RENU 's repositories
Patent_Sentiment_Analysis
Patent Sentiment Analysis is a process of highlighting patent paragraphs (advantages, problems and neutral text) to ease examination process and also to assist patent attorneys in handling litigation and infringement cases during patent analysis.
uspto-patent-data-parser
A python tool for reading, parsing and finding patent using the United States Patent and Trademark (USPTO) Bulk Data Storage System.
expaai_model
Model for EXPAAI - Explainable Patent Analysis using Artificial Intelligence
expaai_model_api
API for the EXPAAI AI Model
Query_formedness_PQAI
Recent research in applying deep learning to the problem of prior-art searching has enabled development of easy-to-use prior-art search engines that accept natural language search queries and provide improved search performance. However, as opposed to the conventional keyword-based techniques where the results are readily explained by the presence of queried keywords, deep-learning based techniques act like a black box. As a result, it is difficult for users to understand how to articulate their information need as a high-quality search query to obtain optimal results. In this paper we share insights on this problem from extensive experimentation with PQAI, an open source deep learning based prior-art search engine. We study the effects of various query parameters such as verbosity, grammar, and specificity on the search results and show that ill-formed queries containing grammatical errors, non-essential content, and broad terminology adversely affect relevance of search results. We also develop and benchmark a number of machine learning models, viz. Grammatical Error Detection Model (GEDM), Query Specificity Model (QSM), and Query Verbosity Model (QVM), to identify and mitigate commonly encountered issues with ill-formed queries.