Analogy Identification System for Reducing Search Time
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for finding and utilizing analogies in learning are inefficient, as they require extensive searching through numerous web pages, often resulting in unfamiliar or irrelevant information, wasting time and effort.
Innovation Solution
A system and method that identifies and characterizes analogies in documents by classifying candidate documents based on region size and linguistic marker count, extracting source concepts, and providing metadata on familiarity, length, and readability to facilitate effective explanation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a general purpose search engine is used to find analogies, then the search can cover a large number of pages, but the learner must read each page to find the analogy, resulting in substantial time wastage
Solution Approach 1:
The patent extracts the region of interest containing the analogy from the entire document, separating the useful information (the analogy itself) from the unnecessary content. This allows the system to present only the relevant analogy to the learner without requiring them to read through thousands of pages, directly resolving the time wastage problem while maintaining comprehensive search coverage.
Solution Approach 2:
The patent introduces an intermediary system (the analogy identification system) that acts as a mediator between the search engine and the learner. This intermediary automatically identifies, extracts, and characterizes analogies from search results, filtering out irrelevant content before presenting it to the learner. This resolves the contradiction by maintaining large-scale search capability while eliminating the need for manual page reading.
2Reliability
If the analogy obtained from Internet search is unfamiliar to the learner, then the learner may have to repeat the search multiple times, but this requires reading each page again, wasting more time
Solution Approach 1:
The patent changes the parameters of the analogy by characterizing it with metadata including familiarity level, length, and readability. This allows the system to select and present analogies that match the learner's specific needs and familiarity level, ensuring the first search attempt provides a suitable analogy rather than requiring repeated searches. The metadata parameters enable precise matching between learner requirements and analogy characteristics.
3Ease of operation
If the analogy is not readily available as a single resource, then the learner must search extensively, but this increases the complexity of the search process
Solution Approach 1:
The patent merges multiple functions into a single integrated system: search execution, analogy identification, region of interest extraction, and metadata characterization all occur within one unified process. This consolidates the scattered search process into a single resource that readily provides the analogy with all necessary context and metadata, eliminating the need for learners to navigate complex multi-step search procedures manually.
Data Source
AI summary
Disclosed is a method and system for identifying and characterizing an analogy in a document. In one implementation, the method comprises identifying a candidate document. The candidate document comprises an analogy for a target concept, a region of interest and a linguistic marker included in the region of interest. Further, the method comprises classifying the candidate document as an analogy document or a non-analogy document based upon a size of a region of interest and a count of linguistic marker. Furthermore, the method comprises identifying a source concept from the analogy document. Subsequently, the method comprises characterizing the source concept with corresponding metadata. The metadata comprises a familiarity of the source concept, a length of the source concept, and a readability of the source concept.