Query Parsing System for Search Parameter Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional computer-implemented mapping services face challenges in accurately parsing user input text to determine search parameters, leading to suboptimal search results due to premature termination of parse consideration once a matching parse is found.
Innovation Solution
A query parsing system generates multiple candidate parses of user input text, scores them based on predefined parsing features, and selects the most accurate parse using a machine learning model, ensuring comprehensive evaluation and improved accuracy in determining search parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If conventional methods terminate parse consideration once a matching parse is found, then processing speed is improved, but parsing accuracy deteriorates
Solution Approach 1:
The system generates multiple candidate parses in advance before selecting the final parse. Instead of terminating immediately upon finding a match, the system pre-generates several potential parses and evaluates them using a machine learning model to determine the most accurate one, thereby improving parsing accuracy while maintaining reasonable processing efficiency
Solution Approach 2:
The system replaces conventional rule-based or deterministic parse selection mechanisms with a machine learning model. The ML model evaluates multiple candidate parses and selects the most accurate one based on learned patterns, substituting traditional mechanical parsing logic with intelligent decision-making that improves accuracy without proportionally increasing processing time
2Measurement precision
If multiple candidate parses are generated and evaluated, then parsing accuracy is improved, but computational complexity increases
Solution Approach 1:
The system generates multiple candidate parses (excessive action) but evaluates them using an efficient machine learning model that processes candidates in a optimized manner. The ML model can prioritize or rank candidates, allowing the system to evaluate only the most promising parses in detail, thus achieving high accuracy without proportionally increasing computational complexity
Solution Approach 2:
The system changes the parameter of parse evaluation from deterministic rule-based scoring to probabilistic machine learning scoring. This parameter change allows for more nuanced evaluation of multiple candidates, improving accuracy while the ML model's efficient architecture keeps computational complexity manageable through learned feature representations
Data Source
AI summary
An exemplary query parsing system accesses user input text representative of a search query. The system generates a plurality of candidate parses of the user input text. Each of the plurality of candidate parses includes a candidate what portion and a candidate where portion determined from the user input text. The system generates a score for each candidate parse in the plurality of candidate parses based on whether one or more of a plurality of predefined parsing features are found in the respective candidate parse and on a machine learning mode. The system selects, from the plurality of candidate parses based on the scores for the plurality of candidate parses, the candidate what portion and the candidate where portion of a particular candidate parse included in the plurality of candidate parses as search parameters for the search query. Corresponding methods and systems are also disclosed.