Machine Learning Data Extraction from Fragmented Sources
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often have fragmented data stored across multiple entities, leading to a lack of a comprehensive view of their data and associated requirements, which existing technologies fail to effectively capture and process.
Innovation Solution
A system and method that uses machine learning to generate a display for receiving fragmented data, extracts and categorizes data entries, and generates recommendations for products or services based on determined data categories, employing algorithms like Support Vector Machines for data processing and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data is stored across multiple entities, then data storage capacity increases, but data fragmentation occurs and comprehensive view is lost
Solution Approach 1:
The patent introduces a data consolidation system that acts as an intermediary between multiple data storage entities. This system collects fragmented data from various sources, processes it through machine learning algorithms to identify patterns and relationships, and reconstructs a comprehensive unified view of user data, thereby preventing information loss while maintaining distributed storage benefits
Solution Approach 2:
The patent merges fragmented data from multiple entities into a unified data structure. By combining data from different sources and using machine learning to integrate information across entities, the system creates a comprehensive view that preserves all original data while adding contextual relationships that were lost in fragmentation
2Measurement precision
If machine learning algorithms are used for data processing, then data analysis accuracy improves, but processing complexity increases
Solution Approach 1:
The patent segments the complex machine learning processing into distinct modular stages: data collection from fragmented sources, data preprocessing and cleaning, feature extraction, model training, and result generation. Each stage handles a specific aspect of the processing pipeline, making the overall complex system more manageable and maintainable while preserving high analysis accuracy
Data Source
AI summary
One or more aspects of the disclosure generally relate to computing devices, computing systems, and computer software that may be used for capturing and extracting fragmented data and for data processing using machine learning. Some aspects disclosed herein are directed to, for example, a system and method comprising generating a display for receiving fragmented data associated with a user. The method may comprise sending, to a user device associated with the user, the display for receiving fragmented data. A computing device may receive, from the user device and via the display for receiving fragmented data, first fragmented data associated with the user. The computing device may extract a plurality of data entries from the first fragmented data. A request for data associated with a first data entry of the plurality of data entries may be sent to the user device. The computing device may determine a data category for each data entry of the plurality of data entries. Based on the determined data category for each data entry of the plurality of data entries, the method may comprise determining one or more of a number of entries in each data category or an amount associated with each data category.