system

Abstract

Provide a system. 【Solution means】 Means for automatically obtaining information from a huge database, Means for analyzing the obtained information to generate a new hypothesis, Interactive interface means for presenting the generated hypothesis and proposal to the user, Process management means for optimizing the research process, Means for integrating knowledge in different fields to create new research ideas, Means for analyzing data related to the manufacturing process to optimize process efficiency, Means for performing real-time anomaly detection and production line adjustment, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the medical research and pharmaceutical industries, a huge amount of time and resources are required for the research of new drugs and treatment methods, and there is a problem that a great deal of labor is involved in grasping and analyzing information. In addition, there are many uncertainties in the development of new drugs, and there is also a problem of low success rate. Therefore, it is desired to solve these problems by efficiently and quickly analyzing a huge amount of data and optimizing the research strategy.

Means for Solving the Problems

[0005] This invention provides a means for automatically acquiring and analyzing information from a database, and offers an interactive interface that presents the generated hypotheses and proposals to the user. It also includes process management means for optimizing the research process and provides a system that can generate new research ideas by integrating knowledge from different fields. This system can improve the efficiency and success rate of medical research.

[0006] "Means of automatically acquiring information" refers to functions that collect necessary data from a vast database without human intervention.

[0007] "A means of analyzing information and generating new hypotheses" refers to the function of discovering new insights and research propositions by analyzing collected data.

[0008] "Interactive interface means" refers to communication methods that allow users to receive information and issue instructions while directly interacting with the system.

[0009] "Process management means for optimizing the research process" refers to functions that provide methods and tools to make research progress more efficient and effective.

[0010] "A means of integrating knowledge from different fields to create new research ideas" refers to the function of summarizing knowledge obtained from various specialized fields and proposing new research directions based on that knowledge. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4]This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention is an AI agent system for medical researchers and pharmaceutical companies to efficiently conduct new drug development and treatment research. The system of this invention has the following configuration.

[0033] Data collection and updating

[0034] First, the server collects information from multiple medical-related databases publicly available on the internet. This collection is automated and carried out according to a regular schedule. For example, it includes the latest medical papers, clinical trial data, and patent information. The collected data undergoes metadata extraction and indexing, and is stored in a database that allows for efficient searching.

[0035] Data analysis and hypothesis generation

[0036] The AI ​​agent deployed on the terminal retrieves necessary information from this database in real time and analyzes it using machine learning and natural language processing techniques. The purpose of the analysis is to discover important trends and correlations and generate new hypotheses and research themes.

[0037] Research support through interactive interfaces

[0038] Users can interact with an AI agent on their device to input questions or research topics and receive responses regarding hypotheses and related information. This interface is interactive, allowing users to ask additional questions and refine information to help clarify the direction of their research.

[0039] Optimization of the research process

[0040] Next, the server manages the project to optimize the user's research process based on suggestions and hypotheses from the AI ​​agent. Specifically, it optimizes experimental design and clinical trial schedules to support efficient progress. The plan is customized according to the user's requirements, ensuring efficient resource allocation.

[0041] Knowledge integration and idea generation

[0042] Finally, the device integrates knowledge from various specialized fields and generates new ideas. This allows users to take a multifaceted research approach that leverages knowledge from different disciplines.

[0043] For example, when researching "the potential of new biomarkers in immunotherapy," the AI ​​agent analyzes the latest relevant research data and presents promising biomarker candidates. Based on this information, the user can then plan and conduct further experiments and research.

[0044] Thus, the present invention provides a powerful tool for medical researchers to drive innovation rapidly and efficiently.

[0045] The following describes the processing flow.

[0046] Step 1:

[0047] The server automatically collects medical-related data from databases and APIs connected to the internet. This includes the latest research papers, clinical trial data, and patent information, and the data is collected on a regularly scheduled basis. The collected data is then indexed after undergoing processes such as deduplicating and formatting standardization.

[0048] Step 2:

[0049] The server stores the indexed data in a database, enabling efficient searching. During this process, metadata is extracted, and the data is categorized and tagged to improve search performance.

[0050] Step 3:

[0051] The device retrieves relevant data from the server based on the user's request. When the user requests a specific research topic, the AI ​​agent filters the target data and prepares to retrieve the most relevant information.

[0052] Step 4:

[0053] The device analyzes the acquired data using an AI model and discovers trends and correlations using natural language processing. This analysis generates new hypotheses and research topics.

[0054] Step 5:

[0055] Through an interactive interface, users receive analysis results and suggestions, and can ask additional questions or give instructions to the AI ​​agent as needed. The agent then refines the information based on the user's feedback.

[0056] Step 6:

[0057] The server leverages the generated hypotheses and proposals to build the user's experimental design and planning schedule through project management tools designed to optimize the research process. This includes resource allocation and scheduling adjustments.

[0058] Step 7:

[0059] The device integrates knowledge from different fields to generate new research ideas. The AI ​​agent combines information from multiple specialized areas to propose multifaceted research approaches to the user.

[0060] Step 8:

[0061] Users accept proposed ideas and plans, take concrete actions to advance their research, and effectively conduct their research with support from the system.

[0062] (Example 1)

[0063] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0064] Traditional research into pharmaceuticals and treatments lacks the means to efficiently collect and analyze large amounts of data, generate new hypotheses, and optimize the research process. Furthermore, multifaceted research utilizing knowledge from different fields has been difficult. Therefore, a new system is needed to enable researchers and pharmaceutical companies to conduct research quickly and efficiently, and to produce innovative results.

[0065] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0066] In this invention, the server includes means for accessing external information sources via a network to automatically acquire information, means for processing and indexing the acquired information to make it efficiently searchable, and means for analyzing the data and generating new hypotheses using machine learning and natural language processing. This enables researchers to generate hypotheses based on the latest information, optimizing the research process and promoting new research through a multifaceted approach.

[0067] "Means of accessing external information sources via a network" refers to a function that uses a network such as the internet to automatically connect to external databases or APIs and retrieve the necessary information.

[0068] "Methods for processing and indexing information to make it efficiently searchable" refers to the process of analyzing the characteristics and relationships of collected information, organizing the data structure to enable efficient searching, and then indexing it.

[0069] "Means of analyzing data and generating new hypotheses using machine learning and natural language processing" refers to the function of forming research hypotheses by applying machine learning algorithms and natural language processing techniques to collected data and discovering new insights and relationships.

[0070] An "interactive user interface" is an interface that allows users to directly interact with a system, and is a mechanism that enables the system to automatically present information and facilitate communication based on user input.

[0071] "Project management methods" are techniques for planning and efficiently advancing the research process, and include functions for allocating resources and adjusting schedules.

[0072] "Integrating multiple areas of expertise and creating new research approaches that span different fields" refers to the process of combining knowledge from different disciplines to develop original and multifaceted research methods.

[0073] This invention is an AI agent system designed to enable medical researchers and pharmaceutical companies to efficiently advance new drug development and treatment research. The system aims to optimize the research process by generating innovative hypotheses through large-scale data collection and analysis.

[0074] Data collection and updating

[0075] The server automatically retrieves information from multiple medical databases via the network. This ensures that the latest medical papers, clinical trial data, and patent information are regularly collected. The software used includes libraries and database management systems to facilitate API access.

[0076] Data analysis and hypothesis generation

[0077] The terminal retrieves indexed data from the server in real time and analyzes it using machine learning and natural language processing techniques. Specifically, by using frameworks such as TENSORFLOW® and PyTorch, it can discover trends and correlations within the data and generate new hypotheses.

[0078] Research support through interactive interfaces

[0079] Users can operate the AI ​​agent through the terminal's interface and input information about their research topic. This allows the AI ​​to share generated hypotheses and related information with the user, supporting the deepening of the research through continuous dialogue.

[0080] Optimization of the research process

[0081] The server manages the execution of plans based on hypotheses provided by AI agents. It optimizes experimental designs and clinical trial schedules, and ensures efficient resource allocation.

[0082] Knowledge integration and idea generation

[0083] The device integrates multiple areas of expertise, creating new research approaches that transcend different disciplines. This enables users to conduct research across a wide range of fields.

[0084] For example, if the research topic is "the potential of new biomarkers in immunotherapy," the AI ​​agent will analyze the latest relevant research data and present promising biomarker candidates.

[0085] Example of a prompt:

[0086] "To discover novel biomarkers, analyze recent immunotherapy data and identify relevant trends and correlations."

[0087] "Generate hypotheses based on the latest medical literature and data to explore the potential of new drugs for treating Alzheimer's disease."

[0088] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0089] Step 1:

[0090] The server accesses external medical-related database APIs via the network on a regularly scheduled basis. Input is requests from the APIs, and output is the received data in the form of the latest medical papers, clinical trial data, and patent information. By retrieving this data, the system maintains up-to-date information at all times.

[0091] Step 2:

[0092] The server processes and indexes the acquired data. In this step, it analyzes the raw data received as input and extracts metadata. The output is indexed data to improve search efficiency. This indexing allows for quick retrieval of necessary information.

[0093] Step 3:

[0094] The terminal receives specific research topics or questions from the user as input. In this process, relevant data is retrieved from the server in real time based on the input topic. The output is the retrieved relevant data, which is used in the next data analysis stage.

[0095] Step 4:

[0096] The device analyzes the acquired data using machine learning algorithms, such as TensorFlow or PyTorch. The input is real-time acquired data, and the output is analysis results that reveal important trends and new hypotheses. This allows users to gain unprecedented insights.

[0097] Step 5:

[0098] The terminal presents the user with newly generated proposals and hypotheses based on the analysis results. In this interactive interface, the analysis results are the input, and the output is proposals and hypotheses for the user. The user can use this to determine new directions for further research.

[0099] Step 6:

[0100] The server optimizes the research process based on suggestions from the AI ​​agent. The input is suggestions obtained from an interactive interface, and the output is an optimized experimental design and clinical trial schedule. This improves research efficiency and enables optimal resource allocation.

[0101] Step 7:

[0102] The device integrates knowledge from diverse fields of expertise and proposes new research approaches. In this step, the input is knowledge from various fields, and the output is new research ideas resulting from interdisciplinary collaboration. This allows users to advance their research from innovative and multifaceted perspectives.

[0103] (Application Example 1)

[0104] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0105] In modern manufacturing facilities, improving the efficiency of manufacturing processes and ensuring quality control are critical challenges. However, in many cases, it is difficult to perform real-time analysis and make appropriate adjustments. This is especially true in pharmaceutical factories, where the manufacturing process for pharmaceuticals is complex and multifaceted, making traditional management methods often inadequate. This problem can lead to increased manufacturing costs, production delays, and a decline in quality. Therefore, there is a need for technologies that can optimize manufacturing processes efficiently and quickly and guarantee quality.

[0106] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0107] In this invention, the server includes means for automatically retrieving information from a vast database, means for analyzing the retrieved information to generate new hypotheses, and means for analyzing data related to the manufacturing process to optimize process efficiency. This enables real-time analysis and immediate adjustment of the manufacturing process in the factory, thereby achieving improved manufacturing efficiency and enhanced quality control.

[0108] A "database" is an information system used to structure and store vast amounts of information, and to efficiently search for and retrieve it.

[0109] "Hypothesis generation" is the process of proposing new research directions and theories by analyzing collected data.

[0110] An "interactive interface" is an operating environment in which users can directly interact with the system and receive the necessary information.

[0111] "Process management" is a management method used to efficiently organize manufacturing and business processes and to adjust them so that they operate according to plan.

[0112] "Knowledge integration" is the process of combining diverse information obtained from different fields to generate new insights and innovations.

[0113] "Process optimization" refers to adjusting each stage of manufacturing or operations to ensure optimal progress, eliminating waste, and improving productivity.

[0114] "Real-time analysis" is a technology that processes information instantly and provides rapid feedback of the results.

[0115] "Production line adjustment" refers to the activity of reviewing the allocation of equipment and personnel according to the progress of the manufacturing process in order to maintain an optimal manufacturing environment.

[0116] The system that realizes this invention consists mainly of a server and terminals. The server automatically retrieves medical information from a vast database and also collects data related to the manufacturing process in real time. This data is indexed and stored in a database that allows for efficient searching. For analysis, machine learning libraries such as TensorFlow or PyTorch and natural language processing tools such as NLTK or spaCy are used. Based on the analyzed data, the server generates hypotheses and transmits new suggestions to the terminals.

[0117] The terminal is operated by the user via an interactive interface. Users input research topics of interest or on-site challenges, and receive optimal manufacturing process adjustments and hypotheses from an AI agent. Based on user guidance, the system monitors the manufacturing line in real time and provides suggestions for maintenance, enabling operational optimization. Furthermore, the terminal facilitates the integration of knowledge from different fields, supporting the generation of new research and manufacturing method ideas.

[0118] As a concrete example, in a tablet manufacturing line, an AI application monitors fluctuations in drug components in real time and immediately adjusts production line parameters as needed. This system makes it possible to improve production efficiency while suppressing the occurrence of defective products.

[0119] An example of a prompt for the generated AI model is, "Analyze manufacturing data in real time and propose an efficient production model." In this way, this system plays an important role in quality assurance and process efficiency in the manufacturing industry.

[0120] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0121] Step 1:

[0122] The server automatically retrieves publicly available medical information from a vast database. Input consists of medical articles and patent information found on the internet, and the program collects information according to a regular schedule. The collected information is then subjected to metadata extraction and indexing, and stored as an efficient, searchable database. The output is a searchable database.

[0123] Step 2:

[0124] The server collects sensor data from the manufacturing process in real time. The input consists of process-related data from sensors installed within the factory, which is continuously transmitted to the server. Based on this real-time data, an anomaly detection algorithm is run, and calculations are performed to immediately analyze the line status. The output provides insights for process efficiency.

[0125] Step 3:

[0126] The terminal analyzes important trends and correlations from data stored on the server and generates new hypotheses using a generative AI model. The input is the data to be analyzed, which is passed through the machine learning library TensorFlow or PyTorch to perform calculations to capture complex data patterns. The output is the proposed hypothesis and suggested improvements to the manufacturing process based on it.

[0127] Step 4:

[0128] The user inputs research topics of interest or work-related challenges through the terminal's interactive interface. This input consists of natural language prompts from the user. These prompts prompt a generative AI model performs reasoning, outputting appropriate hypotheses and manufacturing adjustment proposals on the terminal.

[0129] Step 5:

[0130] The terminal adjusts the manufacturing line based on user prompts and AI-generated hypotheses. Inputs are user requests and AI suggestions, while output is the adjusted manufacturing parameters. These adjustments are reflected in the manufacturing line's operation in real time and communicated via the server to enable more efficient production.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] This invention is an advanced AI agent system designed to significantly improve research processes for medical researchers and pharmaceutical companies. In addition to data collection, analysis, hypothesis generation, user interface, and process management functions, the system incorporates an emotion engine that recognizes user emotions and optimizes responses.

[0133] Data collection and analysis

[0134] First, the server continuously collects information from medical databases, obtaining the latest research and patent data. The collected information is indexed to enable efficient searching and analysis.

[0135] Hypothesis generation

[0136] The AI ​​agent on the device analyzes the collected data and generates new hypotheses using natural language processing and machine learning algorithms. This process leads to insights and suggestions aligned with the user's research topic.

[0137] Interactive interface

[0138] Users can interact directly with an AI agent through their device to receive feedback on their research topics and questions. This interface adapts to user requests and provides data analysis results in real time.

[0139] Emotional Engine

[0140] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time. This engine analyzes the user's text input, facial expressions, and voice tone to determine their emotional state. For example, if the user is feeling frustrated, the agent will provide a more friendly tone and additional support information.

[0141] Process management and knowledge integration

[0142] The server utilizes the output of AI agents to optimize the research process, including efficient experimental design and scheduling. It can also integrate information from different disciplines to generate new research ideas.

[0143] For example, if a user requests to know the latest trends in immunotherapy research, the AI ​​agent analyzes relevant data to identify trends and presents the results to the user. Simultaneously, the emotion engine analyzes the user's reactions and responds according to their level of understanding and interest.

[0144] This system allows medical researchers to not only obtain advanced information and analysis, but also to efficiently advance their research while receiving optimal support tailored to their individual needs and emotional responses. Thus, this invention will be an important tool for promoting innovation in new drug development and treatment research.

[0145] The following describes the processing flow.

[0146] Step 1:

[0147] The server accesses multiple medical databases to automatically collect the latest research papers, clinical trial data, and patent information. This process is scheduled regularly, and duplicate data is removed and formats are standardized to maintain data consistency.

[0148] Step 2:

[0149] The server converts the collected data into metadata and indexes it to enable efficient searching. This indexing allows for the rapid retrieval of data of interest from a vast amount of information.

[0150] Step 3:

[0151] The device's AI agent requests filtered data from the server based on the user's input of specific research topics or interests. Based on this request, only relevant information is provided to the device.

[0152] Step 4:

[0153] The device runs an AI agent and analyzes the acquired data. Here, natural language processing and machine learning algorithms are used to detect important trends and correlations, and new hypotheses and research proposals are generated based on these findings.

[0154] Step 5:

[0155] Users receive analysis results and suggestions through an interactive interface with an AI agent. Through the interface, users can ask questions and request additional information about the results.

[0156] Step 6:

[0157] The device's emotion engine analyzes the user's text input, facial expressions, and voice tone to recognize the user's emotional state. For example, if the user shows interest, the agent will provide more detailed information; conversely, if the user appears confused, it will offer a concise explanation.

[0158] Step 7:

[0159] The server optimizes the user's research process based on information and suggestions generated by the emotion engine and AI agents. This optimization includes adjusting the experiment schedule and efficiently allocating resources.

[0160] Step 8:

[0161] The device integrates knowledge from multiple different specialized fields and proposes new research ideas to the user. This allows the user to advance their research from a broader perspective.

[0162] Step 9:

[0163] Users plan and execute specific research activities using new hypotheses and research ideas suggested by the system. They progress through their research with support and gain further insights from the AI ​​agent based on the results.

[0164] (Example 2)

[0165] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0166] In modern scientific research, particularly in the medical field, efficiently collecting and analyzing vast amounts of information is becoming increasingly important. However, this process is time-consuming and labor-intensive, and many challenges remain in integrating knowledge across different research disciplines and generating hypotheses. Furthermore, support for effectively conducting research while considering user emotions is often insufficient. A comprehensive support system is needed to address these challenges.

[0167] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0168] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for analyzing the collected data and generating new hypotheses, and means for an engine that analyzes the user's emotional state and optimizes the response accordingly. This allows researchers to save a great deal of time and effort while integrating knowledge from different fields to aid in hypothesis generation and obtaining effective support that takes the user's emotions into consideration.

[0169] "Information source" refers to the foundation used to obtain data, and is a concept that includes various databases and online repositories.

[0170] An "automatic data collection device" is a system component that has the function of efficiently acquiring relevant information from a vast amount of information sources.

[0171] A "data analysis device" is a component designed to process acquired data and find patterns and insights, often utilizing artificial intelligence technology.

[0172] "Hypothesis generation" is the process of constructing new research hypotheses based on the results of data analysis.

[0173] An "interactive user interface device" is a component that provides an intuitive means of communication for users to interact with a system in real time and exchange information.

[0174] A "process management device" is a system element that provides functions for optimizing schedule management and other business processes in order to streamline the research process.

[0175] A "knowledge integration device" is a device that unifies information obtained from different fields and has the function of creating new research perspectives and ideas.

[0176] An "emotional state analysis engine" is an analytical tool that evaluates a user's emotions in real time and adjusts the system response accordingly.

[0177] The system in this invention provides a means for streamlining information aggregation and analysis processes in the fields of medicine and scientific research. First, the system automatically collects data from a vast number of information sources via a server. This collection includes access to digital repositories and online databases. Specifically, the server can retrieve relevant papers and patent data using an API interface.

[0178] This data is indexed on the server and prepared for efficient searching and analysis. A search engine such as Elasticsearch® is used for data indexing. During this process, the data's metadata is organized, optimizing the subsequent analysis process.

[0179] Subsequently, an AI agent on the device analyzes this indexed data. The AI ​​agent utilizes natural language processing techniques and generative AI models to generate new hypotheses from the collected data. This model may employ, for example, the Transformer architecture. Specifically, the device identifies trends in medical research and presents new approaches useful for scientific research projects.

[0180] Through interaction with this AI agent, users receive data via an interactive interface. The user interface presents hypotheses and analysis results in real time and responds to user questions. The interface is built using HTML and JavaScript (registered trademark), allowing for intuitive operation.

[0181] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time and analyzes their emotional state. This engine analyzes the user's input text, voice, and facial expressions to generate appropriate responses based on the user's emotions. This feature allows users to acquire information smoothly without feeling stressed.

[0182] For example, if a user requests to learn about the latest research trends in immunotherapy, the AI ​​agent quickly analyzes relevant data and provides the user with trend information. Simultaneously, the emotion engine analyzes the user's response and adjusts the response according to the user's level of understanding and interest.

[0183] An example of a prompt message could be input to a generative AI model in the form of, "Please explain the key points for understanding the latest research in immunotherapy. Also, please point out any particularly noteworthy trends."

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The server accesses medical databases and information sources and collects data based on specified keywords. In this example, the keyword "immunotherapy" is used as input, and relevant article information is retrieved from databases such as PubMed. The data is output in original text format.

[0187] Step 2:

[0188] The server indexes the collected data using a search engine such as Elasticsearch. It uses the text data from Step 1 as input and organizes it by metadata (author, title, abstract, etc.). The output is structured index data that can be quickly searched.

[0189] Step 3:

[0190] The AI ​​agent on the terminal analyzes indexed data. The input is structured indexed data, and natural language processing is performed using a generative AI model. Through this process, patterns are extracted from the data and output as new hypotheses (e.g., "Novel approaches in immunotherapy").

[0191] Step 4:

[0192] Users ask specific questions to the AI ​​agent via their device. By entering prompts such as "I want to know the latest trends in immunotherapy" into the user interface, the AI ​​agent refers to index data and outputs analysis results in real time. This output includes answers and insights tailored to the user's requests.

[0193] Step 5:

[0194] The device's emotion engine analyzes the user's emotional state. Inputs include user text, voice, and facial expression data, which are used for emotion analysis. The output is an AI agent response in a format that is easy for the user to understand—for example, gentle supplementary explanations.

[0195] Step 6:

[0196] The server manages the entire process and provides process management functions to optimize research activities based on the data obtained and the hypotheses generated. The input is the output of all the previous steps, and the server uses this to suggest efficient experimental designs and schedules, generating valuable outputs for researchers.

[0197] (Application Example 2)

[0198] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0199] This invention aims to solve the problem of improving the quality of services provided to users while reducing the burden on care staff by promoting the understanding and appropriate response to the emotional state of users in the care process. Furthermore, it aims to improve the efficiency and optimization of care support by integrating and utilizing data from different information sources.

[0200] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0201] In this invention, the server includes means for automatically acquiring data from a vast number of information sources, means for analyzing the acquired data to generate new hypotheses, interactive interface means for presenting the generated hypotheses and proposals to the user, emotion analysis means for recognizing the user's emotions and optimizing responses, process management means for optimizing the research and support process, and means for integrating knowledge from different domains to create new research or support ideas. This enables care staff to grasp the user's emotions in real time and support optimal care responses.

[0202] An "information source" is a collection of resources from which data is obtained from various fields.

[0203] "Data" refers to units of facts and knowledge obtained from information sources, which are transformed into useful information through analysis.

[0204] "Analysis" is the process of using acquired data to find meaningful patterns and relationships.

[0205] A "hypothesis" is a new proposal or attempt at explanation derived from the results of an analysis.

[0206] An "interactive interface" is a direct means of communication that allows users to exchange information with a system.

[0207] "Emotional analysis" is a process for understanding the emotional state of users and optimizing the system's response.

[0208] "Process management" is a management method for planning, executing, evaluating, and streamlining the flow of research and support activities.

[0209] "Knowledge integration" is the process of combining information obtained from different fields to create new value.

[0210] A "support idea" is a proposal for a new method or technique created in the provision of care and services.

[0211] The system that realizes this application runs on a server and includes an advanced AI agent specifically designed to support the caregiving process. The server acquires and analyzes data from diverse sources. For analysis, it uses a program built in Python, performs facial recognition from image data using OpenCV, and estimates emotions using a TensorFlow model. In addition, it analyzes emotions from voice input using nltk. As a result, care staff, as users, can understand the user's condition in real time through devices such as smart glasses.

[0212] Information obtained through emotion analysis is sent to the caregiver's terminal, where an AI agent presents recommended care responses. The terminal has an interactive interface that provides direct interaction methods and options for the user.

[0213] As a concrete example, if a user experiences stress in their daily life, the system detects changes in their facial expressions and voice. The server analyzes this data and notifies the care staff's terminal with a message such as, "The user is feeling anxious. It would be best to speak to them gently." In this way, the system analyzes emotional data in real time to support caregiving tasks.

[0214] By utilizing generative AI models, it becomes possible to flexibly provide solutions for a variety of situations.

[0215] An example of a prompt message is: "Design a friendly AI assistant that analyzes the user's emotional state from facial expression data and voice input, and provides appropriate care in real time."

[0216] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0217] Step 1:

[0218] The server collects user data from care facilities and affiliated information sources. This data includes image data, audio data, and health status records. The collected data is standardized to support various formats. The input is raw data, and the output is standardized data.

[0219] Step 2:

[0220] The server analyzes image data collected using OpenCV and estimates emotions from the user's facial expressions. It extracts facial landmarks from the image data (input) and classifies emotions using a TensorFlow model. The output is the emotion label estimated based on the user's facial expressions.

[0221] Step 3:

[0222] The device uses NLTK to analyze speech data and recognize emotions from the content and tone of speech. The speech data (input) is converted to text and subjected to natural language processing. This results in an output that indicates emotions.

[0223] Step 4:

[0224] The server uses a generative AI model to comprehensively assess the user's condition based on collected emotional data and health records. In this process, the AI ​​generates care support suggestions appropriate to the user's current emotional state. The input is estimated emotional labels and health data, and the output is specific countermeasures and advice.

[0225] Step 5:

[0226] The device notifies care staff of recommended actions and provides specific instructions through an interactive interface. The notification is the input, and the output is the instruction to the care staff. This allows staff to provide optimal care to users at the appropriate time.

[0227] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0228] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0229] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0230] [Second Embodiment]

[0231] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0232] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0233] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0234] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0235] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0236] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0237] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0238] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0239] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0240] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0241] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0242] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0243] This invention is an AI agent system for medical researchers and pharmaceutical companies to efficiently conduct new drug development and treatment research. The system of this invention has the following configuration.

[0244] Data collection and updating

[0245] First, the server collects information from multiple medical-related databases publicly available on the internet. This collection is automated and carried out according to a regular schedule. For example, it includes the latest medical papers, clinical trial data, and patent information. The collected data undergoes metadata extraction and indexing, and is stored in a database that allows for efficient searching.

[0246] Data analysis and hypothesis generation

[0247] The AI ​​agent deployed on the terminal retrieves necessary information from this database in real time and analyzes it using machine learning and natural language processing techniques. The purpose of the analysis is to discover important trends and correlations and generate new hypotheses and research themes.

[0248] Research support through interactive interfaces

[0249] Users can interact with an AI agent on their device to input questions or research topics and receive responses regarding hypotheses and related information. This interface is interactive, allowing users to ask additional questions and refine information to help clarify the direction of their research.

[0250] Optimization of the research process

[0251] Next, the server manages the project to optimize the user's research process based on suggestions and hypotheses from the AI ​​agent. Specifically, it optimizes experimental design and clinical trial schedules to support efficient progress. The plan is customized according to the user's requirements, ensuring efficient resource allocation.

[0252] Knowledge integration and idea generation

[0253] Finally, the device integrates knowledge from various specialized fields and generates new ideas. This allows users to take a multifaceted research approach that leverages knowledge from different disciplines.

[0254] For example, when researching "the potential of new biomarkers in immunotherapy," the AI ​​agent analyzes the latest relevant research data and presents promising biomarker candidates. Based on this information, the user can then plan and conduct further experiments and research.

[0255] Thus, the present invention provides a powerful tool for medical researchers to drive innovation rapidly and efficiently.

[0256] The following describes the processing flow.

[0257] Step 1:

[0258] The server automatically collects medical-related data from databases and APIs connected to the internet. This includes the latest research papers, clinical trial data, and patent information, and the data is collected on a regularly scheduled basis. The collected data is then indexed after undergoing processes such as deduplicating and formatting standardization.

[0259] Step 2:

[0260] The server stores the indexed data in a database, enabling efficient searching. During this process, metadata is extracted, and the data is categorized and tagged to improve search performance.

[0261] Step 3:

[0262] The device retrieves relevant data from the server based on the user's request. When the user requests a specific research topic, the AI ​​agent filters the target data and prepares to retrieve the most relevant information.

[0263] Step 4:

[0264] The device analyzes the acquired data using an AI model and discovers trends and correlations using natural language processing. This analysis generates new hypotheses and research topics.

[0265] Step 5:

[0266] Through an interactive interface, users receive analysis results and suggestions, and can ask additional questions or give instructions to the AI ​​agent as needed. The agent then refines the information based on the user's feedback.

[0267] Step 6:

[0268] The server leverages the generated hypotheses and proposals to build the user's experimental design and planning schedule through project management tools designed to optimize the research process. This includes resource allocation and scheduling adjustments.

[0269] Step 7:

[0270] The device integrates knowledge from different fields to generate new research ideas. The AI ​​agent combines information from multiple specialized areas to propose multifaceted research approaches to the user.

[0271] Step 8:

[0272] Users accept proposed ideas and plans, take concrete actions to advance their research, and effectively conduct their research with support from the system.

[0273] (Example 1)

[0274] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0275] Traditional research into pharmaceuticals and treatments lacks the means to efficiently collect and analyze large amounts of data, generate new hypotheses, and optimize the research process. Furthermore, multifaceted research utilizing knowledge from different fields has been difficult. Therefore, a new system is needed to enable researchers and pharmaceutical companies to conduct research quickly and efficiently, and to produce innovative results.

[0276] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0277] In this invention, the server includes means for accessing external information sources via a network to automatically acquire information, means for processing and indexing the acquired information to make it efficiently searchable, and means for analyzing the data and generating new hypotheses using machine learning and natural language processing. This enables researchers to generate hypotheses based on the latest information, optimizing the research process and promoting new research through a multifaceted approach.

[0278] "Means of accessing external information sources via a network" refers to a function that uses a network such as the internet to automatically connect to external databases or APIs and retrieve the necessary information.

[0279] "Methods for processing and indexing information to make it efficiently searchable" refers to the process of analyzing the characteristics and relationships of collected information, organizing the data structure to enable efficient searching, and then indexing it.

[0280] "Means of analyzing data and generating new hypotheses using machine learning and natural language processing" refers to the function of forming research hypotheses by applying machine learning algorithms and natural language processing techniques to collected data and discovering new insights and relationships.

[0281] "Interactive user interface means" refers to an interface through which a user can directly interact with a system, and is a mechanism that enables the system to automatically present information and conduct exchanges based on inputs from the user.

[0282] "Project management means" refers to a method for planning and efficiently advancing the research process, and is a function for allocating resources and adjusting schedules.

[0283] "Means for integrating multiple expertises and creating a new research approach across different fields" refers to a process for combining knowledge from different fields and developing innovative and comprehensive research methods.

[0284] This invention is an AI agent system for medical researchers and pharmaceutical companies to efficiently advance new drug development and treatment research. The system aims to generate innovative hypotheses and optimize the research process through large-scale data collection and analysis.

[0285] Data collection and update

[0286] The server automatically obtains information from multiple medical-related databases via a network. As a result, the latest medical papers, clinical trial data, and patent information are regularly collected. The software used includes libraries for facilitating API access and database management systems.

[0287] Data analysis and hypothesis generation

[0288] The terminal obtains the data indexed by the server in real time and analyzes it using machine learning and natural language processing technologies. Specifically, by using frameworks such as TensorFlow and PyTorch, trends and correlations within the data can be discovered, and new hypotheses can be generated.

[0289] Research support through an interactive interface

[0290] Users can operate the AI ​​agent through the terminal's interface and input information about their research topic. This allows the AI ​​to share generated hypotheses and related information with the user, supporting the deepening of the research through continuous dialogue.

[0291] Optimization of the research process

[0292] The server manages the execution of plans based on hypotheses provided by AI agents. It optimizes experimental designs and clinical trial schedules, and ensures efficient resource allocation.

[0293] Knowledge integration and idea generation

[0294] The device integrates multiple areas of expertise, creating new research approaches that transcend different disciplines. This enables users to conduct research across a wide range of fields.

[0295] For example, if the research topic is "the potential of new biomarkers in immunotherapy," the AI ​​agent will analyze the latest relevant research data and present promising biomarker candidates.

[0296] Example of a prompt:

[0297] "To discover novel biomarkers, analyze recent immunotherapy data and identify relevant trends and correlations."

[0298] "Generate hypotheses based on the latest medical literature and data to explore the potential of new drugs for treating Alzheimer's disease."

[0299] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0300] Step 1:

[0301] The server accesses an external medical-related database API based on a schedule set periodically via the network. The input is a request from the API, and the output is the data received in the form of the latest medical papers, clinical trial data, and patent information. By obtaining this data, the system always maintains the latest information.

[0302] Step 2:

[0303] The server processes and indexes the acquired data. In this step, the raw data received as input is analyzed, and metadata is extracted. The output is the data indexed to improve search efficiency. This indexing enables quick retrieval of the necessary information.

[0304] Step 3:

[0305] The terminal receives a specific research theme or question from the user as input. In this process, based on the input theme, relevant data is retrieved from the server in real-time. The output is the retrieved relevant data, which is utilized in the next data analysis stage.

[0306] Step 4:

[0307] The terminal analyzes the acquired data using machine learning algorithms, such as TensorFlow or PyTorch. The input is the data retrieved in real-time, and the output is the analysis result indicating important trends and new hypotheses. This enables the user to obtain unprecedented insights.

[0308] Step 5:

[0309] The terminal presents the newly generated proposals and hypotheses to the user based on the analysis result. In this interactive interface, the analysis result is the input, and the output is the proposals and hypotheses for the user. The user can use this to determine new directions for further research.

[0310] Step 6:

[0311] The server optimizes the research process based on suggestions from the AI ​​agent. The input is suggestions obtained from an interactive interface, and the output is an optimized experimental design and clinical trial schedule. This improves research efficiency and enables optimal resource allocation.

[0312] Step 7:

[0313] The device integrates knowledge from diverse fields of expertise and proposes new research approaches. In this step, the input is knowledge from various fields, and the output is new research ideas resulting from interdisciplinary collaboration. This allows users to advance their research from innovative and multifaceted perspectives.

[0314] (Application Example 1)

[0315] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0316] In modern manufacturing facilities, improving the efficiency of manufacturing processes and ensuring quality control are critical challenges. However, in many cases, it is difficult to perform real-time analysis and make appropriate adjustments. This is especially true in pharmaceutical factories, where the manufacturing process for pharmaceuticals is complex and multifaceted, making traditional management methods often inadequate. This problem can lead to increased manufacturing costs, production delays, and a decline in quality. Therefore, there is a need for technologies that can optimize manufacturing processes efficiently and quickly and guarantee quality.

[0317] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0318] In this invention, the server includes means for automatically retrieving information from a vast database, means for analyzing the retrieved information to generate new hypotheses, and means for analyzing data related to the manufacturing process to optimize process efficiency. This enables real-time analysis and immediate adjustment of the manufacturing process in the factory, thereby achieving improved manufacturing efficiency and enhanced quality control.

[0319] A "database" is an information system used to structure and store vast amounts of information, and to efficiently search for and retrieve it.

[0320] "Hypothesis generation" is the process of proposing new research directions and theories by analyzing collected data.

[0321] An "interactive interface" is an operating environment in which users can directly interact with the system and receive the necessary information.

[0322] "Process management" is a management method used to efficiently organize manufacturing and business processes and to adjust them so that they operate according to plan.

[0323] "Knowledge integration" is the process of combining diverse information obtained from different fields to generate new insights and innovations.

[0324] "Process optimization" refers to adjusting each stage of manufacturing or operations to ensure optimal progress, eliminating waste, and improving productivity.

[0325] "Real-time analysis" is a technology that processes information instantly and provides rapid feedback of the results.

[0326] "Production line adjustment" refers to the activity of reviewing the allocation of equipment and personnel according to the progress of the manufacturing process in order to maintain an optimal manufacturing environment.

[0327] The system that realizes this invention consists mainly of a server and terminals. The server automatically retrieves medical information from a vast database and also collects data related to the manufacturing process in real time. This data is indexed and stored in a database that allows for efficient searching. For analysis, machine learning libraries such as TensorFlow or PyTorch and natural language processing tools such as NLTK or spaCy are used. Based on the analyzed data, the server generates hypotheses and transmits new suggestions to the terminals.

[0328] The terminal is operated by the user via an interactive interface. Users input research topics of interest or on-site challenges, and receive optimal manufacturing process adjustments and hypotheses from an AI agent. Based on user guidance, the system monitors the manufacturing line in real time and provides suggestions for maintenance, enabling operational optimization. Furthermore, the terminal facilitates the integration of knowledge from different fields, supporting the generation of new research and manufacturing method ideas.

[0329] As a concrete example, in a tablet manufacturing line, an AI application monitors fluctuations in drug components in real time and immediately adjusts production line parameters as needed. This system makes it possible to improve production efficiency while suppressing the occurrence of defective products.

[0330] An example of a prompt for the generated AI model is, "Analyze manufacturing data in real time and propose an efficient production model." In this way, this system plays an important role in quality assurance and process efficiency in the manufacturing industry.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] The server automatically retrieves publicly available medical information from a vast database. Input consists of medical articles and patent information found on the internet, and the program collects information according to a regular schedule. The collected information is then subjected to metadata extraction and indexing, and stored as an efficient, searchable database. The output is a searchable database.

[0334] Step 2:

[0335] The server collects sensor data from the manufacturing process in real time. The input consists of process-related data from sensors installed within the factory, which is continuously transmitted to the server. Based on this real-time data, an anomaly detection algorithm is run, and calculations are performed to immediately analyze the line status. The output provides insights for process efficiency.

[0336] Step 3:

[0337] The terminal analyzes important trends and correlations from data stored on the server and generates new hypotheses using a generative AI model. The input is the data to be analyzed, which is passed through the machine learning library TensorFlow or PyTorch to perform calculations to capture complex data patterns. The output is the proposed hypothesis and suggested improvements to the manufacturing process based on it.

[0338] Step 4:

[0339] The user inputs research topics of interest or work-related challenges through the terminal's interactive interface. This input consists of natural language prompts from the user. These prompts prompt a generative AI model performs reasoning, outputting appropriate hypotheses and manufacturing adjustment proposals on the terminal.

[0340] Step 5:

[0341] The terminal adjusts the manufacturing line based on user prompts and AI-generated hypotheses. Inputs are user requests and AI suggestions, while output is the adjusted manufacturing parameters. These adjustments are reflected in the manufacturing line's operation in real time and communicated via the server to enable more efficient production.

[0342] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0343] This invention is an advanced AI agent system designed to significantly improve research processes for medical researchers and pharmaceutical companies. In addition to data collection, analysis, hypothesis generation, user interface, and process management functions, the system incorporates an emotion engine that recognizes user emotions and optimizes responses.

[0344] Data collection and analysis

[0345] First, the server continuously collects information from medical databases, obtaining the latest research and patent data. The collected information is indexed to enable efficient searching and analysis.

[0346] Hypothesis generation

[0347] The AI ​​agent on the device analyzes the collected data and generates new hypotheses using natural language processing and machine learning algorithms. This process leads to insights and suggestions aligned with the user's research topic.

[0348] Interactive interface

[0349] Users can interact directly with an AI agent through their device to receive feedback on their research topics and questions. This interface adapts to user requests and provides data analysis results in real time.

[0350] Emotional Engine

[0351] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time. This engine analyzes the user's text input, facial expressions, and voice tone to determine their emotional state. For example, if the user is feeling frustrated, the agent will provide a more friendly tone and additional support information.

[0352] Process management and knowledge integration

[0353] The server utilizes the output of AI agents to optimize the research process, including efficient experimental design and scheduling. It can also integrate information from different disciplines to generate new research ideas.

[0354] For example, if a user requests to know the latest trends in immunotherapy research, the AI ​​agent analyzes relevant data to identify trends and presents the results to the user. Simultaneously, the emotion engine analyzes the user's reactions and responds according to their level of understanding and interest.

[0355] This system allows medical researchers to not only obtain advanced information and analysis, but also to efficiently advance their research while receiving optimal support tailored to their individual needs and emotional responses. Thus, this invention will be an important tool for promoting innovation in new drug development and treatment research.

[0356] The following describes the processing flow.

[0357] Step 1:

[0358] The server accesses multiple medical databases to automatically collect the latest research papers, clinical trial data, and patent information. This process is scheduled regularly, and duplicate data is removed and formats are standardized to maintain data consistency.

[0359] Step 2:

[0360] The server converts the collected data into metadata and indexes it to enable efficient searching. This indexing allows for the rapid retrieval of data of interest from a vast amount of information.

[0361] Step 3:

[0362] The device's AI agent requests filtered data from the server based on the user's input of specific research topics or interests. Based on this request, only relevant information is provided to the device.

[0363] Step 4:

[0364] The device runs an AI agent and analyzes the acquired data. Here, natural language processing and machine learning algorithms are used to detect important trends and correlations, and new hypotheses and research proposals are generated based on these findings.

[0365] Step 5:

[0366] Users receive analysis results and suggestions through an interactive interface with an AI agent. Through the interface, users can ask questions and request additional information about the results.

[0367] Step 6:

[0368] The device's emotion engine analyzes the user's text input, facial expressions, and voice tone to recognize the user's emotional state. For example, if the user shows interest, the agent will provide more detailed information; conversely, if the user appears confused, it will offer a concise explanation.

[0369] Step 7:

[0370] The server optimizes the user's research process based on information and suggestions generated by the emotion engine and AI agents. This optimization includes adjusting the experiment schedule and efficiently allocating resources.

[0371] Step 8:

[0372] The device integrates knowledge from multiple different specialized fields and proposes new research ideas to the user. This allows the user to advance their research from a broader perspective.

[0373] Step 9:

[0374] Users plan and execute specific research activities using new hypotheses and research ideas suggested by the system. They progress through their research with support and gain further insights from the AI ​​agent based on the results.

[0375] (Example 2)

[0376] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0377] In modern scientific research, particularly in the medical field, efficiently collecting and analyzing vast amounts of information is becoming increasingly important. However, this process is time-consuming and labor-intensive, and many challenges remain in integrating knowledge across different research disciplines and generating hypotheses. Furthermore, support for effectively conducting research while considering user emotions is often insufficient. A comprehensive support system is needed to address these challenges.

[0378] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0379] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for analyzing the collected data and generating new hypotheses, and means for an engine that analyzes the user's emotional state and optimizes the response accordingly. This allows researchers to save a great deal of time and effort while integrating knowledge from different fields to aid in hypothesis generation and obtaining effective support that takes the user's emotions into consideration.

[0380] "Information source" refers to the foundation used to obtain data, and is a concept that includes various databases and online repositories.

[0381] An "automatic data collection device" is a system component that has the function of efficiently acquiring relevant information from a vast amount of information sources.

[0382] A "data analysis device" is a component designed to process acquired data and find patterns and insights, often utilizing artificial intelligence technology.

[0383] "Hypothesis generation" is the process of constructing new research hypotheses based on the results of data analysis.

[0384] An "interactive user interface device" is a component that provides an intuitive means of communication for users to interact with a system in real time and exchange information.

[0385] A "process management device" is a system element that provides functions for optimizing schedule management and other business processes in order to streamline the research process.

[0386] A "knowledge integration device" is a device that unifies information obtained from different fields and has the function of creating new research perspectives and ideas.

[0387] An "emotional state analysis engine" is an analytical tool that evaluates a user's emotions in real time and adjusts the system response accordingly.

[0388] The system in this invention provides a means for streamlining information aggregation and analysis processes in the fields of medicine and scientific research. First, the system automatically collects data from a vast number of information sources via a server. This collection includes access to digital repositories and online databases. Specifically, the server can retrieve relevant papers and patent data using an API interface.

[0389] This data is indexed on the server and prepared for efficient searching and analysis. A search engine such as Elasticsearch is used for data indexing. In this process, the data's metadata is organized, optimizing the subsequent analysis process.

[0390] Subsequently, an AI agent on the device analyzes this indexed data. The AI ​​agent utilizes natural language processing techniques and generative AI models to generate new hypotheses from the collected data. This model may employ, for example, the Transformer architecture. Specifically, the device identifies trends in medical research and presents new approaches useful for scientific research projects.

[0391] Through interaction with this AI agent, users receive data via an interactive interface. The user interface presents hypotheses and analysis results in real time and responds to user questions. The interface is built using HTML and JavaScript, allowing for intuitive operation.

[0392] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time and analyzes their emotional state. This engine analyzes the user's input text, voice, and facial expressions to generate appropriate responses based on the user's emotions. This feature allows users to acquire information smoothly without feeling stressed.

[0393] For example, if a user requests to learn about the latest research trends in immunotherapy, the AI ​​agent quickly analyzes relevant data and provides the user with trend information. Simultaneously, the emotion engine analyzes the user's response and adjusts the response according to the user's level of understanding and interest.

[0394] An example of a prompt message could be input to a generative AI model in the form of, "Please explain the key points for understanding the latest research in immunotherapy. Also, please point out any particularly noteworthy trends."

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] The server accesses medical databases and information sources and collects data based on specified keywords. In this example, the keyword "immunotherapy" is used as input, and relevant article information is retrieved from databases such as PubMed. The data is output in original text format.

[0398] Step 2:

[0399] The server indexes the collected data using a search engine such as Elasticsearch. It uses the text data from Step 1 as input and organizes it by metadata (author, title, abstract, etc.). The output is structured index data that can be quickly searched.

[0400] Step 3:

[0401] The AI ​​agent on the terminal analyzes indexed data. The input is structured indexed data, and natural language processing is performed using a generative AI model. Through this process, patterns are extracted from the data and output as new hypotheses (e.g., "Novel approaches in immunotherapy").

[0402] Step 4:

[0403] Users ask specific questions to the AI ​​agent via their device. By entering prompts such as "I want to know the latest trends in immunotherapy" into the user interface, the AI ​​agent refers to index data and outputs analysis results in real time. This output includes answers and insights tailored to the user's requests.

[0404] Step 5:

[0405] The device's emotion engine analyzes the user's emotional state. Inputs include user text, voice, and facial expression data, which are used for emotion analysis. The output is an AI agent response in a format that is easy for the user to understand—for example, gentle supplementary explanations.

[0406] Step 6:

[0407] The server manages the entire process and provides process management functions to optimize research activities based on the data obtained and the hypotheses generated. The input is the output of all the previous steps, and the server uses this to suggest efficient experimental designs and schedules, generating valuable outputs for researchers.

[0408] (Application Example 2)

[0409] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0410] This invention aims to solve the problem of improving the quality of services provided to users while reducing the burden on care staff by promoting the understanding and appropriate response to the emotional state of users in the care process. Furthermore, it aims to improve the efficiency and optimization of care support by integrating and utilizing data from different information sources.

[0411] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0412] In this invention, the server includes means for automatically acquiring data from a vast number of information sources, means for analyzing the acquired data to generate new hypotheses, interactive interface means for presenting the generated hypotheses and proposals to the user, emotion analysis means for recognizing the user's emotions and optimizing responses, process management means for optimizing the research and support process, and means for integrating knowledge from different domains to create new research or support ideas. This enables care staff to grasp the user's emotions in real time and support optimal care responses.

[0413] An "information source" is a collection of resources from which data is obtained from various fields.

[0414] "Data" refers to units of facts and knowledge obtained from information sources, which are transformed into useful information through analysis.

[0415] "Analysis" is the process of using acquired data to find meaningful patterns and relationships.

[0416] A "hypothesis" is a new proposal or attempt at explanation derived from the results of an analysis.

[0417] An "interactive interface" is a direct means of communication that allows users to exchange information with a system.

[0418] "Emotional analysis" is a process for understanding the emotional state of users and optimizing the system's response.

[0419] "Process management" is a management method for planning, executing, evaluating, and streamlining the flow of research and support activities.

[0420] "Knowledge integration" is the process of combining information obtained from different fields to create new value.

[0421] A "support idea" is a proposal for a new method or technique created in the provision of care and services.

[0422] The system that realizes this application runs on a server and includes an advanced AI agent specifically designed to support the caregiving process. The server acquires and analyzes data from diverse sources. For analysis, it uses a program built in Python, performs facial recognition from image data using OpenCV, and estimates emotions using a TensorFlow model. In addition, it analyzes emotions from voice input using nltk. As a result, care staff, as users, can understand the user's condition in real time through devices such as smart glasses.

[0423] Information obtained through emotion analysis is sent to the caregiver's terminal, where an AI agent presents recommended care responses. The terminal has an interactive interface that provides direct interaction methods and options for the user.

[0424] As a concrete example, if a user experiences stress in their daily life, the system detects changes in their facial expressions and voice. The server analyzes this data and notifies the care staff's terminal with a message such as, "The user is feeling anxious. It would be best to speak to them gently." In this way, the system analyzes emotional data in real time to support caregiving tasks.

[0425] By utilizing generative AI models, it becomes possible to flexibly provide solutions for a variety of situations.

[0426] An example of a prompt message is: "Design a friendly AI assistant that analyzes the user's emotional state from facial expression data and voice input, and provides appropriate care in real time."

[0427] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0428] Step 1:

[0429] The server collects user data from care facilities and affiliated information sources. This data includes image data, audio data, and health status records. The collected data is standardized to support various formats. The input is raw data, and the output is standardized data.

[0430] Step 2:

[0431] The server analyzes image data collected using OpenCV and estimates emotions from the user's facial expressions. It extracts facial landmarks from the image data (input) and classifies emotions using a TensorFlow model. The output is the emotion label estimated based on the user's facial expressions.

[0432] Step 3:

[0433] The device uses NLTK to analyze speech data and recognize emotions from the content and tone of speech. The speech data (input) is converted to text and subjected to natural language processing. This results in an output that indicates emotions.

[0434] Step 4:

[0435] The server uses a generative AI model to comprehensively assess the user's condition based on collected emotional data and health records. In this process, the AI ​​generates care support suggestions appropriate to the user's current emotional state. The input is estimated emotional labels and health data, and the output is specific countermeasures and advice.

[0436] Step 5:

[0437] The device notifies care staff of recommended actions and provides specific instructions through an interactive interface. The notification is the input, and the output is the instruction to the care staff. This allows staff to provide optimal care to users at the appropriate time.

[0438] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0439] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0440] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0441] [Third Embodiment]

[0442] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0443] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0444] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0445] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0446] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0447] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0448] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0449] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0450] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0451] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0452] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0453] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0454] This invention is an AI agent system for medical researchers and pharmaceutical companies to efficiently conduct new drug development and treatment research. The system of this invention has the following configuration.

[0455] Data collection and updating

[0456] First, the server collects information from multiple medical-related databases publicly available on the internet. This collection is automated and carried out according to a regular schedule. For example, it includes the latest medical papers, clinical trial data, and patent information. The collected data undergoes metadata extraction and indexing, and is stored in a database that allows for efficient searching.

[0457] Data analysis and hypothesis generation

[0458] The AI ​​agent deployed on the terminal retrieves necessary information from this database in real time and analyzes it using machine learning and natural language processing techniques. The purpose of the analysis is to discover important trends and correlations and generate new hypotheses and research themes.

[0459] Research support through interactive interfaces

[0460] Users can interact with an AI agent on their device to input questions or research topics and receive responses regarding hypotheses and related information. This interface is interactive, allowing users to ask additional questions and refine information to help clarify the direction of their research.

[0461] Optimization of the research process

[0462] Next, the server manages the project to optimize the user's research process based on suggestions and hypotheses from the AI ​​agent. Specifically, it optimizes experimental design and clinical trial schedules to support efficient progress. The plan is customized according to the user's requirements, ensuring efficient resource allocation.

[0463] Knowledge integration and idea generation

[0464] Finally, the device integrates knowledge from various specialized fields and generates new ideas. This allows users to take a multifaceted research approach that leverages knowledge from different disciplines.

[0465] For example, when researching "the potential of new biomarkers in immunotherapy," the AI ​​agent analyzes the latest relevant research data and presents promising biomarker candidates. Based on this information, the user can then plan and conduct further experiments and research.

[0466] Thus, the present invention provides a powerful tool for medical researchers to drive innovation rapidly and efficiently.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The server automatically collects medical-related data from databases and APIs connected to the internet. This includes the latest research papers, clinical trial data, and patent information, and the data is collected on a regularly scheduled basis. The collected data is then indexed after undergoing processes such as deduplicating and formatting standardization.

[0470] Step 2:

[0471] The server stores the indexed data in a database, enabling efficient searching. During this process, metadata is extracted, and the data is categorized and tagged to improve search performance.

[0472] Step 3:

[0473] The device retrieves relevant data from the server based on the user's request. When the user requests a specific research topic, the AI ​​agent filters the target data and prepares to retrieve the most relevant information.

[0474] Step 4:

[0475] The device analyzes the acquired data using an AI model and discovers trends and correlations using natural language processing. This analysis generates new hypotheses and research topics.

[0476] Step 5:

[0477] Through an interactive interface, users receive analysis results and suggestions, and can ask additional questions or give instructions to the AI ​​agent as needed. The agent then refines the information based on the user's feedback.

[0478] Step 6:

[0479] The server leverages the generated hypotheses and proposals to build the user's experimental design and planning schedule through project management tools designed to optimize the research process. This includes resource allocation and scheduling adjustments.

[0480] Step 7:

[0481] The device integrates knowledge from different fields to generate new research ideas. The AI ​​agent combines information from multiple specialized areas to propose multifaceted research approaches to the user.

[0482] Step 8:

[0483] Users accept proposed ideas and plans, take concrete actions to advance their research, and effectively conduct their research with support from the system.

[0484] (Example 1)

[0485] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0486] Traditional research into pharmaceuticals and treatments lacks the means to efficiently collect and analyze large amounts of data, generate new hypotheses, and optimize the research process. Furthermore, multifaceted research utilizing knowledge from different fields has been difficult. Therefore, a new system is needed to enable researchers and pharmaceutical companies to conduct research quickly and efficiently, and to produce innovative results.

[0487] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0488] In this invention, the server includes means for accessing external information sources via a network to automatically acquire information, means for processing and indexing the acquired information to make it efficiently searchable, and means for analyzing the data and generating new hypotheses using machine learning and natural language processing. This enables researchers to generate hypotheses based on the latest information, optimizing the research process and promoting new research through a multifaceted approach.

[0489] "Means of accessing external information sources via a network" refers to a function that uses a network such as the internet to automatically connect to external databases or APIs and retrieve the necessary information.

[0490] "Methods for processing and indexing information to make it efficiently searchable" refers to the process of analyzing the characteristics and relationships of collected information, organizing the data structure to enable efficient searching, and then indexing it.

[0491] "Means of analyzing data and generating new hypotheses using machine learning and natural language processing" refers to the function of forming research hypotheses by applying machine learning algorithms and natural language processing techniques to collected data and discovering new insights and relationships.

[0492] An "interactive user interface" is an interface that allows users to directly interact with a system, and is a mechanism that enables the system to automatically present information and facilitate communication based on user input.

[0493] "Project management methods" are techniques for planning and efficiently advancing the research process, and include functions for allocating resources and adjusting schedules.

[0494] "Integrating multiple areas of expertise and creating new research approaches that span different fields" refers to the process of combining knowledge from different disciplines to develop original and multifaceted research methods.

[0495] This invention is an AI agent system designed to enable medical researchers and pharmaceutical companies to efficiently advance new drug development and treatment research. The system aims to optimize the research process by generating innovative hypotheses through large-scale data collection and analysis.

[0496] Data collection and updating

[0497] The server automatically retrieves information from multiple medical databases via the network. This ensures that the latest medical papers, clinical trial data, and patent information are regularly collected. The software used includes libraries and database management systems to facilitate API access.

[0498] Data analysis and hypothesis generation

[0499] The terminal retrieves indexed data from the server in real time and analyzes it using machine learning and natural language processing techniques. Specifically, by using frameworks such as TensorFlow and PyTorch, it can discover trends and correlations within the data and generate new hypotheses.

[0500] Research support through interactive interfaces

[0501] Users can operate the AI ​​agent through the terminal's interface and input information about their research topic. This allows the AI ​​to share generated hypotheses and related information with the user, supporting the deepening of the research through continuous dialogue.

[0502] Optimization of the research process

[0503] The server manages the execution of plans based on hypotheses provided by AI agents. It optimizes experimental designs and clinical trial schedules, and ensures efficient resource allocation.

[0504] Knowledge integration and idea generation

[0505] The device integrates multiple areas of expertise, creating new research approaches that transcend different disciplines. This enables users to conduct research across a wide range of fields.

[0506] For example, if the research topic is "the potential of new biomarkers in immunotherapy," the AI ​​agent will analyze the latest relevant research data and present promising biomarker candidates.

[0507] Example of a prompt:

[0508] "To discover novel biomarkers, analyze recent immunotherapy data and identify relevant trends and correlations."

[0509] "Generate hypotheses based on the latest medical literature and data to explore the potential of new drugs for treating Alzheimer's disease."

[0510] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0511] Step 1:

[0512] The server accesses external medical-related database APIs via the network on a regularly scheduled basis. Input is requests from the APIs, and output is the received data in the form of the latest medical papers, clinical trial data, and patent information. By retrieving this data, the system maintains up-to-date information at all times.

[0513] Step 2:

[0514] The server processes and indexes the acquired data. In this step, it analyzes the raw data received as input and extracts metadata. The output is indexed data to improve search efficiency. This indexing allows for quick retrieval of necessary information.

[0515] Step 3:

[0516] The terminal receives specific research topics or questions from the user as input. In this process, relevant data is retrieved from the server in real time based on the input topic. The output is the retrieved relevant data, which is used in the next data analysis stage.

[0517] Step 4:

[0518] The device analyzes the acquired data using machine learning algorithms, such as TensorFlow or PyTorch. The input is real-time acquired data, and the output is analysis results that reveal important trends and new hypotheses. This allows users to gain unprecedented insights.

[0519] Step 5:

[0520] The terminal presents the user with newly generated proposals and hypotheses based on the analysis results. In this interactive interface, the analysis results are the input, and the output is proposals and hypotheses for the user. The user can use this to determine new directions for further research.

[0521] Step 6:

[0522] The server optimizes the research process based on suggestions from the AI ​​agent. The input is suggestions obtained from an interactive interface, and the output is an optimized experimental design and clinical trial schedule. This improves research efficiency and enables optimal resource allocation.

[0523] Step 7:

[0524] The device integrates knowledge from diverse fields of expertise and proposes new research approaches. In this step, the input is knowledge from various fields, and the output is new research ideas resulting from interdisciplinary collaboration. This allows users to advance their research from innovative and multifaceted perspectives.

[0525] (Application Example 1)

[0526] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0527] In modern manufacturing facilities, improving the efficiency of manufacturing processes and ensuring quality control are critical challenges. However, in many cases, it is difficult to perform real-time analysis and make appropriate adjustments. This is especially true in pharmaceutical factories, where the manufacturing process for pharmaceuticals is complex and multifaceted, making traditional management methods often inadequate. This problem can lead to increased manufacturing costs, production delays, and a decline in quality. Therefore, there is a need for technologies that can optimize manufacturing processes efficiently and quickly and guarantee quality.

[0528] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0529] In this invention, the server includes means for automatically retrieving information from a vast database, means for analyzing the retrieved information to generate new hypotheses, and means for analyzing data related to the manufacturing process to optimize process efficiency. This enables real-time analysis and immediate adjustment of the manufacturing process in the factory, thereby achieving improved manufacturing efficiency and enhanced quality control.

[0530] A "database" is an information system used to structure and store vast amounts of information, and to efficiently search for and retrieve it.

[0531] "Hypothesis generation" is the process of proposing new research directions and theories by analyzing collected data.

[0532] An "interactive interface" is an operating environment in which users can directly interact with the system and receive the necessary information.

[0533] "Process management" is a management method used to efficiently organize manufacturing and business processes and to adjust them so that they operate according to plan.

[0534] "Knowledge integration" is the process of combining diverse information obtained from different fields to generate new insights and innovations.

[0535] "Process optimization" refers to adjusting each stage of manufacturing or operations to ensure optimal progress, eliminating waste, and improving productivity.

[0536] "Real-time analysis" is a technology that processes information instantly and provides rapid feedback of the results.

[0537] "Production line adjustment" refers to the activity of reviewing the allocation of equipment and personnel according to the progress of the manufacturing process in order to maintain an optimal manufacturing environment.

[0538] The system that realizes this invention consists mainly of a server and terminals. The server automatically retrieves medical information from a vast database and also collects data related to the manufacturing process in real time. This data is indexed and stored in a database that allows for efficient searching. For analysis, machine learning libraries such as TensorFlow or PyTorch and natural language processing tools such as NLTK or spaCy are used. Based on the analyzed data, the server generates hypotheses and transmits new suggestions to the terminals.

[0539] The terminal is operated by the user via an interactive interface. Users input research topics of interest or on-site challenges, and receive optimal manufacturing process adjustments and hypotheses from an AI agent. Based on user guidance, the system monitors the manufacturing line in real time and provides suggestions for maintenance, enabling operational optimization. Furthermore, the terminal facilitates the integration of knowledge from different fields, supporting the generation of new research and manufacturing method ideas.

[0540] As a concrete example, in a tablet manufacturing line, an AI application monitors fluctuations in drug components in real time and immediately adjusts production line parameters as needed. This system makes it possible to improve production efficiency while suppressing the occurrence of defective products.

[0541] An example of a prompt for the generated AI model is, "Analyze manufacturing data in real time and propose an efficient production model." In this way, this system plays an important role in quality assurance and process efficiency in the manufacturing industry.

[0542] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0543] Step 1:

[0544] The server automatically retrieves publicly available medical information from a vast database. Input consists of medical articles and patent information found on the internet, and the program collects information according to a regular schedule. The collected information is then subjected to metadata extraction and indexing, and stored as an efficient, searchable database. The output is a searchable database.

[0545] Step 2:

[0546] The server collects sensor data from the manufacturing process in real time. The input consists of process-related data from sensors installed within the factory, which is continuously transmitted to the server. Based on this real-time data, an anomaly detection algorithm is run, and calculations are performed to immediately analyze the line status. The output provides insights for process efficiency.

[0547] Step 3:

[0548] The terminal analyzes important trends and correlations from data stored on the server and generates new hypotheses using a generative AI model. The input is the data to be analyzed, which is passed through the machine learning library TensorFlow or PyTorch to perform calculations to capture complex data patterns. The output is the proposed hypothesis and suggested improvements to the manufacturing process based on it.

[0549] Step 4:

[0550] The user inputs research topics of interest or work-related challenges through the terminal's interactive interface. This input consists of natural language prompts from the user. These prompts prompt a generative AI model performs reasoning, outputting appropriate hypotheses and manufacturing adjustment proposals on the terminal.

[0551] Step 5:

[0552] The terminal adjusts the manufacturing line based on user prompts and AI-generated hypotheses. Inputs are user requests and AI suggestions, while output is the adjusted manufacturing parameters. These adjustments are reflected in the manufacturing line's operation in real time and communicated via the server to enable more efficient production.

[0553] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0554] This invention is an advanced AI agent system designed to significantly improve research processes for medical researchers and pharmaceutical companies. In addition to data collection, analysis, hypothesis generation, user interface, and process management functions, the system incorporates an emotion engine that recognizes user emotions and optimizes responses.

[0555] Data collection and analysis

[0556] First, the server continuously collects information from medical databases, obtaining the latest research and patent data. The collected information is indexed to enable efficient searching and analysis.

[0557] Hypothesis generation

[0558] The AI ​​agent on the device analyzes the collected data and generates new hypotheses using natural language processing and machine learning algorithms. This process leads to insights and suggestions aligned with the user's research topic.

[0559] Interactive interface

[0560] Users can interact directly with an AI agent through their device to receive feedback on their research topics and questions. This interface adapts to user requests and provides data analysis results in real time.

[0561] Emotional Engine

[0562] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time. This engine analyzes the user's text input, facial expressions, and voice tone to determine their emotional state. For example, if the user is feeling frustrated, the agent will provide a more friendly tone and additional support information.

[0563] Process management and knowledge integration

[0564] The server utilizes the output of AI agents to optimize the research process, including efficient experimental design and scheduling. It can also integrate information from different disciplines to generate new research ideas.

[0565] For example, if a user requests to know the latest trends in immunotherapy research, the AI ​​agent analyzes relevant data to identify trends and presents the results to the user. Simultaneously, the emotion engine analyzes the user's reactions and responds according to their level of understanding and interest.

[0566] This system allows medical researchers to not only obtain advanced information and analysis, but also to efficiently advance their research while receiving optimal support tailored to their individual needs and emotional responses. Thus, this invention will be an important tool for promoting innovation in new drug development and treatment research.

[0567] The following describes the processing flow.

[0568] Step 1:

[0569] The server accesses multiple medical databases to automatically collect the latest research papers, clinical trial data, and patent information. This process is scheduled regularly, and duplicate data is removed and formats are standardized to maintain data consistency.

[0570] Step 2:

[0571] The server converts the collected data into metadata and indexes it to enable efficient searching. This indexing allows for the rapid retrieval of data of interest from a vast amount of information.

[0572] Step 3:

[0573] The device's AI agent requests filtered data from the server based on the user's input of specific research topics or interests. Based on this request, only relevant information is provided to the device.

[0574] Step 4:

[0575] The device runs an AI agent and analyzes the acquired data. Here, natural language processing and machine learning algorithms are used to detect important trends and correlations, and new hypotheses and research proposals are generated based on these findings.

[0576] Step 5:

[0577] Users receive analysis results and suggestions through an interactive interface with an AI agent. Through the interface, users can ask questions and request additional information about the results.

[0578] Step 6:

[0579] The device's emotion engine analyzes the user's text input, facial expressions, and voice tone to recognize the user's emotional state. For example, if the user shows interest, the agent will provide more detailed information; conversely, if the user appears confused, it will offer a concise explanation.

[0580] Step 7:

[0581] The server optimizes the user's research process based on information and suggestions generated by the emotion engine and AI agents. This optimization includes adjusting the experiment schedule and efficiently allocating resources.

[0582] Step 8:

[0583] The device integrates knowledge from multiple different specialized fields and proposes new research ideas to the user. This allows the user to advance their research from a broader perspective.

[0584] Step 9:

[0585] Users plan and execute specific research activities using new hypotheses and research ideas suggested by the system. They progress through their research with support and gain further insights from the AI ​​agent based on the results.

[0586] (Example 2)

[0587] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0588] In modern scientific research, particularly in the medical field, efficiently collecting and analyzing vast amounts of information is becoming increasingly important. However, this process is time-consuming and labor-intensive, and many challenges remain in integrating knowledge across different research disciplines and generating hypotheses. Furthermore, support for effectively conducting research while considering user emotions is often insufficient. A comprehensive support system is needed to address these challenges.

[0589] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0590] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for analyzing the collected data and generating new hypotheses, and means for an engine that analyzes the user's emotional state and optimizes the response accordingly. This allows researchers to save a great deal of time and effort while integrating knowledge from different fields to aid in hypothesis generation and obtaining effective support that takes the user's emotions into consideration.

[0591] "Information source" refers to the foundation used to obtain data, and is a concept that includes various databases and online repositories.

[0592] An "automatic data collection device" is a system component that has the function of efficiently acquiring relevant information from a vast amount of information sources.

[0593] A "data analysis device" is a component designed to process acquired data and find patterns and insights, often utilizing artificial intelligence technology.

[0594] "Hypothesis generation" is the process of constructing new research hypotheses based on the results of data analysis.

[0595] An "interactive user interface device" is a component that provides an intuitive means of communication for users to interact with a system in real time and exchange information.

[0596] A "process management device" is a system element that provides functions for optimizing schedule management and other business processes in order to streamline the research process.

[0597] A "knowledge integration device" is a device that unifies information obtained from different fields and has the function of creating new research perspectives and ideas.

[0598] An "emotional state analysis engine" is an analytical tool that evaluates a user's emotions in real time and adjusts the system response accordingly.

[0599] The system in this invention provides a means for streamlining information aggregation and analysis processes in the fields of medicine and scientific research. First, the system automatically collects data from a vast number of information sources via a server. This collection includes access to digital repositories and online databases. Specifically, the server can retrieve relevant papers and patent data using an API interface.

[0600] This data is indexed on the server and prepared for efficient searching and analysis. A search engine such as Elasticsearch is used for data indexing. In this process, the data's metadata is organized, optimizing the subsequent analysis process.

[0601] Subsequently, an AI agent on the device analyzes this indexed data. The AI ​​agent utilizes natural language processing techniques and generative AI models to generate new hypotheses from the collected data. This model may employ, for example, the Transformer architecture. Specifically, the device identifies trends in medical research and presents new approaches useful for scientific research projects.

[0602] Through interaction with this AI agent, users receive data via an interactive interface. The user interface presents hypotheses and analysis results in real time and responds to user questions. The interface is built using HTML and JavaScript, allowing for intuitive operation.

[0603] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time and analyzes their emotional state. This engine analyzes the user's input text, voice, and facial expressions to generate appropriate responses based on the user's emotions. This feature allows users to acquire information smoothly without feeling stressed.

[0604] For example, if a user requests to learn about the latest research trends in immunotherapy, the AI ​​agent quickly analyzes relevant data and provides the user with trend information. Simultaneously, the emotion engine analyzes the user's response and adjusts the response according to the user's level of understanding and interest.

[0605] An example of a prompt message could be input to a generative AI model in the form of, "Please explain the key points for understanding the latest research in immunotherapy. Also, please point out any particularly noteworthy trends."

[0606] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0607] Step 1:

[0608] The server accesses medical databases and information sources and collects data based on specified keywords. In this example, the keyword "immunotherapy" is used as input, and relevant article information is retrieved from databases such as PubMed. The data is output in original text format.

[0609] Step 2:

[0610] The server indexes the collected data using a search engine such as Elasticsearch. It uses the text data from Step 1 as input and organizes it by metadata (author, title, abstract, etc.). The output is structured index data that can be quickly searched.

[0611] Step 3:

[0612] The AI ​​agent on the terminal analyzes indexed data. The input is structured indexed data, and natural language processing is performed using a generative AI model. Through this process, patterns are extracted from the data and output as new hypotheses (e.g., "Novel approaches in immunotherapy").

[0613] Step 4:

[0614] Users ask specific questions to the AI ​​agent via their device. By entering prompts such as "I want to know the latest trends in immunotherapy" into the user interface, the AI ​​agent refers to index data and outputs analysis results in real time. This output includes answers and insights tailored to the user's requests.

[0615] Step 5:

[0616] The device's emotion engine analyzes the user's emotional state. Inputs include user text, voice, and facial expression data, which are used for emotion analysis. The output is an AI agent response in a format that is easy for the user to understand—for example, gentle supplementary explanations.

[0617] Step 6:

[0618] The server manages the entire process and provides process management functions to optimize research activities based on the data obtained and the hypotheses generated. The input is the output of all the previous steps, and the server uses this to suggest efficient experimental designs and schedules, generating valuable outputs for researchers.

[0619] (Application Example 2)

[0620] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0621] This invention aims to solve the problem of improving the quality of services provided to users while reducing the burden on care staff by promoting the understanding and appropriate response to the emotional state of users in the care process. Furthermore, it aims to improve the efficiency and optimization of care support by integrating and utilizing data from different information sources.

[0622] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0623] In this invention, the server includes means for automatically acquiring data from a vast number of information sources, means for analyzing the acquired data to generate new hypotheses, interactive interface means for presenting the generated hypotheses and proposals to the user, emotion analysis means for recognizing the user's emotions and optimizing responses, process management means for optimizing the research and support process, and means for integrating knowledge from different domains to create new research or support ideas. This enables care staff to grasp the user's emotions in real time and support optimal care responses.

[0624] An "information source" is a collection of resources from which data is obtained from various fields.

[0625] "Data" refers to units of facts and knowledge obtained from information sources, which are transformed into useful information through analysis.

[0626] "Analysis" is the process of using acquired data to find meaningful patterns and relationships.

[0627] A "hypothesis" is a new proposal or attempt at explanation derived from the results of an analysis.

[0628] An "interactive interface" is a direct means of communication that allows users to exchange information with a system.

[0629] "Emotional analysis" is a process for understanding the emotional state of users and optimizing the system's response.

[0630] "Process management" is a management method for planning, executing, evaluating, and streamlining the flow of research and support activities.

[0631] "Knowledge integration" is the process of combining information obtained from different fields to create new value.

[0632] A "support idea" is a proposal for a new method or technique created in the provision of care and services.

[0633] The system that realizes this application runs on a server and includes an advanced AI agent specifically designed to support the caregiving process. The server acquires and analyzes data from diverse sources. For analysis, it uses a program built in Python, performs facial recognition from image data using OpenCV, and estimates emotions using a TensorFlow model. In addition, it analyzes emotions from voice input using nltk. As a result, care staff, as users, can understand the user's condition in real time through devices such as smart glasses.

[0634] Information obtained through emotion analysis is sent to the caregiver's terminal, where an AI agent presents recommended care responses. The terminal has an interactive interface that provides direct interaction methods and options for the user.

[0635] As a concrete example, if a user experiences stress in their daily life, the system detects changes in their facial expressions and voice. The server analyzes this data and notifies the care staff's terminal with a message such as, "The user is feeling anxious. It would be best to speak to them gently." In this way, the system analyzes emotional data in real time to support caregiving tasks.

[0636] By utilizing generative AI models, it becomes possible to flexibly provide solutions for a variety of situations.

[0637] An example of a prompt message is: "Design a friendly AI assistant that analyzes the user's emotional state from facial expression data and voice input, and provides appropriate care in real time."

[0638] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0639] Step 1:

[0640] The server collects user data from care facilities and affiliated information sources. This data includes image data, audio data, and health status records. The collected data is standardized to support various formats. The input is raw data, and the output is standardized data.

[0641] Step 2:

[0642] The server analyzes image data collected using OpenCV and estimates emotions from the user's facial expressions. It extracts facial landmarks from the image data (input) and classifies emotions using a TensorFlow model. The output is the emotion label estimated based on the user's facial expressions.

[0643] Step 3:

[0644] The device uses NLTK to analyze speech data and recognize emotions from the content and tone of speech. The speech data (input) is converted to text and subjected to natural language processing. This results in an output that indicates emotions.

[0645] Step 4:

[0646] The server uses a generative AI model to comprehensively assess the user's condition based on collected emotional data and health records. In this process, the AI ​​generates care support suggestions appropriate to the user's current emotional state. The input is estimated emotional labels and health data, and the output is specific countermeasures and advice.

[0647] Step 5:

[0648] The device notifies care staff of recommended actions and provides specific instructions through an interactive interface. The notification is the input, and the output is the instruction to the care staff. This allows staff to provide optimal care to users at the appropriate time.

[0649] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0650] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0651] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0652] [Fourth Embodiment]

[0653] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0654] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0655] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0656] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0657] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0658] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0659] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0660] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0661] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0662] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0663] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0664] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0665] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0666] This invention is an AI agent system for medical researchers and pharmaceutical companies to efficiently conduct new drug development and treatment research. The system of this invention has the following configuration.

[0667] Data collection and updating

[0668] First, the server collects information from multiple medical-related databases publicly available on the internet. This collection is automated and carried out according to a regular schedule. For example, it includes the latest medical papers, clinical trial data, and patent information. The collected data undergoes metadata extraction and indexing, and is stored in a database that allows for efficient searching.

[0669] Data analysis and hypothesis generation

[0670] The AI ​​agent deployed on the terminal retrieves necessary information from this database in real time and analyzes it using machine learning and natural language processing techniques. The purpose of the analysis is to discover important trends and correlations and generate new hypotheses and research themes.

[0671] Research support through interactive interfaces

[0672] Users can interact with an AI agent on their device to input questions or research topics and receive responses regarding hypotheses and related information. This interface is interactive, allowing users to ask additional questions and refine information to help clarify the direction of their research.

[0673] Optimization of the research process

[0674] Next, the server manages the project to optimize the user's research process based on suggestions and hypotheses from the AI ​​agent. Specifically, it optimizes experimental design and clinical trial schedules to support efficient progress. The plan is customized according to the user's requirements, ensuring efficient resource allocation.

[0675] Knowledge integration and idea generation

[0676] Finally, the device integrates knowledge from various specialized fields and generates new ideas. This allows users to take a multifaceted research approach that leverages knowledge from different disciplines.

[0677] For example, when researching "the potential of new biomarkers in immunotherapy," the AI ​​agent analyzes the latest relevant research data and presents promising biomarker candidates. Based on this information, the user can then plan and conduct further experiments and research.

[0678] Thus, the present invention provides a powerful tool for medical researchers to drive innovation rapidly and efficiently.

[0679] The following describes the processing flow.

[0680] Step 1:

[0681] The server automatically collects medical-related data from databases and APIs connected to the internet. This includes the latest research papers, clinical trial data, and patent information, and the data is collected on a regularly scheduled basis. The collected data is then indexed after undergoing processes such as deduplicating and formatting standardization.

[0682] Step 2:

[0683] The server stores the indexed data in a database, enabling efficient searching. During this process, metadata is extracted, and the data is categorized and tagged to improve search performance.

[0684] Step 3:

[0685] The device retrieves relevant data from the server based on the user's request. When the user requests a specific research topic, the AI ​​agent filters the target data and prepares to retrieve the most relevant information.

[0686] Step 4:

[0687] The device analyzes the acquired data using an AI model and discovers trends and correlations using natural language processing. This analysis generates new hypotheses and research topics.

[0688] Step 5:

[0689] Through an interactive interface, users receive analysis results and suggestions, and can ask additional questions or give instructions to the AI ​​agent as needed. The agent then refines the information based on the user's feedback.

[0690] Step 6:

[0691] The server leverages the generated hypotheses and proposals to build the user's experimental design and planning schedule through project management tools designed to optimize the research process. This includes resource allocation and scheduling adjustments.

[0692] Step 7:

[0693] The device integrates knowledge from different fields to generate new research ideas. The AI ​​agent combines information from multiple specialized areas to propose multifaceted research approaches to the user.

[0694] Step 8:

[0695] Users accept proposed ideas and plans, take concrete actions to advance their research, and effectively conduct their research with support from the system.

[0696] (Example 1)

[0697] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0698] Traditional research into pharmaceuticals and treatments lacks the means to efficiently collect and analyze large amounts of data, generate new hypotheses, and optimize the research process. Furthermore, multifaceted research utilizing knowledge from different fields has been difficult. Therefore, a new system is needed to enable researchers and pharmaceutical companies to conduct research quickly and efficiently, and to produce innovative results.

[0699] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0700] In this invention, the server includes means for accessing external information sources via a network to automatically acquire information, means for processing and indexing the acquired information to make it efficiently searchable, and means for analyzing the data and generating new hypotheses using machine learning and natural language processing. This enables researchers to generate hypotheses based on the latest information, optimizing the research process and promoting new research through a multifaceted approach.

[0701] "Means of accessing external information sources via a network" refers to a function that uses a network such as the internet to automatically connect to external databases or APIs and retrieve the necessary information.

[0702] "Methods for processing and indexing information to make it efficiently searchable" refers to the process of analyzing the characteristics and relationships of collected information, organizing the data structure to enable efficient searching, and then indexing it.

[0703] "Means of analyzing data and generating new hypotheses using machine learning and natural language processing" refers to the function of forming research hypotheses by applying machine learning algorithms and natural language processing techniques to collected data and discovering new insights and relationships.

[0704] An "interactive user interface" is an interface that allows users to directly interact with a system, and is a mechanism that enables the system to automatically present information and facilitate communication based on user input.

[0705] "Project management methods" are techniques for planning and efficiently advancing the research process, and include functions for allocating resources and adjusting schedules.

[0706] "Integrating multiple areas of expertise and creating new research approaches that span different fields" refers to the process of combining knowledge from different disciplines to develop original and multifaceted research methods.

[0707] This invention is an AI agent system designed to enable medical researchers and pharmaceutical companies to efficiently advance new drug development and treatment research. The system aims to optimize the research process by generating innovative hypotheses through large-scale data collection and analysis.

[0708] Data collection and updating

[0709] The server automatically retrieves information from multiple medical databases via the network. This ensures that the latest medical papers, clinical trial data, and patent information are regularly collected. The software used includes libraries and database management systems to facilitate API access.

[0710] Data analysis and hypothesis generation

[0711] The terminal retrieves indexed data from the server in real time and analyzes it using machine learning and natural language processing techniques. Specifically, by using frameworks such as TensorFlow and PyTorch, it can discover trends and correlations within the data and generate new hypotheses.

[0712] Research support through interactive interfaces

[0713] Users can operate the AI ​​agent through the terminal's interface and input information about their research topic. This allows the AI ​​to share generated hypotheses and related information with the user, supporting the deepening of the research through continuous dialogue.

[0714] Optimization of the research process

[0715] The server manages the execution of plans based on hypotheses provided by AI agents. It optimizes experimental designs and clinical trial schedules, and ensures efficient resource allocation.

[0716] Knowledge integration and idea generation

[0717] The device integrates multiple areas of expertise, creating new research approaches that transcend different disciplines. This enables users to conduct research across a wide range of fields.

[0718] For example, if the research topic is "the potential of new biomarkers in immunotherapy," the AI ​​agent will analyze the latest relevant research data and present promising biomarker candidates.

[0719] Example of a prompt:

[0720] "To discover novel biomarkers, analyze recent immunotherapy data and identify relevant trends and correlations."

[0721] "Generate hypotheses based on the latest medical literature and data to explore the potential of new drugs for treating Alzheimer's disease."

[0722] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0723] Step 1:

[0724] The server accesses external medical-related database APIs via the network on a regularly scheduled basis. Input is requests from the APIs, and output is the received data in the form of the latest medical papers, clinical trial data, and patent information. By retrieving this data, the system maintains up-to-date information at all times.

[0725] Step 2:

[0726] The server processes and indexes the acquired data. In this step, it analyzes the raw data received as input and extracts metadata. The output is indexed data to improve search efficiency. This indexing allows for quick retrieval of necessary information.

[0727] Step 3:

[0728] The terminal receives specific research topics or questions from the user as input. In this process, relevant data is retrieved from the server in real time based on the input topic. The output is the retrieved relevant data, which is used in the next data analysis stage.

[0729] Step 4:

[0730] The device analyzes the acquired data using machine learning algorithms, such as TensorFlow or PyTorch. The input is real-time acquired data, and the output is analysis results that reveal important trends and new hypotheses. This allows users to gain unprecedented insights.

[0731] Step 5:

[0732] The terminal presents the user with newly generated proposals and hypotheses based on the analysis results. In this interactive interface, the analysis results are the input, and the output is proposals and hypotheses for the user. The user can use this to determine new directions for further research.

[0733] Step 6:

[0734] The server optimizes the research process based on suggestions from the AI ​​agent. The input is suggestions obtained from an interactive interface, and the output is an optimized experimental design and clinical trial schedule. This improves research efficiency and enables optimal resource allocation.

[0735] Step 7:

[0736] The device integrates knowledge from diverse fields of expertise and proposes new research approaches. In this step, the input is knowledge from various fields, and the output is new research ideas resulting from interdisciplinary collaboration. This allows users to advance their research from innovative and multifaceted perspectives.

[0737] (Application Example 1)

[0738] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0739] In modern manufacturing facilities, improving the efficiency of manufacturing processes and ensuring quality control are critical challenges. However, in many cases, it is difficult to perform real-time analysis and make appropriate adjustments. This is especially true in pharmaceutical factories, where the manufacturing process for pharmaceuticals is complex and multifaceted, making traditional management methods often inadequate. This problem can lead to increased manufacturing costs, production delays, and a decline in quality. Therefore, there is a need for technologies that can optimize manufacturing processes efficiently and quickly and guarantee quality.

[0740] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0741] In this invention, the server includes means for automatically retrieving information from a vast database, means for analyzing the retrieved information to generate new hypotheses, and means for analyzing data related to the manufacturing process to optimize process efficiency. This enables real-time analysis and immediate adjustment of the manufacturing process in the factory, thereby achieving improved manufacturing efficiency and enhanced quality control.

[0742] A "database" is an information system used to structure and store vast amounts of information, and to efficiently search for and retrieve it.

[0743] "Hypothesis generation" is the process of proposing new research directions and theories by analyzing collected data.

[0744] An "interactive interface" is an operating environment in which users can directly interact with the system and receive the necessary information.

[0745] "Process management" is a management method used to efficiently organize manufacturing and business processes and to adjust them so that they operate according to plan.

[0746] "Knowledge integration" is the process of combining diverse information obtained from different fields to generate new insights and innovations.

[0747] "Process optimization" refers to adjusting each stage of manufacturing or operations to ensure optimal progress, eliminating waste, and improving productivity.

[0748] "Real-time analysis" is a technology that processes information instantly and provides rapid feedback of the results.

[0749] "Production line adjustment" refers to the activity of reviewing the allocation of equipment and personnel according to the progress of the manufacturing process in order to maintain an optimal manufacturing environment.

[0750] The system that realizes this invention consists mainly of a server and terminals. The server automatically retrieves medical information from a vast database and also collects data related to the manufacturing process in real time. This data is indexed and stored in a database that allows for efficient searching. For analysis, machine learning libraries such as TensorFlow or PyTorch and natural language processing tools such as NLTK or spaCy are used. Based on the analyzed data, the server generates hypotheses and transmits new suggestions to the terminals.

[0751] The terminal is operated by the user via an interactive interface. Users input research topics of interest or on-site challenges, and receive optimal manufacturing process adjustments and hypotheses from an AI agent. Based on user guidance, the system monitors the manufacturing line in real time and provides suggestions for maintenance, enabling operational optimization. Furthermore, the terminal facilitates the integration of knowledge from different fields, supporting the generation of new research and manufacturing method ideas.

[0752] As a concrete example, in a tablet manufacturing line, an AI application monitors fluctuations in drug components in real time and immediately adjusts production line parameters as needed. This system makes it possible to improve production efficiency while suppressing the occurrence of defective products.

[0753] An example of a prompt for the generated AI model is, "Analyze manufacturing data in real time and propose an efficient production model." In this way, this system plays an important role in quality assurance and process efficiency in the manufacturing industry.

[0754] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0755] Step 1:

[0756] The server automatically retrieves publicly available medical information from a vast database. Input consists of medical articles and patent information found on the internet, and the program collects information according to a regular schedule. The collected information is then subjected to metadata extraction and indexing, and stored as an efficient, searchable database. The output is a searchable database.

[0757] Step 2:

[0758] The server collects sensor data from the manufacturing process in real time. The input consists of process-related data from sensors installed within the factory, which is continuously transmitted to the server. Based on this real-time data, an anomaly detection algorithm is run, and calculations are performed to immediately analyze the line status. The output provides insights for process efficiency.

[0759] Step 3:

[0760] The terminal analyzes important trends and correlations from data stored on the server and generates new hypotheses using a generative AI model. The input is the data to be analyzed, which is passed through the machine learning library TensorFlow or PyTorch to perform calculations to capture complex data patterns. The output is the proposed hypothesis and suggested improvements to the manufacturing process based on it.

[0761] Step 4:

[0762] The user inputs research topics of interest or work-related challenges through the terminal's interactive interface. This input consists of natural language prompts from the user. These prompts prompt a generative AI model performs reasoning, outputting appropriate hypotheses and manufacturing adjustment proposals on the terminal.

[0763] Step 5:

[0764] The terminal adjusts the manufacturing line based on user prompts and AI-generated hypotheses. Inputs are user requests and AI suggestions, while output is the adjusted manufacturing parameters. These adjustments are reflected in the manufacturing line's operation in real time and communicated via the server to enable more efficient production.

[0765] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0766] This invention is an advanced AI agent system designed to significantly improve research processes for medical researchers and pharmaceutical companies. In addition to data collection, analysis, hypothesis generation, user interface, and process management functions, the system incorporates an emotion engine that recognizes user emotions and optimizes responses.

[0767] Data collection and analysis

[0768] First, the server continuously collects information from medical databases, obtaining the latest research and patent data. The collected information is indexed to enable efficient searching and analysis.

[0769] Hypothesis generation

[0770] The AI ​​agent on the device analyzes the collected data and generates new hypotheses using natural language processing and machine learning algorithms. This process leads to insights and suggestions aligned with the user's research topic.

[0771] Interactive interface

[0772] Users can interact directly with an AI agent through their device to receive feedback on their research topics and questions. This interface adapts to user requests and provides data analysis results in real time.

[0773] Emotional Engine

[0774] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time. This engine analyzes the user's text input, facial expressions, and voice tone to determine their emotional state. For example, if the user is feeling frustrated, the agent will provide a more friendly tone and additional support information.

[0775] Process management and knowledge integration

[0776] The server utilizes the output of AI agents to optimize the research process, including efficient experimental design and scheduling. It can also integrate information from different disciplines to generate new research ideas.

[0777] For example, if a user requests to know the latest trends in immunotherapy research, the AI ​​agent analyzes relevant data to identify trends and presents the results to the user. Simultaneously, the emotion engine analyzes the user's reactions and responds according to their level of understanding and interest.

[0778] This system allows medical researchers to not only obtain advanced information and analysis, but also to efficiently advance their research while receiving optimal support tailored to their individual needs and emotional responses. Thus, this invention will be an important tool for promoting innovation in new drug development and treatment research.

[0779] The following describes the processing flow.

[0780] Step 1:

[0781] The server accesses multiple medical databases to automatically collect the latest research papers, clinical trial data, and patent information. This process is scheduled regularly, and duplicate data is removed and formats are standardized to maintain data consistency.

[0782] Step 2:

[0783] The server converts the collected data into metadata and indexes it to enable efficient searching. This indexing allows for the rapid retrieval of data of interest from a vast amount of information.

[0784] Step 3:

[0785] The device's AI agent requests filtered data from the server based on the user's input of specific research topics or interests. Based on this request, only relevant information is provided to the device.

[0786] Step 4:

[0787] The device runs an AI agent and analyzes the acquired data. Here, natural language processing and machine learning algorithms are used to detect important trends and correlations, and new hypotheses and research proposals are generated based on these findings.

[0788] Step 5:

[0789] Users receive analysis results and suggestions through an interactive interface with an AI agent. Through the interface, users can ask questions and request additional information about the results.

[0790] Step 6:

[0791] The device's emotion engine analyzes the user's text input, facial expressions, and voice tone to recognize the user's emotional state. For example, if the user shows interest, the agent will provide more detailed information; conversely, if the user appears confused, it will offer a concise explanation.

[0792] Step 7:

[0793] The server optimizes the user's research process based on information and suggestions generated by the emotion engine and AI agents. This optimization includes adjusting the experiment schedule and efficiently allocating resources.

[0794] Step 8:

[0795] The device integrates knowledge from multiple different specialized fields and proposes new research ideas to the user. This allows the user to advance their research from a broader perspective.

[0796] Step 9:

[0797] Users plan and execute specific research activities using new hypotheses and research ideas suggested by the system. They progress through their research with support and gain further insights from the AI ​​agent based on the results.

[0798] (Example 2)

[0799] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0800] In modern scientific research, particularly in the medical field, efficiently collecting and analyzing vast amounts of information is becoming increasingly important. However, this process is time-consuming and labor-intensive, and many challenges remain in integrating knowledge across different research disciplines and generating hypotheses. Furthermore, support for effectively conducting research while considering user emotions is often insufficient. A comprehensive support system is needed to address these challenges.

[0801] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0802] In this invention, the server includes means for automatically collecting data from a vast number of information sources, means for analyzing the collected data and generating new hypotheses, and means for an engine that analyzes the user's emotional state and optimizes the response accordingly. This allows researchers to save a great deal of time and effort while integrating knowledge from different fields to aid in hypothesis generation and obtaining effective support that takes the user's emotions into consideration.

[0803] "Information source" refers to the foundation used to obtain data, and is a concept that includes various databases and online repositories.

[0804] An "automatic data collection device" is a system component that has the function of efficiently acquiring relevant information from a vast amount of information sources.

[0805] A "data analysis device" is a component designed to process acquired data and find patterns and insights, often utilizing artificial intelligence technology.

[0806] "Hypothesis generation" is the process of constructing new research hypotheses based on the results of data analysis.

[0807] An "interactive user interface device" is a component that provides an intuitive means of communication for users to interact with a system in real time and exchange information.

[0808] A "process management device" is a system element that provides functions for optimizing schedule management and other business processes in order to streamline the research process.

[0809] A "knowledge integration device" is a device that unifies information obtained from different fields and has the function of creating new research perspectives and ideas.

[0810] An "emotional state analysis engine" is an analytical tool that evaluates a user's emotions in real time and adjusts the system response accordingly.

[0811] The system in this invention provides a means for streamlining information aggregation and analysis processes in the fields of medicine and scientific research. First, the system automatically collects data from a vast number of information sources via a server. This collection includes access to digital repositories and online databases. Specifically, the server can retrieve relevant papers and patent data using an API interface.

[0812] This data is indexed on the server and prepared for efficient searching and analysis. A search engine such as Elasticsearch is used for data indexing. In this process, the data's metadata is organized, optimizing the subsequent analysis process.

[0813] Subsequently, an AI agent on the device analyzes this indexed data. The AI ​​agent utilizes natural language processing techniques and generative AI models to generate new hypotheses from the collected data. This model may employ, for example, the Transformer architecture. Specifically, the device identifies trends in medical research and presents new approaches useful for scientific research projects.

[0814] Through interaction with this AI agent, users receive data via an interactive interface. The user interface presents hypotheses and analysis results in real time and responds to user questions. The interface is built using HTML and JavaScript, allowing for intuitive operation.

[0815] Furthermore, the device is equipped with an emotion engine that recognizes the user's emotions in real time and analyzes their emotional state. This engine analyzes the user's input text, voice, and facial expressions to generate appropriate responses based on the user's emotions. This feature allows users to acquire information smoothly without feeling stressed.

[0816] For example, if a user requests to learn about the latest research trends in immunotherapy, the AI ​​agent quickly analyzes relevant data and provides the user with trend information. Simultaneously, the emotion engine analyzes the user's response and adjusts the response according to the user's level of understanding and interest.

[0817] An example of a prompt message could be input to a generative AI model in the form of, "Please explain the key points for understanding the latest research in immunotherapy. Also, please point out any particularly noteworthy trends."

[0818] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0819] Step 1:

[0820] The server accesses medical databases and information sources and collects data based on specified keywords. In this example, the keyword "immunotherapy" is used as input, and relevant article information is retrieved from databases such as PubMed. The data is output in original text format.

[0821] Step 2:

[0822] The server indexes the collected data using a search engine such as Elasticsearch. It uses the text data from Step 1 as input and organizes it by metadata (author, title, abstract, etc.). The output is structured index data that can be quickly searched.

[0823] Step 3:

[0824] The AI ​​agent on the terminal analyzes indexed data. The input is structured indexed data, and natural language processing is performed using a generative AI model. Through this process, patterns are extracted from the data and output as new hypotheses (e.g., "Novel approaches in immunotherapy").

[0825] Step 4:

[0826] Users ask specific questions to the AI ​​agent via their device. By entering prompts such as "I want to know the latest trends in immunotherapy" into the user interface, the AI ​​agent refers to index data and outputs analysis results in real time. This output includes answers and insights tailored to the user's requests.

[0827] Step 5:

[0828] The device's emotion engine analyzes the user's emotional state. Inputs include user text, voice, and facial expression data, which are used for emotion analysis. The output is an AI agent response in a format that is easy for the user to understand—for example, gentle supplementary explanations.

[0829] Step 6:

[0830] The server manages the entire process and provides process management functions to optimize research activities based on the data obtained and the hypotheses generated. The input is the output of all the previous steps, and the server uses this to suggest efficient experimental designs and schedules, generating valuable outputs for researchers.

[0831] (Application Example 2)

[0832] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0833] This invention aims to solve the problem of improving the quality of services provided to users while reducing the burden on care staff by promoting the understanding and appropriate response to the emotional state of users in the care process. Furthermore, it aims to improve the efficiency and optimization of care support by integrating and utilizing data from different information sources.

[0834] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0835] In this invention, the server includes means for automatically acquiring data from a vast number of information sources, means for analyzing the acquired data to generate new hypotheses, interactive interface means for presenting the generated hypotheses and proposals to the user, emotion analysis means for recognizing the user's emotions and optimizing responses, process management means for optimizing the research and support process, and means for integrating knowledge from different domains to create new research or support ideas. This enables care staff to grasp the user's emotions in real time and support optimal care responses.

[0836] An "information source" is a collection of resources from which data is obtained from various fields.

[0837] "Data" refers to units of facts and knowledge obtained from information sources, which are transformed into useful information through analysis.

[0838] "Analysis" is the process of using acquired data to find meaningful patterns and relationships.

[0839] A "hypothesis" is a new proposal or attempt at explanation derived from the results of an analysis.

[0840] An "interactive interface" is a direct means of communication that allows users to exchange information with a system.

[0841] "Emotional analysis" is a process for understanding the emotional state of users and optimizing the system's response.

[0842] "Process management" is a management method for planning, executing, evaluating, and streamlining the flow of research and support activities.

[0843] "Knowledge integration" is the process of combining information obtained from different fields to create new value.

[0844] A "support idea" is a proposal for a new method or technique created in the provision of care and services.

[0845] The system that realizes this application runs on a server and includes an advanced AI agent specifically designed to support the caregiving process. The server acquires and analyzes data from diverse sources. For analysis, it uses a program built in Python, performs facial recognition from image data using OpenCV, and estimates emotions using a TensorFlow model. In addition, it analyzes emotions from voice input using nltk. As a result, care staff, as users, can understand the user's condition in real time through devices such as smart glasses.

[0846] Information obtained through emotion analysis is sent to the caregiver's terminal, where an AI agent presents recommended care responses. The terminal has an interactive interface that provides direct interaction methods and options for the user.

[0847] As a concrete example, if a user experiences stress in their daily life, the system detects changes in their facial expressions and voice. The server analyzes this data and notifies the care staff's terminal with a message such as, "The user is feeling anxious. It would be best to speak to them gently." In this way, the system analyzes emotional data in real time to support caregiving tasks.

[0848] By utilizing generative AI models, it becomes possible to flexibly provide solutions for a variety of situations.

[0849] An example of a prompt message is: "Design a friendly AI assistant that analyzes the user's emotional state from facial expression data and voice input, and provides appropriate care in real time."

[0850] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0851] Step 1:

[0852] The server collects user data from care facilities and affiliated information sources. This data includes image data, audio data, and health status records. The collected data is standardized to support various formats. The input is raw data, and the output is standardized data.

[0853] Step 2:

[0854] The server analyzes image data collected using OpenCV and estimates emotions from the user's facial expressions. It extracts facial landmarks from the image data (input) and classifies emotions using a TensorFlow model. The output is the emotion label estimated based on the user's facial expressions.

[0855] Step 3:

[0856] The device uses NLTK to analyze speech data and recognize emotions from the content and tone of speech. The speech data (input) is converted to text and subjected to natural language processing. This results in an output that indicates emotions.

[0857] Step 4:

[0858] The server uses a generative AI model to comprehensively assess the user's condition based on collected emotional data and health records. In this process, the AI ​​generates care support suggestions appropriate to the user's current emotional state. The input is estimated emotional labels and health data, and the output is specific countermeasures and advice.

[0859] Step 5:

[0860] The device notifies care staff of recommended actions and provides specific instructions through an interactive interface. The notification is the input, and the output is the instruction to the care staff. This allows staff to provide optimal care to users at the appropriate time.

[0861] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0862] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0863] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0864] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0865] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0866] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0867] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0868] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0869] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0870] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0871] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0872] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0873] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0874] 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.

[0875] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0876] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0877] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0878] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0879] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0880] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0881] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0882] The following is further disclosed regarding the embodiments described above.

[0883] (Claim 1)

[0884] A means of automatically retrieving information from a vast database,

[0885] A means of analyzing acquired information to generate new hypotheses,

[0886] An interactive interface that presents the generated hypotheses and proposals to the user,

[0887] Process management means for optimizing the research process,

[0888] A means of integrating knowledge from different fields to create new research ideas,

[0889] A system that includes this.

[0890] (Claim 2)

[0891] The system according to claim 1, which indexes the collected data and makes it searchable efficiently.

[0892] (Claim 3)

[0893] The system according to claim 1, which acquires data based on user requests and provides analysis results in real time.

[0894] "Example 1"

[0895] (Claim 1)

[0896] Means for accessing external information sources via a network in order to automatically acquire information,

[0897] A means of processing acquired information, indexing it, and making it efficiently searchable,

[0898] Methods for analyzing data and generating new hypotheses using machine learning and natural language processing,

[0899] An interactive user interface that presents hypotheses and suggestions generated in response to user input,

[0900] A project management method that optimizes the user's research process based on the proposed hypothesis and appropriately allocates resources,

[0901] A means of integrating multiple areas of expertise and creating new research approaches that span different fields,

[0902] A system that includes this.

[0903] (Claim 2)

[0904] The system according to claim 1, which retrieves information in real time from data stored in a searchable format and provides analysis results in response to user requests.

[0905] (Claim 3)

[0906] The system according to claim 1, which performs machine learning based on acquired data to discover important trends and correlations.

[0907] "Application Example 1"

[0908] (Claim 1)

[0909] A means of automatically retrieving information from a vast database,

[0910] A means of analyzing acquired information to generate new hypotheses,

[0911] An interactive interface that presents the generated hypotheses and proposals to the user,

[0912] Process management means for optimizing the research process,

[0913] A means of integrating knowledge from different fields to create new research ideas,

[0914] A means of optimizing process efficiency by analyzing data related to the manufacturing process,

[0915] A means of performing real-time anomaly detection and production line adjustment,

[0916] A system that includes this.

[0917] (Claim 2)

[0918] The system according to claim 1, which indexes the collected data and makes it searchable efficiently.

[0919] (Claim 3)

[0920] The system according to claim 1, which acquires data based on user requests and provides analysis results in real time.

[0921] "Example 2 of combining an emotion engine"

[0922] (Claim 1)

[0923] A device that automatically collects data from a vast number of information sources,

[0924] A device that analyzes collected data and generates new hypotheses,

[0925] An interactive user interface device for manipulating the generated hypotheses and proposals,

[0926] A process control device for streamlining and optimizing the research process,

[0927] A device that integrates knowledge from diverse fields to generate new research ideas,

[0928] A device equipped with an engine that analyzes the user's emotional state and optimizes the response based on that analysis,

[0929] A system that includes this.

[0930] (Claim 2)

[0931] The system according to claim 1, which indexes the collected data and enables efficient information retrieval and analysis.

[0932] (Claim 3)

[0933] The system according to claim 1, which accepts user requests, acquires data based on those requests, and provides analysis results in real time.

[0934] "Application example 2 when combining with an emotional engine"

[0935] (Claim 1)

[0936] A means of automatically acquiring data from a vast number of information sources,

[0937] A means of analyzing acquired data to generate new hypotheses,

[0938] An interactive interface that presents generated hypotheses and proposals to the user,

[0939] An emotion analysis tool that recognizes the user's emotions and optimizes the response,

[0940] Process management tools for optimizing research and support processes,

[0941] A means of integrating knowledge from different fields to create new research or support ideas,

[0942] A system that includes this.

[0943] (Claim 2)

[0944] The system according to claim 1, which indexes the collected data and makes it searchable efficiently.

[0945] (Claim 3)

[0946] The system according to claim 1, which acquires data based on user requests and provides analysis results and sentiment evaluations in real time. [Explanation of symbols]

[0947] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of automatically retrieving information from a vast database, A means of analyzing acquired information to generate new hypotheses, An interactive interface that presents the generated hypotheses and proposals to the user, Process management means for optimizing the research process, A means of integrating knowledge from different fields to create new research ideas, A means of optimizing process efficiency by analyzing data related to the manufacturing process, A means of performing real-time anomaly detection and production line adjustment, A system that includes this.

2. The system according to claim 1, which indexes the collected data and makes it searchable efficiently.

3. The system according to claim 1, which acquires data based on user requests and provides analysis results in real time.

Images