Query Refinement via Grammar Parsing and Knowledge Base Validation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search systems often fail to identify desired items when users input incomplete or descriptive queries, leading to mixed results and lack of meaningful assistance in refining searches.
Innovation Solution
A query processing system (QPS) that interprets user input using rule modules and a structured knowledge base to generate synthetic query suggestions, providing refinement options and preview items, ensuring meaningful search results by leveraging query-expression grammars and information items from the knowledge base.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the search system generates query suggestions based on similar queries and dictionary resources, then the user receives assistance in refining the search, but the suggestions may not guarantee meaningful search results
Solution Approach 1:
The patent introduces an intermediary component that acts as a bridge between the user's natural language query and the search system. This intermediary parses the query using grammar rules, identifies entities and attributes, validates them against a knowledge base, and generates structured synthetic queries. This intermediary layer ensures that query suggestions are both user-friendly and guaranteed to produce meaningful results by leveraging the structured knowledge base.
Solution Approach 2:
The system performs preliminary actions by pre-processing and validating query components against the knowledge base before generating suggestions. The grammar parser and entity validator prepare the query structure in advance, ensuring that only queries with guaranteed meaningful results are presented to the user. This preliminary validation prevents wasting user time on suggestions that would yield no results.
2Productivity
If the search system provides generic query suggestions, then the user receives quick suggestions, but the suggestions may not be contextually relevant or grammatically natural
Solution Approach 1:
The system changes parameters by transforming unstructured natural language queries into structured synthetic queries with specific grammatical patterns. The grammar parser applies rules that enforce proper syntax and structure, while the knowledge base provides contextually relevant entities and attributes. This transformation maintains naturalness by using learned query patterns while ensuring grammatical correctness and contextual relevance.
3Adaptability or versatility
If the search system accepts incomplete or descriptive user queries, then the user can search with limited knowledge, but the system may fail to identify the desired item
Solution Approach 1:
The intermediary component parses incomplete or descriptive queries using grammar rules and fills in missing information by querying the knowledge base. When users provide partial information, the system identifies the intended entities and attributes, validates them against the knowledge base structure, and completes the query with accurate information from the knowledge base, thereby maintaining both flexibility and precision.
Solution Approach 2:
The system uses feedback from the knowledge base validation process to improve query accuracy. When a user's incomplete query is parsed, the system checks the identified entities and attributes against the knowledge base, receives feedback on what information is missing or incorrect, and automatically corrects or completes the query to ensure accurate search results.
Data Source
AI summary
A query processing system (QPS) for generating query suggestions to a user by matching the user's input query against a set of query-detection grammars defined by respective rule modules, and with respect to a structured knowledge base. In response to the matching operation, the QPS may generate a set of synthetic query suggestions to the user, representing refinements of the user's input query. The QPS can also present a refinement tool that conveys refinement options to the user. The QPS may also present one or more preview items to the user upon the user's selection of one of the synthetic query suggestions. Each synthetic query suggestion and each preview item is guaranteed to having a matching counterpart information item in the structured knowledge base.