{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/automating-the-search-for-a-patents-prior-art","title":"Automating the search for a patent's prior art with a full text similarity search","arxiv_id":"1901.03136","date":"2019-01-10","proceeding":null,"authors":["Lea Helmers","Franziska Horn","Franziska Biegler","Tim Oppermann","Klaus-Robert Müller"],"abstract":"More than ever, technical inventions are the symbol of our society's advance.\nPatents guarantee their creators protection against infringement. For an\ninvention being patentable, its novelty and inventiveness have to be assessed.\nTherefore, a search for published work that describes similar inventions to a\ngiven patent application needs to be performed. Currently, this so-called\nsearch for prior art is executed with semi-automatically composed keyword\nqueries, which is not only time consuming, but also prone to errors. In\nparticular, errors may systematically arise by the fact that different keywords\nfor the same technical concepts may exist across disciplines. In this paper, a\nnovel approach is proposed, where the full text of a given patent application\nis compared to existing patents using machine learning and natural language\nprocessing techniques to automatically detect inventions that are similar to\nthe one described in the submitted document. Various state-of-the-art\napproaches for feature extraction and document comparison are evaluated. In\naddition to that, the quality of the current search process is assessed based\non ratings of a domain expert. The evaluation results show that our automated\napproach, besides accelerating the search process, also improves the search\nresults for prior art with respect to their quality.","url_abs":"http://arxiv.org/abs/1901.03136v2","url_pdf":"http://arxiv.org/pdf/1901.03136v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"automating-the-search-for-a-patents-prior-art","repo_url":"https://github.com/helmersl/patent_similarity_search","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"text-similarity","task_name":"text similarity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1901.03136","atlas_url":"https://app.syntology.ai/?focus=1901.03136","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}