App Search Query Expansion via Related Indicator Terms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face challenges in finding relevant software applications due to the limitations of textual-based search queries, which often return irrelevant results as users are forced to express complex concepts with a finite number of words, leading to frustration and inefficiency.
Innovation Solution
The system identifies related indicator terms by analyzing user interactions and document associations, using a data structure to expand search queries and rank results based on relevance, ensuring that apps with high relatedness metrics are prioritized in search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users enter search queries with limited words to capture complex concepts, then the search interface remains simple and responsive, but the search results become irrelevant and inaccurate
Solution Approach 1:
The patent introduces an intermediary mechanism that automatically expands user queries by identifying and incorporating related terms from app metadata. The system acts as a mediator between the user's limited query words and the comprehensive app descriptions, using related term detection algorithms to bridge the gap and improve search accuracy without requiring users to enter more words.
Solution Approach 2:
The system performs preliminary analysis of app metadata, titles, and descriptions to pre-identify related terms before the actual search occurs. By analyzing the relationship between query terms and potential related terms in advance, the system prepares an expanded search query that accurately represents the user's intent, ensuring high-precision results without increasing user input burden.
2Quantity of substance
If the system returns all apps containing query terms, then the search coverage is comprehensive, but the search quality deteriorates with many irrelevant results
Solution Approach 1:
The patent applies local quality by differentiating the treatment of different terms within app metadata. Instead of uniformly weighting all query terms equally, the system identifies which terms are most relevant to the user's intent and prioritizes those in the search matching process. Related terms are weighted differently based on their semantic proximity to the query, ensuring high-relevance results while maintaining comprehensive coverage.
Solution Approach 2:
The system changes the search parameter from simple keyword matching to a multi-dimensional matching approach that incorporates term relatedness scores, metadata weightings, and semantic relationships. By transforming the search algorithm to consider these additional parameters, the system maintains comprehensive search coverage while significantly improving result relevance and filtering out irrelevant apps.
3Productivity
If the system uses traditional textual search only, then the implementation is simple and fast, but it cannot capture the full intent of complex concepts
Solution Approach 1:
The patent segments the search process into distinct phases: query term extraction, related term identification, and expanded query construction. By breaking down the complex search intent into manageable segments and processing them sequentially, the system maintains fast processing speeds while accurately capturing complex concepts through multi-stage analysis of app metadata and term relationships.
Solution Approach 2:
The system adds another dimension to traditional textual search by incorporating semantic relatedness and metadata analysis alongside keyword matching. This dimensional expansion allows the search to operate in a multi-dimensional space that captures both literal query terms and implied related concepts, improving intent accuracy without significantly impacting processing speed through optimized algorithms.
Data Source
AI summary
A set of potential search-query terms can be identified based on empirical queries for apps. For each potential search-query term, a subset of documents within a set of documents can be identified based on apps that users were likely to click on or download following entry of a search query with a comparable or same term. One or more other indicator terms can be identified as being related to the potential search-query term based on the one or more second indicator terms being prevalent within the subset of documents. Upon receipt of a subsequent search query, a search can then be performed using both a term within the search query and one or more related other indicator terms.