Evidence of Use Search Optimization via Batch Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current evidence of use (EOU) searches are hindered by limitations in computer processing speed and internet connection speed, resulting in slow search times and a high percentage of redundant or irrelevant results, with initial search batches often lacking relevant information, necessitating improved methods to determine when to stop the search.
Innovation Solution
A system and method that utilize a cloud-based network with an API and AI-driven EOU Chaser Module to rank documents based on customized criteria, including an EOU Chaser Module for tracking and updating evidence of use, a Scoring Module for applying scoring rules, and a Page Ranking Database to sort results, allowing for optimized search termination and result presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a comprehensive search returns a large volume of data to ensure coverage, then the completeness of results is improved, but the processing time and resource consumption increase significantly
Solution Approach 1:
The patent segments the large volume of search results into batches and processes them in parallel using multiple computing resources. The search results are divided into manageable chunks that can be scanned simultaneously, reducing overall processing time while maintaining comprehensive coverage of all results.
Solution Approach 2:
The patent performs preliminary filtering and ranking of search results before the full scan. By pre-processing the data to identify and prioritize potentially relevant documents, the system reduces the amount of data that requires intensive processing, thereby decreasing total search time while preserving completeness.
2Reliability
If the search scans many documents to ensure all relevant information is found, then the completeness of evidence is improved, but the resource waste increases due to repetitive and irrelevant results
Solution Approach 1:
The patent applies preliminary filtering using relevance scoring and duplicate detection algorithms before the full evidence scan. This pre-processing step identifies and eliminates repetitive and clearly irrelevant documents, allowing the system to focus computational resources only on documents that have potential evidentiary value.
Solution Approach 2:
The patent applies different processing strategies to different portions of the search results based on their relevance score. High-scoring documents receive full detailed analysis, while low-scoring documents receive minimal processing or are discarded, optimizing resource allocation according to the local quality or potential value of each document.
3Reliability
If the search processes all batches of results to ensure no relevant information is missed, then the completeness is improved, but the time required increases due to initial batches having lower relevance
Solution Approach 1:
The patent performs preliminary ranking and relevance assessment of all search batches before conducting the full evidence analysis. By pre-identifying and prioritizing batches with higher relevance scores, the system can focus intensive processing on the most promising batches while applying lighter processing to lower-priority batches, reducing total search time while maintaining completeness.
Solution Approach 2:
The patent segments the search batches into priority groups based on relevance scoring and processes them in parallel according to their priority level. High-priority batches are processed with full detail while low-priority batches receive reduced processing, allowing the system to maintain completeness information while significantly reducing the time spent on low-value batches.
Data Source
AI summary
A method of optimizing an EOU search by increasing the number of sources searched by a predetermined variable and notifying the user of the optimal search results. For example, the EOU tool may search 5-20 pages in 5 page increments and compare the results of the various searches to determine which one provides the best results. Based on the results of the searches the EOU tool can send a notification to the user such as “increasing the search results by 10 pages will improve EOU results”.