Document Search Apparatus Intent Estimation Query Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current document search methods using natural language sentences often return undesired results due to incorrect interpretation of query words, failing to accurately match the user's intended search intention.
Innovation Solution
A document search apparatus that includes an acquisition unit, morphological analysis unit, query word extraction unit, intention estimation unit, query generator, and search unit, which acquires and processes user input to estimate search intentions and generate queries that accurately match the user's intended search criteria by utilizing a search expression list and additional query word list.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If all documents are searched with the query word extracted from the input sentence, then the search coverage is improved, but the search precision deteriorates due to inclusion of undesired documents
Solution Approach 1:
The patent segments the query word into multiple candidate words by extracting different forms (e.g., base form, inflected forms, synonyms) from the input sentence. Instead of using a single query word to search all documents, the system divides the search into multiple targeted searches using segmented word candidates, thereby improving precision while maintaining coverage.
Solution Approach 2:
The patent applies local quality by searching for documents containing specific candidate words in specific contexts. The system identifies local patterns in the input sentence (such as word order, grammatical structure, or semantic relationships) and uses these to guide the search, ensuring that only documents with relevant local characteristics are returned.
2Device complexity
If a simple query word extraction method is used, then the processing complexity is reduced, but the search intention accuracy deteriorates
Solution Approach 1:
The patent performs preliminary action by pre-processing the input sentence to extract multiple candidate words before the actual search begins. The system analyzes the sentence structure, identifies potential query words, and prepares a list of candidate words in advance. This preliminary preparation enables more accurate search intention matching without adding complexity during the search execution phase.
Solution Approach 2:
The patent introduces an intermediary layer between the input sentence and the search query. Instead of directly converting the sentence to a single query word, the system uses an intermediary processing stage that generates multiple candidate words and selects the most appropriate one based on contextual analysis. This intermediary step improves accuracy while keeping the overall process simple.
Data Source
AI summary
According to one embodiment, a document search apparatus includes the following elements. The query word extraction unit extracts, from an input sentence, a word for use in a search as a query word. The intention estimation unit estimates a search intention based on the input sentence. The query generator acquires, from a search expression list, a search expression corresponding to the estimated search intention, acquires, from an additional query word list, an additional query word corresponding to a set of the acquired search expression and the extracted query word, and generates a query based on the extracted query word, the acquired additional query word, and the acquired search expression. The search unit searches for a document that matches the query.