Artificial intelligence for patent prior art searching

Abstract This study explored how artificial intelligence (AI) could assist patent examiners as part of the prior art search process. The proof-of-concept allowed experimentation with different AI techniques to suggest search terms, retrieve most relevant documents, rank them and visualise their content. The study suggested that AI is less effective in formulating search queries but can reduce the time and cost of the process of sifting through a large number of patents. The study highlighted the importance of the humanin-the-loop approach and the need for better tools for human-centred decision and performance support in prior art searching.

[1]  Andreas Rauber,et al.  Improving Retrievability of Patents in Prior-Art Search , 2010, ECIR.

[2]  Suzan Verberne,et al.  Genre and domain in patent texts , 2010, PaIR '10.

[3]  Clinton Gormley,et al.  Elasticsearch: The Definitive Guide , 2015 .

[4]  Ye Jin,et al.  User Interface for Managing and Refining Related Patent Terms , 2018, HCI.

[5]  Allan Hanbury,et al.  The Portability of Three Types of Text Mining Techniques into the Patent Text Genre , 2017 .

[6]  Ian Ruthven,et al.  Evaluating Real Patent Retrieval Effectiveness , 2011, Current Challenges in Patent Information Retrieval.

[7]  Anand Kumar,et al.  Text mining and ontologies in biomedicine: Making sense of raw text , 2005, Briefings Bioinform..

[8]  Goran Nenadic,et al.  Clinical Text Data in Machine Learning: Systematic Review , 2020, JMIR medical informatics.

[9]  Padmini Srinivasan,et al.  Using Classification Code Hierarchies for Patent Prior Art Searches , 2011, Current Challenges in Patent Information Retrieval.

[10]  Dominique Andlauer.  Automatic Pre-Search: An overview , 2018 .

[11]  M. Ashburner,et al.  The OBO Foundry: coordinated evolution of ontologies to support biomedical data integration , 2007, Nature Biotechnology.

[12]  Leonidas Aristodemou,et al.  The state-of-the-art on Intellectual Property Analytics (IPA): A literature review on artificial intelligence, machine learning and deep learning methods for analysing intellectual property (IP) data , 2018, World Patent Information.

[13]  Stephen Adams.  TEMPORARY REMOVAL: Is the full text the full answer? – Considerations of database quality , 2017 .

[14]  Klaus-Robert Müller,et al.  Automating the search for a patent’s prior art with a full text similarity search , 2019, PloS one.

[15]  Fabio Crestani,et al.  Combination of similarity measures for effective spoken document retrieval , 2003, J. Inf. Sci..

[16]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[17]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.

[18]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[19]  Dean Alderucci,et al.  Applying Artificial Intelligence to the Patent System , 2019 .

[20]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[21]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[22]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[23]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[24]  Hinrich Schütze,et al.  Introduction to information retrieval , 2008 .

[25]  David H. Wolpert,et al.  The Lack of A Priori Distinctions Between Learning Algorithms , 1996, Neural Computation.

[26]  Kristine H. Atkinson.  Toward a more rational patent search paradigm , 2008, PaIR '08.