Query Intent Identification via Natural Language Parsing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional software products require users to submit queries in concise technical terms to locate available functionality, which can be unfamiliar to users who prefer natural language expressions, leading to a gap between user intent and actual software functions.
Innovation Solution
A method that repeatedly parses and merges natural language queries into defined terms based on predetermined naming conventions, identifying clusters of previous search terms to create intent-based cluster information, allowing for accurate identification of user intent and retrieval of relevant software functionality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users are required to enter queries in concise technical terms to match pre-defined function descriptions, then the precision of matching between query and function is improved, but the ease of operation deteriorates because users are not familiar with internal naming conventions
Solution Approach 1:
The patent introduces a query processing service as an intermediary between the user's natural language query and the software product's internal function descriptions. This service automatically parses, normalizes, and translates user queries into terms that match the pre-defined function descriptions, eliminating the need for users to learn internal naming conventions while maintaining accurate matching.
Solution Approach 2:
The query processing service performs self-service by automatically analyzing and transforming queries without requiring user intervention or knowledge of the transformation rules. The service independently handles spelling corrections, synonym replacements, and grammatical variations to match queries with appropriate functions.
2Device complexity
If the help tool uses a small group of predefined terms to describe software functions, then the device complexity is reduced, but the adaptability deteriorates because it cannot account for the large variety of natural language expressions users may employ
Solution Approach 1:
The patent implements a dynamic query processing approach that adapts to different natural language expressions while maintaining a relatively simple predefined term set. The system dynamically adjusts by applying multiple transformation rules (spelling corrections, synonym replacements, grammatical variations) to map diverse user inputs to the standardized function descriptions, achieving high adaptability without proportionally increasing system complexity.
Solution Approach 2:
The query processing service changes parameters of the input query (spelling, wording, grammar, case) to transform it into a form that matches the predefined function descriptions. This allows the system to handle a wide variety of natural language expressions using a relatively small set of predefined terms.
3Productivity
If the help tool employs complex algorithms to infer relevant functionality from user phrases, then the productivity is improved by providing accurate results, but the device complexity increases making the system harder to implement and maintain
Solution Approach 1:
The patent segments the query processing into multiple distinct, manageable steps: spelling correction, synonym replacement, grammatical variation handling, and function matching. Each step is implemented as a separate rule set that can be independently developed, tested, and maintained, reducing overall system complexity while achieving accurate results through the cumulative effect of multiple specialized processing stages.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Technologies are described herein for identifying query intent from a raw query. A method for identifying intent may include repeatedly separating and merging terms of a natural language expression based on a set of rule-based transpositions of natural language terms into one or more defined terms based on predetermined naming conventions for at least one software function. Thereafter, a cluster of previous search terms related to the defined terms may be identified, and the natural language expression may be associated with the identified cluster to create intent-based cluster information.