LLM Claim Charting for Relevant Product and Entity Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing patent analysis systems face challenges in accurately and efficiently identifying relevant entities and products, particularly in the manual processing of textual and visual data, leading to time-consuming and inaccurate results, with a lack of automated solutions for comprehensive claim-element-to-product mapping.
Innovation Solution
An automated system utilizing a pre-trained large language model (LLM) and advanced internet search modules for extracting, analyzing, and mapping textual and visual data, including a retrieval augmented generation (RAG) module for enhanced patent data analysis, generating claim chart tables, and providing quantitative scoring for prioritized results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual processes are used for patent analysis and product identification, then accuracy can be maintained through human judgment, but the process becomes time-consuming and inefficient
Solution Approach 1:
The patent replaces manual mechanical analysis processes with an automated system comprising web mining units, RAG modules, and claim chart generation modules. These components automatically extract patent information, perform internet searches, retrieve relevant data, and generate structured claim charts without human intervention, thereby dramatically increasing analysis speed while maintaining accuracy through systematic automated procedures
Solution Approach 2:
The system enables self-service automation where the patent analysis process executes autonomously through pre-configured modules. The web mining unit automatically crawls specified URLs, the RAG module autonomously retrieves and processes information, and the claim chart generator automatically produces results without requiring continuous human operation or manual data collection
2Measurement precision
If comprehensive patent analysis is performed manually to ensure accuracy, then detailed insights can be obtained, but the complexity and time required increase significantly
Solution Approach 1:
The patent divides the complex patent analysis task into distinct functional modules: a web mining unit for data collection, a RAG module for information retrieval and processing, and a claim chart generation module for structured output. Each module handles a specific aspect of the analysis, reducing overall system complexity through functional decomposition while maintaining comprehensive analysis capabilities
Solution Approach 2:
The RAG module serves as an intermediary between the web mining unit and the claim chart generation module. It retrieves relevant information from internet sources, processes the data, and prepares it for structured presentation, thereby simplifying the interaction between data collection and analysis components while ensuring accurate information flow
3Productivity
If automated systems are implemented for patent analysis, then efficiency improves, but accuracy and comprehensiveness of results may be compromised
Solution Approach 1:
The system incorporates feedback mechanisms where the RAG module continuously retrieves information from internet sources based on patent parameters, validates the retrieved data against the patent information, and adjusts the analysis process accordingly. This iterative feedback loop ensures that automated analysis maintains high accuracy by verifying results against multiple data sources and refining outputs based on retrieved information
Data Source
AI summary
The present disclosure relates to a system and a method for determining relevant entities and products using an LLM model. A patent information extraction unit extracts patent related information. A large language model (LLM) unit analyzes the extracted claims for identifying top companies, startups, and products, forming a first list. A background collection module employs the LLM units along with advanced searching unit to generate a second list of relevant entities and products. A result combiner unit generates a list of relevant entities and products. A web mining unit search for relevant hyperlinks disclosing features of the identified products. A RAG module embeds background text extracted from identified hyperlinks. A claim chart module generates a claim chart table for each of the identified products. A ranking module ranks the patent via a weightage-based score and a report generation unit prepares a summarized report comprising an image-report and a textual-report.