Hierarchical Data Search Scoring via Combined Similarity and Context
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems face challenges in effectively scoring and retrieving results from multidimensional hierarchical data sets using natural language queries, as they struggle to accurately combine similarity and contextual scores, leading to suboptimal search outcomes.
Innovation Solution
A computer-implemented method that receives a search label, determines similarity and contextual scores between the label and node labels in a hierarchical data source, combines these scores, and returns results ordered by a combined score, utilizing techniques like Levenshtein distance for text comparisons and graph distance for contextual awareness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing systems use natural language queries to search hierarchical data sets, then search functionality is provided, but the accuracy and relevance of search results deteriorate due to inability to effectively combine similarity and contextual scores
Solution Approach 1:
The patent segments the search scoring process into two distinct components: similarity scoring (comparing search label with node labels using Levenshtein distance) and contextual scoring (determining graph distance from context node). This segmentation allows each component to be optimized independently while maintaining overall system manageability.
Solution Approach 2:
The patent merges the similarity score and contextual score into a unified ranking mechanism. Both scores are calculated for each candidate node and combined to produce a final ranking, enabling the system to leverage both text similarity and hierarchical context for improved search result accuracy.
2Reliability
If existing systems retrieve results from hierarchical data sets, then search functionality is provided, but the relevance of results deteriorates due to suboptimal combination of similarity and contextual information
Solution Approach 1:
The patent performs preliminary actions by pre-calculating and storing the hierarchical structure and context node relationships before the actual search query is executed. During query processing, the system leverages these pre-computed structures to quickly determine graph distances and combine scores, improving processing efficiency while maintaining result relevance.
Solution Approach 2:
The patent introduces an intermediary scoring mechanism that acts as a mediator between the raw search input and the final result ranking. The dual-score system (similarity + contextual) serves as an intermediary layer that processes and reconciles multiple factors before producing the final ranked results, ensuring both relevance and efficiency.
Data Source
AI summary
A computer-implemented method includes receiving a search label and accessing a hierarchical data source comprising a plurality of nodes. One node may be a context node. The method further includes determining a similarity score between the search label and a node label of each node, determining a contextual score between the context node and each node, combining, for each node, the similarity score with the contextual score to yield a combined score, and returning a result. The result may be based on ordering the plurality of nodes according to each node's combined score. A corresponding computer program product and computer system are also disclosed.