. Specifically, they can enter keywords or phrases into a search form using devices such as smartphones or smart glasses. At this time, the user's emotional data is also collected using a camera and microphone.

[0806] Server Means

[0807] The server receives the search query and sentiment data sent from the user interface and analyzes them appropriately. After analysis, it passes the search parameters to the generation AI. It also returns the search results and summaries returned by the generation AI to the user interface for display.

[0808] Generation AI means

[0809] Generative AI has the ability to search a database based on a search query and sentiment data, find relevant information, automatically extract key content from each piece of information, and generate a summary that includes the gist, conclusion, and key data of the information.

[0810] Database

[0811] The database is a repository that stores a huge amount of information. The generative AI queries the database based on the search query and sentiment data to retrieve relevant information.

[0812] Emotion Engine

[0813] The emotion engine analyzes emotion data collected from the user's device to complete or modify search queries and optimize the summaries displayed. For example, if the user is feeling stressed, the emotion engine will provide a simpler and easier-to-understand summary.

[0814] Explanation of program processing

[0815] The server receives and analyzes the search queries and sentiment data sent by users. Natural language processing (NLP) and machine learning algorithms are used for the analysis. The analyzed search queries and sentiment data are used as database search parameters by the generative AI.

[0816] Hardware and software used

[0817] Camera and microphone: Used to collect user emotional data.

[0818] OpenCV: Used for face recognition and facial expression analysis.

[0819] Keras: A deep learning library used to build emotion recognition models.

[0820] Flask: A web framework used for server-side API processing.

[0821] Specific examples

[0822] For example, if a user enters "advertising" as a search query and their facial expression is captured by the camera, the system will analyze the emotional data and recognize that the user is feeling "joy." Based on this, the generative AI will search for related advertisements and provide advertising information optimized for that emotion.

[0823] Prompt Sentence Examples

[0824] "Generate the optimal ad to show when the user has a happy expression."

[0825] This method allows for quick and efficient provision of information optimized based on the user's emotional state.

[0826] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0827] Step 1:

[0828] The user enters a search query into the device's user interface. Specifically, they enter a keyword or phrase into the search form on their smartphone or smart glasses and click the search button. At this time, the user's facial expressions and voice are collected using a camera and microphone. Input: Search query, emotion data. Output: Search query, collected emotion data.

[0829] Step 2:

[0830] The device sends the entered search query and emotion data to the server. This includes a process to ensure that the query and emotion data are in the appropriate format. For example, the query is in text format, and the emotion data is in image and audio data. Input: Search query, emotion data. Output: Data formatted in JSON format.

[0831] Step 3:

[0832] The server analyzes the received search query and emotion data. Here, it uses natural language processing (NLP) to analyze the query and machine learning algorithms to analyze the emotion data. For example, OpenCV and Keras are used to classify emotions from facial expressions. Input: Data in JSON format. Output: Analyzed search query, analyzed emotion data.

[0833] Step 4:

[0834] Based on the analysis results, the server passes search parameters to the generation AI. The generation AI uses these parameters to search the database. As a specific example, the generation AI uses libraries such as TensorFlow or PyTorch to retrieve information related to the query from the database. Input: Parsed search query, parsed emotion data. Output: List of related information.

[0835] Step 5:

[0836] Generative AI extracts key content from retrieved information and automatically generates a summary. This uses information summarization algorithms to extract the gist and important data. Input: List of relevant information. Output: Automatically generated summary.

[0837] Step 6:

[0838] The emotion engine optimizes the generated summary. For example, if the user is feeling stressed, the summary is converted into a simple and easy-to-understand format. Input: Automatically generated summary, analyzed emotion data. Output: Optimized summary.

[0839] Step 7:

[0840] The server formats the data to display an optimized summary in the user interface. The data is sent to the device in a specific format (e.g. JSON). Input: Optimized summary. Output: Data formatted in a form that can be displayed in the user interface.

[0841] Step 8:

[0842] The device receives the formatted data from the server, parses it, and displays it in the user interface. The user can review the generated summary and related information and click to view more information. Input: Formatted data. Output: Optimized summary displayed in the user interface.

[0843] 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.

[0844] 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.

[0845] 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.

[0846] [Third embodiment]

[0847] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0848] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0849] 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).

[0850] 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.

[0851] 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.

[0852] 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).

[0853] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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."

[0859] Overall system overview

[0860] This system allows medical professionals to efficiently search medical papers and quickly obtain their summaries. The system mainly consists of the following components: a user interface, a server, a generative AI, and a database.

[0861] Functions of each component

[0862] User Interface

[0863] The user interface provides a search form for the healthcare professional to enter a search query, enter a specific keyword or phrase, and click a search button, which sends the query to the server.

[0864] server

[0865] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface.

[0866] Generation AI

[0867] The generative AI searches medical databases based on the search query passed from the server. The generative AI searches for relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[0868] Database

[0869] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[0870] Program Operation

[0871] 1. User operations

[0872] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[0873] 2. Device Operation

[0874] The terminal sends the entered query to the server, which checks that the query is in the correct format.

[0875] 3. Server Operation

[0876] The server receives the query and passes the search parameters to the AI ​​generator, which then searches the database and selects relevant papers, up to a maximum of eight of the most relevant papers.

[0877] 4. Controlling the Generative AI

[0878] The generative AI takes the full text of the selected papers and automatically generates a summary for each one, including the main points, conclusions, and key data.

[0879] 5. Server Operation

[0880] The server formats the received data and sends it to the terminal in order to return the generated summary to the user interface.

[0881] 6. Device Operation

[0882] The terminal receives the response from the server and displays it on the user interface. Tanaka can check the displayed summaries, select the paper that interests him, and read it in more detail.

[0883] 7. User Usage

[0884] Tanaka can view the displayed summary and, if necessary, click on a link to the original text to view more detailed information. For example, if he needs more detailed data based on the summarized information, he can download the original text and read it.

[0885] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[0886] The processing flow will be explained below.

[0887] Step 1:

[0888] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[0889] Step 2:

[0890] The device validates the entered search query, checking whether the query is properly formed and displaying an error message to the user if it is not.

[0891] Step 3:

[0892] The device sends the verified search query to the server, generating an API request and sending it to the server's specified endpoint.

[0893] Step 4:

[0894] The server receives the search query from the device, analyzes the query, and based on the analysis results, generates search parameters that require further processing by the generation AI.

[0895] Step 5:

[0896] The server passes the generated search parameters to the generation AI, which uses these parameters to search for relevant medical papers.

[0897] Step 6:

[0898] The generative AI runs search queries against medical databases to retrieve relevant papers, then selects up to eight of the most relevant papers.

[0899] Step 7:

[0900] The AI ​​takes the full text of the selected papers and automatically generates a summary for each one, including the paper's main points, conclusions, and key data.

[0901] Step 8:

[0902] The server receives the summary returned by the generation AI, formats the data for display in the user interface, and sends the formatted data back to the device in a specific format (e.g., JSON).

[0903] Step 9:

[0904] The device receives the response from the server, parses the data, and converts the formatted data into a format for display in the user interface.

[0905] Step 10:

[0906] The terminal displays the paper title, author, publication year, and abstract on the screen in a format that is easy for the user to see.

[0907] Step 11:

[0908] Users can check the displayed abstracts and click on the abstract of the paper they are interested in to view more detailed information. If necessary, they can click on the link to the original article to view more detailed information.

[0909] This series of processes allows users, who are medical professionals, to access the latest medical information quickly and efficiently, which can be useful in clinical practice and research activities.

[0910] Example 1

[0911] 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."

[0912] In today's medical field, many medical professionals are required to quickly access vast amounts of academic materials and efficiently understand their contents. However, with existing systems, the process of entering a search query, retrieving relevant materials, and generating summaries is time-consuming and laborious. Furthermore, these operations are often cumbersome and require specialized medical knowledge. This makes it difficult for medical professionals to quickly and efficiently refer to the latest medical information.

[0913] 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.

[0914] In this invention, the server includes: means for providing an operation unit for inputting a search query; control unit means for receiving and analyzing the input search query; generation AI means for searching an information storage device for relevant academic materials based on the analyzed search query; generation AI means for automatically generating summaries from the searched materials; and means for transmitting data from the control unit to display the generated summaries on the operation unit. This enables relevant academic materials to be quickly obtained based on a search query input by a medical professional, and their summaries to be automatically generated and displayed. This allows medical professionals to efficiently access the latest medical information and effectively utilize it in their daily clinical practice and research activities.

[0915] A "search query" is a keyword or phrase that a user enters to search for specific information.

[0916] The "operation unit" is a user interface that allows the user to input information and perform operations such as searches.

[0917] "Controller means" refers to a server or computer system for receiving and analyzing input search queries.

[0918] A "generative AI means" is a type of artificial intelligence that has the function of searching an information storage device based on a received search query, selecting relevant academic materials, and automatically generating a summary.

[0919] An "information storage device" is a database system that stores a huge amount of academic materials and data.

[0920] The "means for transmitting data" is a communication function for transmitting data from the control device in order to display the generated summary data on the operation unit.

[0921] "Academic materials" refers to literature related to specialized fields, such as medical papers and research reports.

[0922] A "summary" is a text that concisely summarizes the main content, conclusions, and important data of academic material.

[0923] This system allows medical professionals to efficiently search for academic materials and quickly obtain their summaries. The system mainly consists of the following components: an operating unit, a control unit, a generation AI, and an information storage unit.

[0924] Operation section

[0925] The operation unit provides a user interface for users to enter search queries. When a user enters a specific keyword or phrase into the operation unit's search form and clicks the search button, the query is sent to the control device. For example, a user might enter "COVID-19 vaccine effectiveness."

[0926] control device

[0927] The control device receives and analyzes the search query sent from the operation unit. This analysis includes properly formatting the received search query and passing it to the generation AI. It also receives the summary results returned by the generation AI and sends the data to the operation unit. Specifically, the control device packs the data in JSON format and sends and receives the data via HTTP requests and responses.

[0928] Generation AI

[0929] The generative AI searches the information storage device based on a search query passed from the control device. It typically uses an artificial intelligence model and implements advanced natural language processing algorithms. It selects relevant academic materials and extracts up to eight of the most relevant papers. It then automatically generates a summary for each paper, including the paper's main idea, conclusions, and key data.

[0930] Information Storage Device

[0931] The information storage device is a database system that stores a vast amount of academic materials. The generative AI queries the database based on the search query to retrieve relevant materials.

[0932] Specific examples

[0933] Dr. Tanaka enters "COVID-19 vaccine effectiveness" into the search form on the control unit and clicks the search button. The query is sent to the control unit, which then sends it to the generation AI. The generation AI searches the information storage device, extracts up to eight relevant papers, and generates a summary of each paper. The summaries are sent back to the control unit, and the formatted data is displayed on the control unit. Dr. Tanaka can review the displayed summaries and select papers of interest for further reading.

[0934] Prompt Sentence Examples

[0935] "Please find and provide a summary of the latest academic literature on the effectiveness of COVID-19 vaccines."

[0936] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[0937] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0938] Step 1:

[0939] A user enters a query into the search form on the control panel and clicks the search button. For example, a doctor enters "COVID-19 vaccine effectiveness."

[0940] Input: Search query "COVID-19 vaccine effectiveness"

[0941] Output: Search button click action

[0942] Specific action: The user enters a query into the search form and clicks the search button.

[0943] Step 2:

[0944] The terminal receives the entered search query, verifies that the query is properly formatted, and then transmits the query to the control device.

[0945] Input: Search query "COVID-19 vaccine effectiveness"

[0946] Output: Search query sent in HTTP request format

[0947] Specific operation: The terminal packs the query in JSON format and sends it to the control device via an HTTP request.

[0948] Step 3:

[0949] The server (controller) analyzes the received query and passes it to the generation AI as search parameters. Analysis includes understanding the content of the query and formatting it appropriately.

[0950] Input: Search query in HTTP request format

[0951] Output: Search parameters for the generation AI

[0952] What happens: The server parses the query and sends parameters to the generator AI in the following format:

[0953] json

[0954] {

[0955] "query": "COVID-19 vaccine effectiveness",

[0956] "maximum_results": 8

[0957] }

[0958] Step 4:

[0959] The generation AI receives search parameters from the server, searches the specified information storage device, selects relevant academic materials, and extracts up to eight of the most relevant materials from among them.

[0960] Input: Search parameters (query "COVID-19 vaccine effectiveness", maximum results 8)

[0961] Output: Metadata and full text of associated material

[0962] Specific operation: The generating AI searches the information storage device (database) and extracts relevant materials.

[0963] Step 5:

[0964] The generative AI takes the full text of the selected documents and automatically generates a summary for each document, including the main idea, conclusion, and key data.

[0965] Input: Metadata and full text of relevant material

[0966] Output: Summary of the material

[0967] How it works: Generative AI uses natural language processing algorithms to generate summaries of materials.

[0968] Step 6:

[0969] The server (controller) receives the summary results returned by the generation AI, formats them, and sends them to the terminal. Formatting includes converting the data into a format that is easy for users to view.

[0970] Input: Summary of material from generative AI

[0971] Output: Summary data in HTTP response format

[0972] Specific operation: The server analyzes and formats the summary results returned by the generation AI and sends them to the terminal as an HTTP response.

[0973] Step 7:

[0974] The terminal receives the summary information sent from the server and displays it on the user interface. The user can then check the displayed summaries, select the paper of interest, and view it in more detail.

[0975] Input: Summary data in HTTP response format

[0976] Output: Summary information displayed in the user interface

[0977] Specific operation: The terminal analyzes the received summary data and displays it in list format on the user interface.

[0978] This concretely shows the flow of the entire system, clarifies the input and output of each step, and allows you to understand how data is processed or calculated.

[0979] (Application example 1)

[0980] 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."

[0981] Modern factories lack a means to quickly and efficiently retrieve technical literature and research papers related to manufacturing processes and review their summaries. This results in workers spending a great deal of time and effort to obtain the necessary information, resulting in reduced productivity. Furthermore, delays in retrieving and interpreting information hinder efficient factory operations and rapid problem resolution. Therefore, there is a need for a system that allows factory workers to easily search for technical literature and quickly retrieve its summaries.

[0982] 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.

[0983] In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, means for generating AI to search a database for relevant documents based on the analyzed search query, means for automatically generating summaries from the retrieved documents, means for transmitting data to display the generated summaries on the user interface, and means for reviewing the summarized documents and providing links to display detailed information, thereby enabling factory workers to efficiently search for relevant technical documents and quickly review their summaries.

[0984] A "search query" refers to a keyword or phrase entered by a user to retrieve related literature information.

[0985] "User Interface" refers to the screen or interactive means by which a user enters a search query and interacts with the system.

[0986] "Server" refers to the computer system responsible for analyzing the received search query and passing the search parameters to the generation AI.

[0987] "Generative AI" refers to an artificial intelligence model that searches for relevant literature based on a received search query and automatically generates a summary of it.

[0988] "Database" refers to a repository that stores a vast amount of relevant bibliographic information.

[0989] An "abstract" refers to information that concisely summarizes the main points, conclusions, and important data of a document.

[0990] "Link" refers to an associated URL or reference point for further information after reviewing the abstracted literature.

[0991] The system that realizes this invention aims to enable factory workers to efficiently search technical literature and quickly obtain summaries. The system consists of the following main components: a user interface, a server, a generative AI, and a database.

[0992] Hardware and Software

[0993] Hardware

[0994] Factory robots

[0995] Embedded computers (e.g., NVIDIA Jetson Nano)

[0996] software

[0997] Operating System: Linux

[0998] Programming language: Python

[0999] Web server: Flask

[1000] Database: PostgreSQL

[1001] Generative AI model: GPT-4 (OpenAI API)

[1002] Data processing and calculation flow

[1003] 1. User operations

[1004] Factory workers use the robot's on-board touchscreen to input queries for specific technical information or research papers, such as "properties of new materials."

[1005] 2. Device Operation

[1006] The entered query is sent via a user interface to the server, which verifies that the received query is well-formed and parses it appropriately.

[1007] 3. Server Operation

[1008] The server passes the query analysis results to the generation AI, which then searches the database for relevant literature and selects the most relevant literature.

[1009] 4. Controlling the Generative AI

[1010] The generation AI retrieves the full text of the selected documents and extracts the main points, conclusions, and important data from each document to generate a summary.

[1011] 5. Server Operation

[1012] The server sends the formatted data to the terminal in order to return the generated summary to the user interface.

[1013] 6. User Interface Operation

[1014] Factory workers can view summaries via touchscreen panels and click on links to view more detailed information about documents that interest them.

[1015] Specific examples

[1016] If a factory worker wants to research the properties of a new material, he or she can enter "properties of new material" into the robot's search form. The system will then search the database for relevant technical literature and display its summary. For example,

[1017] "Research into the properties and applications of new material X"

[1018] "Heat resistance of new materials and their potential uses"

[1019] "Improved product strength through the use of new materials"

[1020] Workers can view the summary and, if they want to learn more about "Improving product strength through the use of new materials," they can click on a link to view the full text.

[1021] Prompt Sentence Examples

[1022] "Find relevant technical literature and generate summaries of them based on the following query: 'properties of new materials'. For each publication, include the main points, conclusions, and key data."

[1023] This invention allows factory workers to quickly search and obtain summaries of relevant technical literature, which can contribute to improving manufacturing processes and resolving problems.

[1024] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1025] Step 1:

[1026] User query input

[1027] Factory workers use the robot's touchscreen to input queries for specific technical information or research papers, such as "properties of a new material." Input is received from the user interface and transmitted to the server.

[1028] Step 2:

[1029] Query analysis by the server

[1030] The server parses the search query received from the user interface. First, it checks whether the received data is in the correct format, and then it parses the query to generate appropriate search parameters. The input is the query "properties of new materials," and the output is the parsed search parameters.

[1031] Step 3:

[1032] Literature search using generative AI

[1033] The server passes the generated search parameters to the generation AI, which then searches the database for relevant literature based on the search parameters. The AI ​​model (e.g., GPT-4) searches for literature according to the prompt. The input is the search parameters, and the output is a list of matching literature.

[1034] Step 4:

[1035] Full-text document acquisition and summary generation

[1036] Generative AI takes the full text of the documents retrieved through the search and generates a summary for each document. The summary includes the main idea, conclusion, and important data. The input is the full text of the document, and the output is the summarized information. Generative AI extracts the main idea, conclusion, and important data from the document and generates a summary.

[1037] Step 5:

[1038] Data formatting and transmission by the server

[1039] The server formats the summary received from the generation AI and converts it into a data format for sending back to the user interface. The server then sends the formatted data to the user interface. The input is the summarized bibliographic information, and the output is the formatted summary data.

[1040] Step 6:

[1041] Summary display in the user interface

[1042] The user interface displays the summaries received from the server on a touch panel. Factory workers check the displayed summaries and click on links for more information. The input is the summarized literature information, and the output is the summary displayed on the user interface. Clicking on a link also displays the full text of the literature for more information.

[1043] Step 7:

[1044] View user details

[1045] A factory worker clicks on a link to view detailed information about a document of interest. This displays the full text of the document, enabling deeper understanding and analysis. The input is the user's request for more information, and the output is the full text of the document.

[1046] The above processing steps allow factory personnel to efficiently search technical literature, quickly review summaries, and obtain further details.

[1047] 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.

[1048] Overall system overview

[1049] This system allows medical professionals to efficiently search for medical papers and quickly obtain their summaries. It incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on those emotions. The system mainly consists of the following components: user interface, server, generative AI, database, and emotion engine.

[1050] Functions of each component

[1051] User Interface

[1052] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[1053] server

[1054] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[1055] Generation AI

[1056] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[1057] Database

[1058] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[1059] Emotion Engine

[1060] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[1061] Program Operation

[1062] 1. User operations

[1063] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[1064] 2. Device Operation

[1065] The device sends the collected emotion data along with the input query to the server, which verifies that the query and emotion data are in the correct format.

[1066] 3. Server Operation

[1067] The server receives the query and emotion data, analyzes the query and the emotion data, and based on the analysis results, generates search parameters and emotion data that need further processing by the generative AI and emotion engine.

[1068] 4. Controlling the Generative AI

[1069] The generative AI uses analytical parameters to search medical databases, select relevant literature, and automatically generate summaries.

[1070] 5. Manipulating the Emotion Engine

[1071] The emotion engine complements, modifies, and optimizes generated summaries and search results based on the user's emotions. For example, if the user is feeling stressed, the emotion engine will provide a simpler and more understandable summary.

[1072] 6. Server Operation

[1073] It receives summaries returned by the generative AI and emotion engine, formats the data for display in the user interface, and sends the formatted data to the device in a specific format (e.g., JSON).

[1074] 7. Device Operation

[1075] The device receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[1076] 8. Display and Use

[1077] The user's device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the summaries and click on the paper that interests him to view detailed information. Using the summarized information, he can quickly and efficiently obtain the information he needs.

[1078] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[1079] The processing flow will be explained below.

[1080] Step 1:

[1081] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[1082] Step 2:

[1083] The device validates the entered search query and collected sentiment data to ensure they are in the proper format, and then generates an API request to send to the server.

[1084] Step 3:

[1085] The device then sends the generated API request to the server, which includes the search query and sentiment data.

[1086] Step 4:

[1087] The server receives search queries and emotion data from the device, analyzes the received data, and passes the search parameters and emotion data to the generation AI and emotion engine.

[1088] Step 5:

[1089] The generation AI uses search parameters provided by the server to search the database for relevant medical papers, selecting up to eight highly relevant papers.

[1090] Step 6:

[1091] The AI ​​retrieves the full text of the selected papers, extracts key content, and automatically generates a summary for each paper, including the main points, conclusions, and key data.

[1092] Step 7:

[1093] The emotion engine analyzes the user's emotional data and complements, corrects, and optimizes the generated summaries and search results based on that data. For example, if the user is feeling stressed, it will provide a simpler and easier-to-understand summary.

[1094] Step 8:

[1095] The server receives the summaries returned by the generative AI and emotion engine and formats the data for display in the user interface in a specific format, such as JSON.

[1096] Step 9:

[1097] The terminal receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[1098] Step 10:

[1099] The device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the abstracts and click to view more information about the paper that interests her.

[1100] Step 11:

[1101] Users can quickly obtain important information based on the optimized summary and, if necessary, click on a link to the original text to view more detailed information.

[1102] This will enable healthcare professionals, who are users, to quickly and efficiently access the latest medical information that is optimized using emotional data.

[1103] Example 2

[1104] 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."

[1105] Conventional medical paper search systems make it difficult for medical professionals to efficiently obtain the information they need. In particular, they provide uniform results without considering the user's emotional state, which can cause stress and waste time. This creates a high demand for a system that can quickly and effectively search and summarize medical papers.

[1106] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, generation AI means for searching a database for related documents based on the analyzed search query, generation AI means for automatically generating a summary from the retrieved documents, means for transmitting data from the server to display the generated summary on the user interface, and emotion engine means for recognizing user emotion data and complementing, correcting, and optimizing the summary based on the emotion. This enables more efficient and appropriate information provision while taking the user's emotional state into consideration.

[1107] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[1108] A "user interface" is an interface that provides a screen or input form for a user to interact with a system.

[1109] A "server" is a computer system that receives requests from users, analyzes them, and passes appropriate data to the generative AI or emotion engine.

[1110] "Generative AI" is an artificial intelligence technology that searches for relevant literature from a database based on a search query, extracts important content from each document, and generates a summary.

[1111] A "database" is a system for storing and managing vast amounts of bibliographic information.

[1112] An "emotion engine" is a system that analyzes emotional data obtained from a user's facial expressions, voice, etc., and complements, corrects, and optimizes search results and summaries based on those emotions.

[1113] A "summary" is a compact summary that extracts the main points, conclusions, important data, etc. of a document.

[1114] "Emotion data" is information collected from facial expressions and voice to understand the user's emotional state.

[1115] MODE FOR CARRYING OUT THE INVENTION

[1116] The present invention relates to a system for medical professionals to efficiently search medical papers and quickly obtain their summaries. The system incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on the emotions. Specific embodiments of the system are described below.

[1117] System Components

[1118] The system mainly consists of the following components:

[1119] User Interface

[1120] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[1121] server

[1122] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[1123] Generation AI

[1124] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[1125] Database

[1126] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[1127] Emotion Engine

[1128] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[1129] System Operation

[1130] When a user enters a query into the search form, the system sends the query along with the user's emotional data to the server. The server analyzes this data and passes appropriate search parameters to the generation AI. The generation AI searches the database and generates summaries of relevant literature. The emotion engine complements, corrects, and optimizes the generated summaries and search results based on the user's emotions. The final search results and summaries are displayed on the user interface via the server.

[1131] For example, if a doctor enters a query such as "COVID-19 vaccine effectiveness" and clicks the search button, the query and the acquired emotion data are sent to the server. The server analyzes the query and emotion data and passes appropriate search parameters to the generation AI. The generation AI searches for relevant papers and generates a summary. The emotion engine analyzes the summary and optimizes it based on the user's emotion. The summarized content is then displayed in the user interface.

[1132] Prompt Sentence Examples

[1133] Below is an example of a prompt sentence to input to the generative AI model.

[1134] User query: "COVID-19 vaccine effectiveness"

[1135] User sentiment: "Tension: High"

[1136] To search for relevant medical articles and generate summaries of:

[1137] Purpose of the paper

[1138] conclusion

[1139] Important Data

[1140] Concise and easy-to-understand expression

[1141] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[1142] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1143] Step 1:

[1144] User query input and sentiment data collection

[1145] A user enters a query into a search form on their device and clicks the search button. This action causes the device to collect emotional data from facial expressions and voice using the user's camera and microphone. For example, a doctor may enter a search query such as "COVID-19 vaccine effectiveness," and emotional data may be recorded from facial expressions and tone of voice.

[1146] Input: User search query and emotional data (e.g., facial expressions, voice)

[1147] Output: Collected search queries and sentiment data

[1148] Step 2:

[1149] Sending data from the device to the server

[1150] The device checks the query entered by the user and the format of the collected emotion data, converts it into an appropriate format (e.g., JSON), and sends it to the server. For example, data is sent in the following JSON format:

[1151] json

[1152] {

[1153] "query": "COVID-19 vaccine effectiveness",

[1154] "emotion_data": {

[1155] "stress": 0.8,

[1156] "anxiety": 0.7

[1157] }

[1158] }

[1159] Input: User search query and sentiment data

[1160] Output: JSON format data sent to the server

[1161] Step 3:

[1162] Server-side query and sentiment analysis

[1163] The server analyzes the data received from the device. First, it decomposes and analyzes the query to generate search parameters. It also analyzes the emotional data to evaluate the user's emotional state, and based on the results, generates data for the generation AI and emotion engine.

[1164] Input: JSON format data sent from the terminal

[1165] Output: Parsed data to feed into generative AI and emotion engines

[1166] Step 4:

[1167] Paper search and summary generation using generative AI

[1168] The generation AI searches a database of medical papers using search parameters provided by the server. It selects relevant papers, extracts the gist, conclusions, and important data from each paper, and generates a summary. For example, it searches for multiple papers on "COVID-19 vaccine effectiveness" and generates a summary for each.

[1169] Input: Search parameters provided by the server

[1170] Output: Abstracted bibliographic information

[1171] Step 5:

[1172] Summarization optimization using emotion engine

[1173] The emotion engine analyzes the summary received from the generative AI and optimizes it based on the user's emotional state. For example, if the user is feeling stressed, it will modify the summary to make it more concise and easy to understand.

[1174] Input: Summary provided by the generative AI and user sentiment data

[1175] Output: Optimized summary information

[1176] Step 6:

[1177] Formatting and sending data from the server to the terminal

[1178] The server receives the optimized summary and formats it for display in the user interface. This formatted data might be in JSON format, for example:

[1179] json

[1180] {

[1181] "title": "COVID-19 Vaccine Effectiveness",

[1182] "authors": ["Author 1", "Author 2"],

[1183] "published_year": 2021,

[1184] "summary": "This paper is a study examining the effectiveness of COVID-19 vaccines, and its main conclusion is XXX. Key data is YYY."

[1185] }

[1186] This data is sent to the terminal.

[1187] Input: Optimized summary provided by the sentiment engine

[1188] Output: Data formatted to send to the terminal

[1189] Step 7:

[1190] Data parsing and display on the device

[1191] The device parses the data received from the server, converts it into a human-readable format, and displays it in a user interface, using HTML and CSS to format the search results so that the title, author, publication year, and abstract are easily readable.

[1192] Input: Formatted data sent from the server

[1193] Output: Search results displayed in the user interface

[1194] Step 8:

[1195] User review and use of information

[1196] Users can check the abstracts and titles of papers displayed on their devices and click on the paper they are interested in to view detailed information, allowing them to quickly and efficiently obtain the information they need and use it in their clinical practice and research activities.

[1197] Input: Search results displayed in the user interface

[1198] Output: Specific paper information that the user retrieves

[1199] (Application example 2)

[1200] 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."

[1201] Conventional information search systems have the problem of not being able to quickly provide optimal information that users desire because they do not take into account the emotional state of the user. Furthermore, the lack of emotion-based information optimization makes it difficult to improve user satisfaction. The purpose of this invention is to solve these problems.

[1202] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing emotion data along with an input search query, generation AI means for searching a database for related information based on the analyzed search query and emotion data, generation AI means for automatically generating a summary from the searched information, and means for transmitting data from the server to display information optimized based on the generated summary and emotions on a user interface. This makes it possible to quickly and efficiently provide information optimized based on the user's emotional state.

[1203] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[1204] A "user interface" is an interface through which a user interacts with a system or application.

[1205] The "server means" is a computer system that has the function of receiving and analyzing information input from a user interface.

[1206] "Emotion data" is data that indicates the user's emotional state, collected from the user's facial expressions, voice, etc.

[1207] A "generative AI means" is a system that uses artificial intelligence to analyze data, extract relevant information, and generate summaries.

[1208] A "database" is a repository of vast amounts of information that can be used to retrieve relevant information based on a search query.

[1209] "Search parameters" are specific indicators or conditions for extracting related information that are generated by combining a search query and emotion data.

[1210] A "summary" is a shortened version of the main content of the retrieved information.

[1211] "Optimization" is the process of tailoring information based on the user's emotional data to present it in a more useful way.

[1212] This invention provides an information retrieval system that optimizes information based on the user's emotional state. Specifically, it analyzes the user's emotional data in addition to the search query entered by the user, and presents optimized information.

[1213] Overall system overview

[1214] The system consists of the following main components: user interface, server, generative AI, database, and emotion engine.

[1215] User Interface

[1216] The user interface is the interface through which users enter search queries. Specifically, they can enter keywords or phrases into a search form using devices such as smartphones or smart glasses. At this time, the user's emotional data is also collected using a camera and microphone.

[1217] Server Means

[1218] The server receives the search query and sentiment data sent from the user interface and analyzes them appropriately. After analysis, it passes the search parameters to the generation AI. It also returns the search results and summaries returned by the generation AI to the user interface for display.

[1219] Generation AI means

[1220] Generative AI has the ability to search a database based on a search query and sentiment data, find relevant information, automatically extract key content from each piece of information, and generate a summary that includes the gist, conclusion, and key data of the information.

[1221] Database

[1222] The database is a repository that stores a vast amount of information. The generative AI queries the database based on the search query and sentiment data to retrieve relevant information.

[1223] Emotion Engine

[1224] The emotion engine analyzes emotion data collected from the user's device to complete or modify search queries and optimize the summaries displayed. For example, if the user is feeling stressed, the emotion engine will provide a simpler and easier-to-understand summary.

[1225] Explanation of program processing

[1226] The server receives and analyzes the search query and sentiment data sent by the user. Natural language processing (NLP) and machine learning algorithms are used for the analysis. The analyzed search query and sentiment data are used as database search parameters by the generative AI.

[1227] Hardware and software used

[1228] Camera and microphone: Used to collect user emotional data.

[1229] OpenCV: Used for face recognition and facial expression analysis.

[1230] Keras: A deep learning library used to build emotion recognition models.

[1231] Flask: A web framework used for server-side API processing.

[1232] Specific examples

[1233] For example, if a user enters "advertising" as a search query and their facial expression is captured by the camera, the system will analyze the emotional data and recognize that the user is feeling "joy." Based on this, the generative AI will search for related advertisements and provide advertising information optimized for that emotion.

[1234] Prompt Sentence Examples

[1235] "Generate the optimal ad to show when the user has a happy expression."

[1236] This method allows for quick and efficient provision of information optimized based on the user's emotional state.

[1237] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1238] Step 1:

[1239] The user enters a search query into the device's user interface. Specifically, they enter a keyword or phrase into the search form on their smartphone or smart glasses and click the search button. At this time, the user's facial expressions and voice are collected using a camera and microphone. Input: Search query, emotion data. Output: Search query, collected emotion data.

[1240] Step 2:

[1241] The device sends the entered search query and emotion data to the server. This includes a process to ensure that the query and emotion data are in the appropriate format. For example, the query is in text format, and the emotion data is in image and audio data. Input: Search query, emotion data. Output: Data formatted in JSON format.

[1242] Step 3:

[1243] The server analyzes the received search query and emotion data. Here, it uses natural language processing (NLP) to analyze the query and machine learning algorithms to analyze the emotion data. For example, OpenCV and Keras are used to classify emotions from facial expressions. Input: Data in JSON format. Output: Analyzed search query, analyzed emotion data.

[1244] Step 4:

[1245] Based on the analysis results, the server passes search parameters to the generation AI. The generation AI uses these parameters to search the database. As a specific example, the generation AI uses libraries such as TensorFlow or PyTorch to retrieve information related to the query from the database. Input: Parsed search query, parsed emotion data. Output: List of related information.

[1246] Step 5:

[1247] Generative AI extracts key content from retrieved information and automatically generates a summary. This uses information summarization algorithms to extract the gist and important data. Input: List of relevant information. Output: Automatically generated summary.

[1248] Step 6:

[1249] The emotion engine optimizes the generated summary. For example, if the user is feeling stressed, the summary is converted into a simple and easy-to-understand format. Input: Automatically generated summary, analyzed emotion data. Output: Optimized summary.

[1250] Step 7:

[1251] The server formats the data to display an optimized summary in the user interface. The data is sent to the device in a specific format (e.g. JSON). Input: Optimized summary. Output: Data formatted in a form that can be displayed in the user interface.

[1252] Step 8:

[1253] The device receives the formatted data from the server, parses it, and displays it in the user interface. The user can review the generated summary and related information and click to view more information. Input: Formatted data. Output: Optimized summary displayed in the user interface.

[1254] 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.

[1255] 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.

[1256] 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.

[1257] [Fourth embodiment]

[1258] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1259] 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.

[1260] 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).

[1261] 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.

[1262] 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.

[1263] 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).

[1264] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1265] 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.

[1266] 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.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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."

[1271] Overall system overview

[1272] This system allows medical professionals to efficiently search medical papers and quickly obtain their summaries. The system mainly consists of the following components: a user interface, a server, a generative AI, and a database.

[1273] Functions of each component

[1274] User Interface

[1275] The user interface provides a search form for the healthcare professional to enter a search query, enter a specific keyword or phrase, and click a search button, which sends the query to the server.

[1276] server

[1277] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface.

[1278] Generation AI

[1279] The generative AI searches medical databases based on the search query passed from the server. The generative AI searches for relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[1280] Database

[1281] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[1282] Program Operation

[1283] 1. User operations

[1284] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[1285] 2. Device Operation

[1286] The terminal sends the entered query to the server, which checks that the query is in the correct format.

[1287] 3. Server Operation

[1288] The server receives the query and passes the search parameters to the AI ​​generator, which then searches the database and selects relevant papers, up to a maximum of eight of the most relevant papers.

[1289] 4. Controlling the Generative AI

[1290] The generative AI takes the full text of the selected papers and automatically generates a summary for each one, including the main points, conclusions, and key data.

[1291] 5. Server Operation

[1292] The server formats the received data and sends it to the terminal in order to return the generated summary to the user interface.

[1293] 6. Device Operation

[1294] The terminal receives the response from the server and displays it on the user interface. Tanaka can check the displayed summaries, select the paper that interests him, and read it in more detail.

[1295] 7. User Usage

[1296] Tanaka can view the displayed summary and, if necessary, click on a link to the original text to view more detailed information. For example, if he needs more detailed data based on the summarized information, he can download the original text and read it.

[1297] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[1298] The processing flow will be explained below.

[1299] Step 1:

[1300] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness."

[1301] Step 2:

[1302] The device validates the entered search query, checking whether the query is properly formed and displaying an error message to the user if it is not.

[1303] Step 3:

[1304] The device sends the verified search query to the server, generating an API request and sending it to the server's specified endpoint.

[1305] Step 4:

[1306] The server receives the search query from the device, analyzes the query, and based on the analysis results, generates search parameters that require further processing by the generation AI.

[1307] Step 5:

[1308] The server passes the generated search parameters to the generation AI, which uses these parameters to search for relevant medical papers.

[1309] Step 6:

[1310] The generative AI runs search queries against medical databases to retrieve relevant papers, then selects up to eight of the most relevant papers.

[1311] Step 7:

[1312] The AI ​​takes the full text of the selected papers and automatically generates a summary for each one, including the paper's main points, conclusions, and key data.

[1313] Step 8:

[1314] The server receives the summary returned by the generation AI, formats the data for display in the user interface, and sends the formatted data back to the device in a specific format (e.g., JSON).

[1315] Step 9:

[1316] The device receives the response from the server, parses the data, and converts the formatted data into a format for display in the user interface.

[1317] Step 10:

[1318] The terminal displays the paper title, author, publication year, and abstract on the screen in a format that is easy for the user to see.

[1319] Step 11:

[1320] Users can check the displayed abstracts and click on the abstract of the paper they are interested in to view more detailed information. If necessary, they can click on the link to the original article to view more detailed information.

[1321] This series of processes allows users, who are medical professionals, to access the latest medical information quickly and efficiently, which can be useful in clinical practice and research activities.

[1322] Example 1

[1323] 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."

[1324] In today's medical field, many medical professionals are required to quickly access vast amounts of academic materials and efficiently understand their contents. However, with existing systems, the process of entering a search query, retrieving relevant materials, and generating summaries is time-consuming and laborious. Furthermore, these operations are often cumbersome and require specialized medical knowledge. This makes it difficult for medical professionals to quickly and efficiently refer to the latest medical information.

[1325] 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.

[1326] In this invention, the server includes: means for providing an operation unit for inputting a search query; control unit means for receiving and analyzing the input search query; generation AI means for searching an information storage device for relevant academic materials based on the analyzed search query; generation AI means for automatically generating summaries from the searched materials; and means for transmitting data from the control unit to display the generated summaries on the operation unit. This enables relevant academic materials to be quickly obtained based on a search query input by a medical professional, and their summaries to be automatically generated and displayed. This allows medical professionals to efficiently access the latest medical information and effectively utilize it in their daily clinical practice and research activities.

[1327] A "search query" is a keyword or phrase that a user enters to search for specific information.

[1328] The "operation unit" is a user interface that allows the user to input information and perform operations such as searches.

[1329] "Controller means" refers to a server or computer system for receiving and analyzing input search queries.

[1330] A "generative AI means" is a type of artificial intelligence that has the function of searching an information storage device based on a received search query, selecting relevant academic materials, and automatically generating a summary.

[1331] An "information storage device" is a database system that stores a huge amount of academic materials and data.

[1332] The "means for transmitting data" is a communication function for transmitting data from the control device in order to display the generated summary data on the operation unit.

[1333] "Academic materials" refers to literature related to specialized fields, such as medical papers and research reports.

[1334] A "summary" is a text that concisely summarizes the main content, conclusions, and important data of academic material.

[1335] This system allows medical professionals to efficiently search for academic materials and quickly obtain their summaries. The system mainly consists of the following components: an operating unit, a control unit, a generation AI, and an information storage unit.

[1336] Operation section

[1337] The operation unit provides a user interface for users to enter search queries. When a user enters a specific keyword or phrase into the operation unit's search form and clicks the search button, the query is sent to the control device. For example, a user might enter "COVID-19 vaccine effectiveness."

[1338] control device

[1339] The control device receives and analyzes the search query sent from the operation unit. This analysis includes properly formatting the received search query and passing it to the generation AI. It also receives the summary results returned by the generation AI and sends the data to the operation unit. Specifically, the control device packs the data in JSON format and sends and receives the data via HTTP requests and responses.

[1340] Generation AI

[1341] The generative AI searches the information storage device based on a search query passed from the control device. It typically uses an artificial intelligence model and implements advanced natural language processing algorithms. It selects relevant academic materials and extracts up to eight of the most relevant papers. It then automatically generates a summary for each paper, including the paper's main idea, conclusions, and key data.

[1342] Information Storage Device

[1343] The information storage device is a database system that stores a vast amount of academic materials. The generative AI queries the database based on the search query to retrieve relevant materials.

[1344] Specific examples

[1345] Dr. Tanaka enters "COVID-19 vaccine effectiveness" into the search form on the control unit and clicks the search button. The query is sent to the control unit, which then sends it to the generation AI. The generation AI searches the information storage device, extracts up to eight relevant papers, and generates a summary of each paper. The summaries are sent back to the control unit, and the formatted data is displayed on the control unit. Dr. Tanaka can review the displayed summaries and select papers of interest for further reading.

[1346] Prompt Sentence Examples

[1347] "Please find and provide a summary of the latest academic literature on the effectiveness of COVID-19 vaccines."

[1348] The system provides healthcare professionals with rapid access to the latest, most relevant medical information to aid in their daily clinical practice and research activities.

[1349] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1350] Step 1:

[1351] A user enters a query into the search form on the control panel and clicks the search button. For example, a doctor enters "COVID-19 vaccine effectiveness."

[1352] Input: Search query "COVID-19 vaccine effectiveness"

[1353] Output: Search button click action

[1354] Specific action: The user enters a query into the search form and clicks the search button.

[1355] Step 2:

[1356] The terminal receives the entered search query, verifies that the query is properly formatted, and then transmits the query to the control device.

[1357] Input: Search query "COVID-19 vaccine effectiveness"

[1358] Output: Search query sent in HTTP request format

[1359] Specific operation: The terminal packs the query in JSON format and sends it to the control device via an HTTP request.

[1360] Step 3:

[1361] The server (controller) analyzes the received query and passes it to the generation AI as search parameters. Analysis includes understanding the content of the query and formatting it appropriately.

[1362] Input: Search query in HTTP request format

[1363] Output: Search parameters for the generation AI

[1364] What happens: The server parses the query and sends parameters to the generator AI in the following format:

[1365] json

[1366] {

[1367] "query": "COVID-19 vaccine effectiveness",

[1368] "maximum_results": 8

[1369] }

[1370] Step 4:

[1371] The generation AI receives search parameters from the server, searches the specified information storage device, selects relevant academic materials, and extracts up to eight of the most relevant materials from among them.

[1372] Input: Search parameters (query "COVID-19 vaccine effectiveness", maximum results 8)

[1373] Output: Metadata and full text of associated material

[1374] Specific operation: The generating AI searches the information storage device (database) and extracts relevant materials.

[1375] Step 5:

[1376] The generative AI takes the full text of the selected documents and automatically generates a summary for each document, including the main idea, conclusion, and key data.

[1377] Input: Metadata and full text of relevant material

[1378] Output: Summary of the material

[1379] How it works: Generative AI uses natural language processing algorithms to generate summaries of materials.

[1380] Step 6:

[1381] The server (controller) receives the summary results returned by the generation AI, formats them, and sends them to the terminal. Formatting includes converting the data into a format that is easy for users to view.

[1382] Input: Summary of material from generative AI

[1383] Output: Summary data in HTTP response format

[1384] Specific operation: The server analyzes and formats the summary results returned by the generation AI and sends them to the terminal as an HTTP response.

[1385] Step 7:

[1386] The terminal receives the summary information sent from the server and displays it on the user interface. The user can then check the displayed summaries, select the paper of interest, and view it in more detail.

[1387] Input: Summary data in HTTP response format

[1388] Output: Summary information displayed in the user interface

[1389] Specific operation: The terminal analyzes the received summary data and displays it in list format on the user interface.

[1390] This concretely shows the flow of the entire system, clarifies the input and output of each step, and allows you to understand how data is processed or calculated.

[1391] (Application example 1)

[1392] 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."

[1393] Modern factories lack a means to quickly and efficiently retrieve technical literature and research papers related to manufacturing processes and review their summaries. This results in workers spending a great deal of time and effort to obtain the necessary information, resulting in reduced productivity. Furthermore, delays in retrieving and interpreting information hinder efficient factory operations and rapid problem resolution. Therefore, there is a need for a system that allows factory workers to easily search for technical literature and quickly retrieve its summaries.

[1394] 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.

[1395] In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, means for generating AI to search a database for relevant documents based on the analyzed search query, means for automatically generating summaries from the retrieved documents, means for transmitting data to display the generated summaries on the user interface, and means for reviewing the summarized documents and providing links to display detailed information, thereby enabling factory workers to efficiently search for relevant technical documents and quickly review their summaries.

[1396] A "search query" refers to a keyword or phrase entered by a user to retrieve related literature information.

[1397] "User Interface" refers to the screen or interactive means by which a user enters a search query and interacts with the system.

[1398] "Server" refers to the computer system responsible for analyzing the received search query and passing the search parameters to the generation AI.

[1399] "Generative AI" refers to an artificial intelligence model that searches for relevant literature based on a received search query and automatically generates a summary of it.

[1400] "Database" refers to a repository that stores a vast amount of relevant bibliographic information.

[1401] An "abstract" refers to information that concisely summarizes the main points, conclusions, and important data of a document.

[1402] "Link" refers to an associated URL or reference point for further information after reviewing the abstracted literature.

[1403] The system that realizes this invention aims to enable factory workers to efficiently search technical literature and quickly obtain summaries. The system consists of the following main components: a user interface, a server, a generative AI, and a database.

[1404] Hardware and Software

[1405] Hardware

[1406] Factory robots

[1407] Embedded computers (e.g., NVIDIA Jetson Nano)

[1408] software

[1409] Operating System: Linux

[1410] Programming language: Python

[1411] Web server: Flask

[1412] Database: PostgreSQL

[1413] Generative AI model: GPT-4 (OpenAI API)

[1414] Data processing and calculation flow

[1415] 1. User operations

[1416] Factory workers use the robot's on-board touchscreen to input queries for specific technical information or research papers, such as "properties of new materials."

[1417] 2. Device Operation

[1418] The entered query is sent via a user interface to the server, which verifies that the received query is well-formed and parses it appropriately.

[1419] 3. Server Operation

[1420] The server passes the query analysis results to the generation AI, which then searches the database for relevant literature and selects the most relevant literature.

[1421] 4. Controlling the Generative AI

[1422] The generation AI retrieves the full text of the selected documents and extracts the main points, conclusions, and important data from each document to generate a summary.

[1423] 5. Server Operation

[1424] The server sends the formatted data to the terminal in order to return the generated summary to the user interface.

[1425] 6. User Interface Operation

[1426] Factory workers can view summaries via touchscreen panels and click on links to view more detailed information about documents that interest them.

[1427] Specific examples

[1428] If a factory worker wants to research the properties of a new material, he or she can enter "properties of new material" into the robot's search form. The system will then search the database for relevant technical literature and display its summary. For example,

[1429] "Research into the properties and applications of new material X"

[1430] "Heat resistance of new materials and their potential uses"

[1431] "Improved product strength through the use of new materials"

[1432] Workers can view the summary and, if they want to learn more about "Improving product strength through the use of new materials," they can click on a link to view the full text.

[1433] Prompt Sentence Examples

[1434] "Find relevant technical literature and generate summaries of them based on the following query: 'properties of new materials'. For each publication, include the main points, conclusions, and key data."

[1435] This invention allows factory workers to quickly search and obtain summaries of relevant technical literature, which can contribute to improving manufacturing processes and resolving problems.

[1436] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1437] Step 1:

[1438] User query input

[1439] Factory workers use the robot's touchscreen to input queries for specific technical information or research papers, such as "properties of a new material." Input is received from the user interface and transmitted to the server.

[1440] Step 2:

[1441] Query analysis by the server

[1442] The server parses the search query received from the user interface. First, it checks whether the received data is in the correct format, and then it parses the query to generate appropriate search parameters. The input is the query "properties of new materials," and the output is the parsed search parameters.

[1443] Step 3:

[1444] Literature search using generative AI

[1445] The server passes the generated search parameters to the generation AI, which then searches the database for relevant literature based on the search parameters. The AI ​​model (e.g., GPT-4) searches for literature according to the prompt. The input is the search parameters, and the output is a list of matching literature.

[1446] Step 4:

[1447] Full-text document acquisition and summary generation

[1448] Generative AI takes the full text of the documents retrieved through the search and generates a summary for each document. The summary includes the main idea, conclusion, and important data. The input is the full text of the document, and the output is the summarized information. Generative AI extracts the main idea, conclusion, and important data from the document and generates a summary.

[1449] Step 5:

[1450] Data formatting and transmission by the server

[1451] The server formats the summary received from the generation AI and converts it into a data format for sending back to the user interface. The server then sends the formatted data to the user interface. The input is the summarized bibliographic information, and the output is the formatted summary data.

[1452] Step 6:

[1453] Summary display in the user interface

[1454] The user interface displays the summaries received from the server on a touch panel. Factory workers check the displayed summaries and click on links for more information. The input is the summarized literature information, and the output is the summary displayed on the user interface. Clicking on a link also displays the full text of the literature for more information.

[1455] Step 7:

[1456] View user details

[1457] A factory worker clicks on a link to view detailed information about a document of interest. This displays the full text of the document, enabling deeper understanding and analysis. The input is the user's request for more information, and the output is the full text of the document.

[1458] The above processing steps allow factory personnel to efficiently search technical literature, quickly review summaries, and obtain further details.

[1459] 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.

[1460] Overall system overview

[1461] This system allows medical professionals to efficiently search for medical papers and quickly obtain their summaries. It incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on those emotions. The system mainly consists of the following components: user interface, server, generative AI, database, and emotion engine.

[1462] Functions of each component

[1463] User Interface

[1464] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[1465] server

[1466] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[1467] Generation AI

[1468] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[1469] Database

[1470] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[1471] Emotion Engine

[1472] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[1473] Program Operation

[1474] 1. User operations

[1475] A healthcare professional enters a query into the search form on the device and clicks the search button. For example, let's say Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[1476] 2. Device Operation

[1477] The device sends the collected emotion data along with the input query to the server, which verifies that the query and emotion data are in the correct format.

[1478] 3. Server Operation

[1479] The server receives the query and emotion data, analyzes the query and the emotion data, and based on the analysis results, generates search parameters and emotion data that need further processing by the generative AI and emotion engine.

[1480] 4. Controlling the Generative AI

[1481] The generative AI uses analytical parameters to search medical databases, select relevant literature, and automatically generate summaries.

[1482] 5. Manipulating the Emotion Engine

[1483] The emotion engine complements, modifies, and optimizes generated summaries and search results based on the user's emotions. For example, if the user is feeling stressed, the emotion engine will provide a simpler and more understandable summary.

[1484] 6. Server Operation

[1485] It receives summaries returned by the generative AI and emotion engine, formats the data for display in the user interface, and sends the formatted data to the device in a specific format (e.g., JSON).

[1486] 7. Device Operation

[1487] The device receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[1488] 8. Display and Use

[1489] The user's device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the summaries and click on the paper that interests him to view detailed information. Using the summarized information, he can quickly and efficiently obtain the information he needs.

[1490] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] A user enters a search query and clicks the search button. For example, Dr. Tanaka enters "COVID-19 vaccine effectiveness." At this time, emotion data is collected from Dr. Tanaka's facial expressions and voice.

[1494] Step 2:

[1495] The device validates the entered search query and collected sentiment data to ensure they are in the proper format, and then generates an API request to send to the server.

[1496] Step 3:

[1497] The device then sends the generated API request to the server, which includes the search query and sentiment data.

[1498] Step 4:

[1499] The server receives search queries and emotion data from the device, analyzes the received data, and passes the search parameters and emotion data to the generation AI and emotion engine.

[1500] Step 5:

[1501] The generation AI uses search parameters provided by the server to search the database for relevant medical papers, selecting up to eight highly relevant papers.

[1502] Step 6:

[1503] The AI ​​retrieves the full text of the selected papers, extracts key content, and automatically generates a summary for each paper, including the main points, conclusions, and key data.

[1504] Step 7:

[1505] The emotion engine analyzes the user's emotional data and complements, corrects, and optimizes the generated summaries and search results based on that data. For example, if the user is feeling stressed, it will provide a simpler and easier-to-understand summary.

[1506] Step 8:

[1507] The server receives the summaries returned by the generative AI and emotion engine and formats the data for display in the user interface in a specific format, such as JSON.

[1508] Step 9:

[1509] The terminal receives the response from the server, parses the data, and converts it into a format for display in the user interface.

[1510] Step 10:

[1511] The device displays the paper title, author, publication year, and abstract in an easy-to-read format. Tanaka can review the abstracts and click to view more information about the paper that interests her.

[1512] Step 11:

[1513] Users can quickly obtain important information based on the optimized summary and, if necessary, click on a link to the original text to view more detailed information.

[1514] This will enable healthcare professionals, who are users, to quickly and efficiently access the latest medical information that is optimized using emotional data.

[1515] Example 2

[1516] 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."

[1517] Conventional medical paper search systems make it difficult for medical professionals to efficiently obtain the information they need. In particular, they provide uniform results without considering the user's emotional state, which can cause stress and waste time. This creates a high demand for a system that can quickly and effectively search and summarize medical papers.

[1518] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for providing a user interface for inputting a search query, means for receiving and analyzing the input search query, generation AI means for searching a database for related documents based on the analyzed search query, generation AI means for automatically generating a summary from the retrieved documents, means for transmitting data from the server to display the generated summary on the user interface, and emotion engine means for recognizing user emotion data and complementing, correcting, and optimizing the summary based on the emotion. This enables more efficient and appropriate information provision while taking the user's emotional state into consideration.

[1519] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[1520] A "user interface" is an interface that provides a screen or input form for a user to interact with a system.

[1521] A "server" is a computer system that receives requests from users, analyzes them, and passes appropriate data to the generative AI or emotion engine.

[1522] "Generative AI" is an artificial intelligence technology that searches for relevant literature from a database based on a search query, extracts important content from each document, and generates a summary.

[1523] A "database" is a system for storing and managing vast amounts of bibliographic information.

[1524] An "emotion engine" is a system that analyzes emotional data obtained from a user's facial expressions, voice, etc., and complements, corrects, and optimizes search results and summaries based on those emotions.

[1525] A "summary" is a compact summary that extracts the main points, conclusions, important data, etc. of a document.

[1526] "Emotion data" is information collected from facial expressions and voice to understand the user's emotional state.

[1527] MODE FOR CARRYING OUT THE INVENTION

[1528] The present invention relates to a system for medical professionals to efficiently search medical papers and quickly obtain their summaries. The system incorporates an emotion engine that recognizes the user's emotions and complements, corrects, and optimizes search results based on the emotions. Specific embodiments of the system are described below.

[1529] System Components

[1530] The system mainly consists of the following components:

[1531] User Interface

[1532] The user interface provides a search form for a medical professional to enter a search query, for example, a physician may enter a particular keyword or phrase and click a search button, which sends the query to the server.

[1533] server

[1534] The server receives the search query sent from the user interface, analyzes it appropriately, passes the search parameters to the generation AI, and returns the search results and summaries returned by the generation AI to the user interface for display.

[1535] Generation AI

[1536] The generative AI searches medical databases based on a search query passed from the server, finds relevant papers, automatically extracts important content from each paper, and generates a summary that includes the paper's main idea, conclusion, and key data.

[1537] Database

[1538] The database is a repository of a vast number of medical papers, and the generative AI queries the database based on the search query to retrieve relevant papers.

[1539] Emotion Engine

[1540] The emotion engine complements and corrects search queries and optimizes the displayed summary based on emotion data collected from the user's device. Emotion data is obtained from the user's facial expressions and voice and analyzed through appropriate processing.

[1541] System Operation

[1542] When a user enters a query into the search form, the system sends the query along with the user's emotional data to the server. The server analyzes this data and passes appropriate search parameters to the generation AI. The generation AI searches the database and generates summaries of relevant literature. The emotion engine complements, corrects, and optimizes the generated summaries and search results based on the user's emotions. The final search results and summaries are displayed on the user interface via the server.

[1543] For example, if a doctor enters a query such as "COVID-19 vaccine effectiveness" and clicks the search button, the query and the acquired emotion data are sent to the server. The server analyzes the query and emotion data and passes appropriate search parameters to the generation AI. The generation AI searches for relevant papers and generates a summary. The emotion engine analyzes the summary and optimizes it based on the user's emotion. The summarized content is then displayed in the user interface.

[1544] Prompt Sentence Examples

[1545] Below is an example of a prompt sentence to input to the generative AI model.

[1546] User query: "COVID-19 vaccine effectiveness"

[1547] User sentiment: "Tension: High"

[1548] To search for relevant medical articles and generate summaries of:

[1549] Purpose of the paper

[1550] conclusion

[1551] Important Data

[1552] Concise and easy-to-understand expression

[1553] This system enables medical professionals to quickly and efficiently obtain optimized information based on emotional data and use it in clinical practice and research activities.

[1554] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1555] Step 1:

[1556] User query input and sentiment data collection

[1557] A user enters a query into a search form on their device and clicks the search button. This action causes the device to collect emotional data from facial expressions and voice using the user's camera and microphone. For example, a doctor may enter a search query such as "COVID-19 vaccine effectiveness," and emotional data may be recorded from facial expressions and tone of voice.

[1558] Input: User search query and emotional data (e.g., facial expressions, voice)

[1559] Output: Collected search queries and sentiment data

[1560] Step 2:

[1561] Sending data from the device to the server

[1562] The device checks the query entered by the user and the format of the collected emotion data, converts it into an appropriate format (e.g., JSON), and sends it to the server. For example, data is sent in the following JSON format:

[1563] json

[1564] {

[1565] "query": "COVID-19 vaccine effectiveness",

[1566] "emotion_data": {

[1567] "stress": 0.8,

[1568] "anxiety": 0.7

[1569] }

[1570] }

[1571] Input: User search query and sentiment data

[1572] Output: JSON format data sent to the server

[1573] Step 3:

[1574] Server-side query and sentiment analysis

[1575] The server analyzes the data received from the device. First, it decomposes and analyzes the query to generate search parameters. It also analyzes the emotional data to evaluate the user's emotional state, and based on the results, generates data for the generation AI and emotion engine.

[1576] Input: JSON format data sent from the terminal

[1577] Output: Parsed data to feed into generative AI and emotion engines

[1578] Step 4:

[1579] Paper search and summary generation using generative AI

[1580] The generation AI searches a database of medical papers using search parameters provided by the server. It selects relevant papers, extracts the gist, conclusions, and important data from each paper, and generates a summary. For example, it searches for multiple papers on "COVID-19 vaccine effectiveness" and generates a summary for each.

[1581] Input: Search parameters provided by the server

[1582] Output: Abstracted bibliographic information

[1583] Step 5:

[1584] Summarization optimization using emotion engine

[1585] The emotion engine analyzes the summary received from the generative AI and optimizes it based on the user's emotional state. For example, if the user is feeling stressed, it will modify the summary to make it more concise and easy to understand.

[1586] Input: Summary provided by the generative AI and user sentiment data

[1587] Output: Optimized summary information

[1588] Step 6:

[1589] Formatting and sending data from the server to the terminal

[1590] The server receives the optimized summary and formats it for display in the user interface. This formatted data might be in JSON format, for example:

[1591] json

[1592] {

[1593] "title": "COVID-19 Vaccine Effectiveness",

[1594] "authors": ["Author 1", "Author 2"],

[1595] "published_year": 2021,

[1596] "summary": "This paper is a study examining the effectiveness of COVID-19 vaccines, and its main conclusion is XXX. Key data is YYY."

[1597] }

[1598] This data is sent to the terminal.

[1599] Input: Optimized summary provided by the sentiment engine

[1600] Output: Data formatted to send to the terminal

[1601] Step 7:

[1602] Data parsing and display on the device

[1603] The device parses the data received from the server, converts it into a human-readable format, and displays it in a user interface, using HTML and CSS to format the search results so that the title, author, publication year, and abstract are easily readable.

[1604] Input: Formatted data sent from the server

[1605] Output: Search results displayed in the user interface

[1606] Step 8:

[1607] User review and use of information

[1608] Users can check the abstracts and titles of papers displayed on their devices and click on the paper they are interested in to view detailed information, allowing them to quickly and efficiently obtain the information they need and use it in their clinical practice and research activities.

[1609] Input: Search results displayed in the user interface

[1610] Output: Specific paper information that the user retrieves

[1611] (Application example 2)

[1612] 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."

[1613] Conventional information search systems have the problem of not being able to quickly provide optimal information that users desire because they do not take into account the emotional state of the user. Furthermore, the lack of emotion-based information optimization makes it difficult to improve user satisfaction. The purpose of this invention is to solve these problems.

[1614] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving and analyzing emotion data along with an input search query, generation AI means for searching a database for related information based on the analyzed search query and emotion data, generation AI means for automatically generating a summary from the searched information, and means for transmitting data from the server to display information optimized based on the generated summary and emotions on a user interface. This makes it possible to quickly and efficiently provide information optimized based on the user's emotional state.

[1615] A "search query" is a keyword or phrase that a user enters to retrieve specific information.

[1616] A "user interface" is an interface through which a user interacts with a system or application.

[1617] The "server means" is a computer system that has the function of receiving and analyzing information input from a user interface.

[1618] "Emotion data" is data that indicates the user's emotional state, collected from the user's facial expressions, voice, etc.

[1619] A "generative AI means" is a system that uses artificial intelligence to analyze data, extract relevant information, and generate summaries.

[1620] A "database" is a repository of vast amounts of information that can be used to retrieve relevant information based on a search query.

[1621] "Search parameters" are specific indicators or conditions for extracting related information that are generated by combining a search query and emotion data.

[1622] A "summary" is a shortened version of the main content of the retrieved information.

[1623] "Optimization" is the process of tailoring information based on the user's emotional data to present it in a more useful way.

[1624] This invention provides an information retrieval system that optimizes information based on the user's emotional state. Specifically, it analyzes the user's emotional data in addition to the search query entered by the user, and presents optimized information.

[1625] Overall system overview

[1626] The system consists of the following main components: user interface, server, generative AI, database, and emotion engine.

[1627] User Interface

[1628] The user interface is the interface through which users enter search queries. Specifically, they can enter keywords or phrases into a search form using devices such as smartphones or smart glasses. At this time, the user's emotional data is also collected using a camera and microphone.

[1629] Server Means

[1630] The server receives the search query and sentiment data sent from the user interface and analyzes them appropriately. After analysis, it passes the search parameters to the generation AI. It also returns the search results and summaries returned by the generation AI to the user interface for display.

[1631] Generation AI means

[1632] Generative AI has the ability to search a database based on a search query and sentiment data, find relevant information, automatically extract key content from each piece of information, and generate a summary that includes the gist, conclusion, and key data of the information.

[1633] Database

[1634] The database is a repository that stores a huge amount of information. The generative AI queries the database based on the search query and sentiment data to retrieve relevant information.

[1635] Emotion Engine

[1636] The emotion engine analyzes emotion data collected from the user's device to complete or modify search queries and optimize the summaries displayed. For example, if the user is feeling stressed, the emotion engine will provide a simpler and easier-to-understand summary.

[1637] Explanation of program processing

[1638] The server receives and analyzes the search queries and sentiment data sent by users. Natural language processing (NLP) and machine learning algorithms are used for the analysis. The analyzed search queries and sentiment data are used as database search parameters by the generative AI.

[1639] Hardware and software used

[1640] Camera and microphone: Used to collect user emotional data.

[1641] OpenCV: Used for face recognition and facial expression analysis.

[1642] Keras: A deep learning library used to build emotion recognition models.

[1643] Flask: A web framework used for server-side API processing.

[1644] Specific examples

[1645] For example, if a user enters "advertising" as a search query and their facial expression is captured by the camera, the system will analyze the emotional data and recognize that the user is feeling "joy." Based on this, the generative AI will search for related advertisements and provide advertising information optimized for that emotion.

[1646] Prompt Sentence Examples

[1647] "Generate the optimal ad to show when the user has a happy expression."

[1648] This method allows for quick and efficient provision of information optimized based on the user's emotional state.

[1649] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1650] Step 1:

[1651] The user enters a search query into the device's user interface. Specifically, they enter a keyword or phrase into the search form on their smartphone or smart glasses and click the search button. At this time, the user's facial expressions and voice are collected using a camera and microphone. Input: Search query, emotion data. Output: Search query, collected emotion data.

[1652] Step 2:

[1653] The device sends the entered search query and emotion data to the server. This includes a process to ensure that the query and emotion data are in the appropriate format. For example, the query is in text format, and the emotion data is in image and audio data. Input: Search query, emotion data. Output: Data formatted in JSON format.

[1654] Step 3:

[1655] The server analyzes the received search query and emotion data. Here, it uses natural language processing (NLP) to analyze the query and machine learning algorithms to analyze the emotion data. For example, OpenCV and Keras are used to classify emotions from facial expressions. Input: Data in JSON format. Output: Analyzed search query, analyzed emotion data.

[1656] Step 4:

[1657] Based on the analysis results, the server passes search parameters to the generation AI. The generation AI uses these parameters to search the database. As a specific example, the generation AI uses libraries such as TensorFlow or PyTorch to retrieve information related to the query from the database. Input: Parsed search query, parsed emotion data. Output: List of related information.

[1658] Step 5:

[1659] Generative AI extracts key content from retrieved information and automatically generates a summary. This uses information summarization algorithms to extract the gist and important data. Input: List of relevant information. Output: Automatically generated summary.

[1660] Step 6:

[1661] The emotion engine optimizes the generated summary. For example, if the user is feeling stressed, the summary is converted into a simple and easy-to-understand format. Input: Automatically generated summary, analyzed emotion data. Output: Optimized summary.

[1662] Step 7:

[1663] The server formats the data to display an optimized summary in the user interface. The data is sent to the device in a specific format (e.g. JSON). Input: Optimized summary. Output: Data formatted in a form that can be displayed in the user interface.

[1664] Step 8:

[1665] The device receives the formatted data from the server, parses it, and displays it in the user interface. The user can review the generated summary and related information and click to view more information. Input: Formatted data. Output: Optimized summary displayed in the user interface.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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).

[1673] 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.

[1674] 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."

[1675] 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.

[1676] 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).

[1677] 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.

[1678] 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.

[1679] 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.

[1680] 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.

[1681] 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.

[1682] 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.

[1683] 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.

[1684] 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.

[1685] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1686] 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.

[1687] The following is further disclosed regarding the above embodiment.

[1688] (Claim 1)

[1689] means for providing a user interface for entering a search query;

[1690] a server means for receiving and analyzing the input search query;

[1691] A generative AI means for searching relevant medical papers from a database based on the analyzed search query;

[1692] A generation AI method that automatically generates summaries from retrieved papers;

[1693] means for transmitting data from the server for displaying the generated summary on a user interface;

[1694] A system including:

[1695] (Claim 2)

[1696] The system of claim 1, further comprising a generation AI means for analyzing a search query and generating search parameters for articles.

[1697] (Claim 3)

[1698] The system of claim 1 further comprises a generation AI means for retrieving the full text of the retrieved article from the database and extracting the main content based thereon.

[1699] "Example 1"

[1700] (Claim 1)

[1701] means for providing an operation unit for inputting a search query;

[1702] a controller means for receiving and analyzing the input search query;

[1703] a generating AI means for searching for relevant academic materials from an information storage device based on the analyzed search query;

[1704] A generative AI method that automatically generates summaries from retrieved materials;

[1705] means for transmitting data from the control device to display the generated summary on the operation unit;

[1706] A system including:

[1707] (Claim 2)

[1708] 10. The system of claim 1, further comprising a generation AI means for analyzing a search query and generating search parameters for the material.

[1709] (Claim 3)

[1710] The system according to claim 1, further comprising a generating AI means for retrieving the full text of the retrieved material from the information storage device and extracting the main content based thereon.

[1711] "Application Example 1"

[1712] (Claim 1)

[1713] means for providing a user interface for entering a search query;

[1714] a server means for receiving and analyzing the input search query;

[1715] A generative AI means for searching for relevant literature from a database based on the analyzed search query;

[1716] A generation AI method that automatically generates summaries from retrieved documents;

[1717] means for transmitting data from the server for displaying the generated summary on a user interface;

[1718] A means of reviewing the abstracted literature and providing links to view more information;

[1719] A system including:

[1720] (Claim 2)

[1721] 10. The system of claim 1, further comprising a generation AI means for analyzing a search query and generating search parameters for the literature.

[1722] (Claim 3)

[1723] The system of claim 1 further comprises a generating AI means for retrieving the full text of the retrieved document from the database and extracting key content based thereon.

[1724] "Example 2: Combining Emotion Engines"

[1725] (Claim 1)

[1726] means for providing a user interface for entering a search query;

[1727] a server means for receiving and analyzing the input search query;

[1728] A generative AI means for searching for relevant literature from a database based on the analyzed search query;

[1729] A generation AI method that automatically generates summaries from retrieved documents;

[1730] means for transmitting data from the server for displaying the generated summary on a user interface;

[1731] an emotion engine means for recognizing emotion data of a user and completing, modifying, and optimizing a summary based on the emotion;

[1732] A system including:

[1733] (Claim 2)

[1734] 10. The system of claim 1, further comprising a generation AI means for analyzing a search query and generating search parameters for the literature.

[1735] (Claim 3)

[1736] The system of claim 1 further comprises a generating AI means for retrieving the full text of the retrieved document from the database and extracting key content based thereon.

[1737] "Application example 2 when combining emotion engines"

[1738] (Claim 1)

[1739] means for providing a user interface for entering a search query;

[1740] a server means for receiving and analyzing emotion data along with an input search query;

[1741] a generative AI means for searching for relevant information from a database based on the analyzed search query and sentiment data;

[1742] A generative AI method that automatically generates summaries from searched information;

[1743] means for transmitting data from the server to display information optimized based on the generated summary and sentiment on a user interface;

[1744] A system including:

[1745] (Claim 2)

[1746] 2. The system of claim 1, further comprising a generation AI means for analyzing a search query and generating search parameters combined with emotion data.

[1747] (Claim 3)

[1748] The system according to claim 1, further comprising a generating AI means for obtaining the full text of the retrieved information from the database and extracting the main content based thereon. [Explanation of symbols]

[1749] 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. means for providing a user interface for entering a search query; a server means for receiving and analyzing the input search query; A generative AI means for searching relevant medical papers from a database based on the analyzed search query; A generation AI method that automatically generates summaries from retrieved papers; means for transmitting data from the server for displaying the generated summary on a user interface; A system including:

2. The system of claim 1 further comprising a generation AI means for analyzing a search query and generating search parameters for articles.

3. The system according to claim 1, further comprising a generating AI means for retrieving the full text of the retrieved article from the database and extracting the main content based thereon.

Images