Patent Claim Segmentation for Prior Art Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conducting patent searches is challenging due to the difficulty in finding prior art references that disclose entire patent application claims, requiring additional time to search for secondary references and facing limitations in finding relevant prior art.
Innovation Solution
An online wireless worldwide patent search and analytics tool that identifies relevant prior art by breaking down claim limitations, incorporating patent and non-patent literature searching, social networking, and utilizing a blockchain-based patent registry with advanced analytics tools like Q-Score and V-Score, and spam filtering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a patent searcher uses traditional patent search methods to find prior art references, then the search process can identify some relevant references, but it requires additional time to search for secondary references and faces limitations in finding the most relevant prior art
Solution Approach 1:
The system segments a patent claim into multiple claim limitations automatically. Each limitation is then searched independently in patent databases, allowing parallel processing and more comprehensive coverage without requiring manual sequential searching of secondary references.
Solution Approach 2:
The system introduces an intermediary tool (computing device with patent search software) that automatically performs the complex task of breaking down claims, searching for prior art across multiple limitations, and compiling results. This intermediary handles the time-consuming manual work of identifying secondary references.
2Measurement precision
If a patent searcher manually analyzes each claim limitation to find relevant prior art, then the accuracy of prior art identification improves, but the complexity and time required for the search process increases
Solution Approach 1:
The system performs self-service by automatically breaking down patent claims into limitations and conducting independent searches for each limitation without requiring manual intervention. The computing device autonomously manages the entire search process, from claim segmentation to result compilation.
Solution Approach 2:
The system performs preliminary actions by automatically segmenting claims into limitations before the actual prior art search begins. This preprocessing step is executed automatically, reducing the complexity of the subsequent search process while improving accuracy.
3Measurement precision
If traditional patent search methods are used, then the search process can be completed with simple tools, but the ability to find the most relevant prior art is limited
Solution Approach 1:
By segmenting claims into multiple limitations and searching each independently, the system achieves more comprehensive prior art identification. This segmentation allows the system to find relevant prior art that might be missed in traditional holistic searches while maintaining high efficiency through automated parallel processing.
Solution Approach 2:
The system changes the search parameter from treating claims as single units to analyzing individual limitations. This parameter change enables more precise matching with prior art references while the automated process maintains high productivity by handling multiple limitations simultaneously.
Data Source
AI summary
A system and method for a patent search and analytics software tool that finds prior art for each claim limitation/element by breaking up claims into individual claim limitations. Once the claims are separated, the system finds the best prior art for each of the individual separate, different claim limitations/elements. Additionally, the software finds the best prior art for entire claims, including non-patent literature (NPL) searching. The system takes into account the limitations of the claim under consideration (query claim of query patent), the text of the art, the link structure of the citation network, and the patent classification and then constructs a network that consists of two types of nodes: (i) the art (patents and non-patent literature) and the (ii) classes of the patent classification. Each art node is linked to all the art nodes that it cites and is linked to all the classification nodes that it belongs to.