Search Clustering Using Suffix Tree and Multi-Factor Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search algorithms face inefficiencies in generating accurate and timely search results due to suboptimal data structure organization, leading to increased time and noise in search processes.
Innovation Solution
Implementing a Suffix Tree Clustering (STC) algorithm that builds a searchable data structure with clusters based on relevancy weighting, seller factors, price factors, category factors, and image factors, using a trie or hash table data structure for near constant-time search performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional search algorithms are used with conventional data structures, then the search process is simpler to implement, but the search time increases and accuracy decreases
Solution Approach 1:
The patent segments the search data into multiple clusters organized in a tree structure, where each node represents a cluster of related items. This segmentation allows the search algorithm to navigate through hierarchical groups rather than scanning all items linearly, significantly reducing search time while managing complexity through structured organization.
Solution Approach 2:
The patent introduces a hierarchical dimensional structure to the data organization, transforming a flat one-dimensional list into a multi-dimensional tree structure with multiple levels of clustering. This dimensional change enables faster navigation and retrieval by allowing jumps between hierarchical levels rather than sequential scanning.
2Measurement precision
If multi-factor clustering is implemented to improve search accuracy, then recall improves, but the complexity of the search algorithm increases
Solution Approach 1:
The patent changes the parameters used for clustering by incorporating multiple factors (relevancy weighting, seller factors, price factors, category factors, image factors) instead of relying on a single criterion. This multi-parameter approach improves search accuracy and recall by considering diverse aspects of item similarity, while the hierarchical tree structure manages the computational complexity of evaluating multiple factors.
Data Source
AI summary
In one example embodiment, a method is illustrated as including retrieving item data from a plurality of listings, the item data filtered from noise data, constructing at least one base cluster having at least one document with common item data stored in a suffix ordering, compacting the at least one base cluster to create a compacted cluster representation having a reduced duplicate suffix ordering amongst the clusters, and merging the compacted cluster representation to generate a merged cluster, the merging based upon a first overlap value applied to the at least one document with common item data.