Development of a smart patent recommendation system with natural language processing capabilities

Amy J.C. Trappey*, Charles V. Trappey, Alex H.I. Hsieh

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

Artificial Intelligence (AI) and machine learning are increasingly adopted in diverse areas such as medicine, manufacturing, finance, transportation, retailing, and supply chain management to enhance productional and operational efficiency and smart decision making. This research develops an intelligent patent recommendation system using AI techniques and non-supervised machine learning (M/L) with natural language processing (NLP) for technology mining. Technology e-discovery for specific smart machines and manufacturing systems, such as sensors, controllers, and cyber physical systems (CPS), are used as case examples to demonstrate the prototype patent recommender. The recommendation system, trained for other domains, can be configured as a generic patent recommender. Collaborative filtering and content-based M/L and NLP approaches are adopted to implement the patent recommender with self-learning patent search capabilities. The proposed patent recommender can provide predictions for future research and development, avoiding intellectual property infringement, and provide proactive protection for market advances.

Original languageEnglish
JournalProceedings of International Conference on Computers and Industrial Engineering, CIE
Volume2018-December
StatePublished - 1 Jan 2018
Event48th International Conference on Computers and Industrial Engineering, CIE 2018 - Auckland, New Zealand
Duration: 2 Dec 20185 Dec 2018

Keywords

  • Natural language processing
  • Non-supervised machine learning
  • Recommendation system
  • Smart machinery

Fingerprint Dive into the research topics of 'Development of a smart patent recommendation system with natural language processing capabilities'. Together they form a unique fingerprint.

Cite this