Search Intent Identification via Compatibility Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search engines fail to accurately identify the primary intent behind natural language search queries with multiple intents, leading to irrelevant search results and increased user interaction time.
Innovation Solution
A system that uses an attention mechanism and machine learning models to compute compatibility scores between intention terms and query contexts, determining a primary intention term and generating intent-based search results, while also considering user preferences and features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing search engines use keywords-based search to provide search results, then the search system is simple to implement, but the search results do not accurately reflect the user's primary intent when multiple intents are present
Solution Approach 1:
The patent segments the search query processing into distinct components: identifying multiple intention terms, computing compatibility scores for each term with query context, and selecting the primary intention term. This segmentation allows the system to handle complex natural language queries with multiple intents by breaking them down into manageable analysis steps, thereby improving measurement precision without overwhelming system complexity
Solution Approach 2:
The patent introduces compatibility scores as an intermediary mechanism to evaluate and compare different intention terms against the query context. This intermediary scoring system enables the search engine to objectively determine which intention term best represents the user's primary intent, improving accuracy while maintaining a structured processing approach that doesn't excessively increase system complexity
2Loss of time
If existing search engines display all potential search results without prioritizing by intent, then comprehensive results are provided, but users spend significant time ignoring irrelevant results before finding relevant ones
Solution Approach 1:
The patent performs preliminary action by identifying and selecting the primary intention term before generating search results. By computing compatibility scores and determining which intention term best represents the user's primary intent ahead of time, the system can prioritize and surface the most relevant results first, significantly reducing the time users spend scrolling through irrelevant content
Solution Approach 2:
The patent implements feedback mechanisms where compatibility scores are computed based on the relationship between intention terms and query context. This feedback loop allows the system to continuously refine its understanding of user intent and adjust result prioritization accordingly, ensuring that the most relevant results appear first while maintaining high measurement precision
3Measurement precision
If search engines treat all keywords equally without considering intent weighting, then the processing algorithm is simple, but results include items that do not correspond to the real intent of the searcher
Solution Approach 1:
The patent applies local quality by assigning different compatibility scores to different intention terms based on their specific relationship with the query context. Rather than treating all keywords uniformly, the system evaluates each intention term's compatibility locally with the surrounding context, allowing more precise alignment with the user's real intent while managing complexity through focused local analysis rather than global reprocessing
Data Source
AI summary
This application relates to systems and methods for providing search results based on a primary intent. In some examples, a disclosed system includes a memory resource storing instructions; and one or more processors coupled to the memory resource. The one or more processors are configured to execute the instructions to: receive, from a user, a search query including a plurality of words, identify a plurality of intention terms from the words of the search query, compute, for each of the plurality of intention terms, a compatibility score between the intention term and a query context associated with the intention term, determine, from the plurality of intention terms, a primary intention term having a maximum compatibility score among the plurality of intention terms, and generate, based on the primary intention term, a set of intent-based search results in response to the search query, the set of intent-based search results identifying a set of items associated with the primary intention term.