Document Search Relevance Indexing via Association Dictionary
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing document search methods are inefficient as they do not account for the varying relevance of different parts of a document and lack consideration of associated words, synonyms, hyponym/hypernym, and meronym/holonym relationships, leading to suboptimal search results.
Innovation Solution
A computer-implemented method that uses an association dictionary and parsing techniques to generate relevance values for documents by considering the occurrences of search terms and their associated words, allowing for a more precise and efficient search by providing summaries and calculating relevance values based on document content and structure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If a simple index is used for all documents, then the search speed is improved, but the search precision deteriorates because all documents are treated equally without relevance ratings
Solution Approach 1:
The patent applies local quality by creating different types of indexes for different parts of the document collection. Specifically, it creates a simple index for all documents to enable fast searching, while simultaneously creating a relevance index for selected documents to provide precise relevance ratings. This allows the system to use the appropriate index type depending on the specific search needs, thereby maintaining both speed and precision.
2Measurement precision
If a relevance index is created for all documents, then the search precision is improved by rating document relevance, but the device complexity and processing time increase
Solution Approach 1:
The patent segments the document collection into different groups: documents that receive full relevance indexing and those that use simple indexing. The relevance index is selectively applied to documents where detailed relevance analysis is most beneficial, while other documents rely on the simpler index structure. This segmentation reduces overall system complexity while maintaining high precision where needed.
Solution Approach 2:
Instead of applying full relevance indexing to all documents, the patent applies partial action by creating relevance indexes only for a subset of documents. This partial indexing approach provides sufficient relevance precision for the most important documents while avoiding the excessive processing complexity that would result from indexing every document in the collection.
3Ease of manufacture
If traditional word occurrence averaging is used, then the calculation simplicity is maintained, but the search depth and result quality deteriorate due to lack of associated word consideration
Solution Approach 1:
The patent introduces an association dictionary as an intermediary component that stores relationships between words (synonyms, hyponyms, meronyms). During search operations, this dictionary acts as a mediator that expands the search beyond exact word matches to include semantically related terms. This allows the system to maintain relatively simple calculation processes while significantly improving search depth by considering associated words without losing the simplicity advantage of traditional methods.
Data Source
AI summary
Techniques are disclosed for searching a set of documents using search terms. In one embodiment, a summary is provided for each document in the set. Search terms are received, and the set of documents are parsed using the received search terms. A first relevance value is calculated using only the summary of each document. A subset of documents having the highest relevance is provided by using the first relevance value. The subset of documents is parsed using the received search terms, to calculate a second relevance value for each document using the respective document. Query results are provided, the query results including documents having the highest relevance according to the second relevance value.