Weighted Section Search Profiles for Patent Document Retrieval
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing electronic intellectual property document search tools do not effectively support different classes of searches, such as novelty, product clearance, and invalidity searches, as they fail to leverage the various sections of intellectual property documents efficiently, leading to increased burdens on searchers due to the growing number of documents in databases.
Innovation Solution
A method and system that compile and index patent documents into multiple sections, allowing for the creation of search profiles with weighted sections, where a relevancy score is computed for each document based on query data, and results are dynamically ranked and limited to provide accurate and relevant search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional electronic search tools are used to search patent documents, then the search can be conducted electronically, but the searcher must manually review all sections of all documents, leading to increased burden and time consumption as database size grows
Solution Approach 1:
The patent divides patent documents into multiple sections (e.g., abstract, claims, description, drawings) and creates different search profiles that emphasize different sections based on the search objective. This segmentation allows searchers to focus only on relevant sections rather than reviewing entire documents, significantly reducing review time and improving search efficiency.
Solution Approach 2:
The system assigns different weights to different sections of patent documents based on the search profile being used. For example, a novelty search might weight the abstract and claims more heavily, while an invalidity search might weight the detailed description more. This local quality approach ensures that each section is evaluated according to its relevance for the specific search type, reducing unnecessary review time.
2Reliability
If all sections of patent documents are reviewed equally, then comprehensive search coverage is achieved, but the search results include irrelevant documents, reducing accuracy
Solution Approach 1:
The patent implements search profiles that assign different weights to different sections of patent documents based on the specific search objective. For example, for novelty searches, the abstract and claims sections are weighted more heavily, while for invalidity searches, the detailed description receives higher weight. This differential weighting improves search result accuracy by emphasizing sections most relevant to each search type while maintaining comprehensive coverage where needed.
Solution Approach 2:
The system changes the evaluation parameters (weights) for different document sections based on the search profile selected. By dynamically adjusting the importance of different sections according to the search objective, the system achieves both comprehensive coverage and high accuracy, returning only the most relevant documents for each specific search type.
3Quantity of substance
If the database of patent documents grows, then more prior art is available for search, but the burden on searchers increases due to the larger number of documents to review
Solution Approach 1:
The patent segments patent documents into distinct sections and creates specialized search profiles that focus on specific sections based on search objectives. This segmentation allows the system to efficiently handle large databases by directing searchers' attention only to relevant sections of relevant documents, making the increasing volume of patent literature manageable despite the growing database size.
Solution Approach 2:
The system extracts and emphasizes only the most relevant sections of patent documents based on the search profile being used. By taking out and prioritizing specific sections (such as abstracts for novelty searches or claims for infringement searches), the system reduces the effective search space and minimizes searcher burden even as the overall database grows.
4Adaptability or versatility
If traditional search tools are used without section-based profiles, then the system is simple to implement, but it cannot support different classes of searches (novelty, product clearance, invalidity)
Solution Approach 1:
The patent creates a universal search system with multiple search profiles that can handle different classes of searches (novelty, product clearance, invalidity, etc.) through a single integrated platform. Each profile is configured with specific section weights appropriate for its search type, allowing the system to adapt to various search objectives without requiring separate tools, thereby achieving versatility with manageable complexity.
Data Source
AI summary
A method, system, and article are provided for efficiently and effectively searching an electronic document collection. Each of the documents in the collection is pre-divided into sub-sections. One or more profiles are created, each including a selection of at least one of the sections of the documents in the collection. In addition, a weight is assigned to each of the selected sections in the profile. Based upon the parameters of a query and selection of a profile, select sub-sections of each document are employed to compare query data to the underlying document collection. A compilation of documents is created with data matching the query data, and a relevancy score is computed for each document in the compilation. The relevancy score is then leveraged to sort the documents in a manner to convey relevancy to the query submission.