Pharmaceutical Mixer Control Using Similar Clinical Trial Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Clinical trial data management using paper media faces challenges with data storage, security, limited data sharing, and variability in review periods, making it difficult to utilize and follow up on clinical trial data effectively.
Innovation Solution
A method and device utilizing a similar clinical trial data provision server that preprocesses clinical trial data, generates vectors using metadata or tokenized words, and uses a pretrained learning model to measure similarity grades, extracting and providing clinical trial data that matches user input data, with specific applications for structured and unstructured data types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If paper media-based clinical trial data management is used, then data storage and security become manageable with traditional methods, but data sharing and reprocessing capabilities are extremely limited
Solution Approach 1:
The patent replaces the mechanical paper-based data management system with an electronic data processing system that uses computers and networks. This substitution enables advanced data sharing and reprocessing capabilities while maintaining security through electronic access controls and encryption, directly resolving the contradiction between security and adaptability.
Solution Approach 2:
The patent creates multiple digital copies of clinical trial data that can be simultaneously accessed and shared across different systems and locations without compromising the original data's security. The electronic copying mechanism allows unlimited distribution of data while the source system maintains secure control, resolving the limitation of data sharing in paper-based systems.
2Ease of manufacture
If paper media-based clinical trial data management is used, then data storage is straightforward, but data reprocessing and follow-up reference utilization are extremely limited
Solution Approach 1:
The patent replaces manual paper-based data storage and retrieval with automated electronic data processing systems. This enables efficient data reprocessing through computer algorithms and automated analysis tools, dramatically improving productivity while maintaining organized storage through electronic database structures.
Solution Approach 2:
The patent implements preliminary data processing and structuring in electronic format, preparing data for future reprocessing and analysis. By organizing data electronically with standardized formats and metadata from the outset, the system enables rapid reprocessing and follow-up reference utilization without the limitations of paper-based methods.
3Reliability
If conventional electronic CRF systems are used, then data storage and security are improved, but data sharing and reprocessing capabilities remain limited
Solution Approach 1:
The patent creates a universal electronic data platform that performs multiple functions including secure storage, advanced sharing capabilities, reprocessing, and analysis. This multi-functional system simultaneously provides security through encryption and access controls while enabling broad data sharing and reprocessing through standardized electronic interfaces and network connectivity.
Solution Approach 2:
The patent introduces an electronic data processing system as an intermediary between data storage and data sharing functions. This intermediary layer provides secure electronic storage while simultaneously enabling controlled sharing and reprocessing through software-based access management, resolving the contradiction present in conventional eCRF systems.
Data Source
AI summary
An apparatus and a method for controlling a pharmaceutical mixer based on similar clinical trial data extracted by machine learnings. The method may include: training a learning model; when clinical trial data is received from a user terminal, determining a type of the clinical trial data; generating a vector using each piece of metadata of the clinical trial data; generating a vector by tokenizing words extracted from the clinical trial data according to the type of the clinical trial data; inputting the vector to the pretrained learning model and calculating a distance between a prestored vector in the learning model and the vector; measuring a similarity grade; extracting clinical trial data having a predetermined similarity grade; and transmitting a control signal to the pharmaceutical mixer based on the extracted clinical trial data.