Automating the search for a patent’s prior art with a full text similarity search

Автоматизация поиска уровня техники для патента с использованием полнотекстового поиска по сходству
Lea Helmers, Franziska Horn, Franziska Biegler, Tim Oppermann, Klaus‐Robert Müller
2019-03-04

document comparisonfull-text similarity searchmachine learningnatural language processingpatent prior art search
More than ever, technical inventions are the symbol of our society's advance. Patents guarantee their creators protection against infringement. For an invention being patentable, its novelty and inventiveness have to be assessed. Therefore, a search for published work that describes similar inventions to a given patent application needs to be performed. Currently, this so-called search for prior art is executed with semi-automatically composed keyword queries, which is not only time consuming, but also prone to errors. In particular, errors may systematically arise by the fact that different keywords for the same technical concepts may exist across disciplines. In this paper, a novel approach is proposed, where the full text of a given patent application is compared to existing patents using machine learning and natural language processing techniques to automatically detect inventions that are similar to the one described in the submitted document. Various state-of-the-art approaches for feature extraction and document comparison are evaluated. In addition to that, the quality of the current search process is assessed based on ratings of a domain expert. The evaluation results show that our automated approach, besides accelerating the search process, also improves the search results for prior art with respect to their quality.
1
Domain-expert ratings are used to assess the quality of the existing search process and the automated results.
2
Multiple state-of-the-art feature-extraction and document-comparison methods are evaluated for detecting patents describing similar inventions.
3
The approach addresses limitations of keyword-based searches, including time consumption, manual effort, and errors caused by discipline-specific terminology differences.
4
The evaluation indicates that automated full-text similarity search both accelerates prior-art retrieval and improves the quality of the results.
5
The paper introduces an automated prior-art search method that compares a patent application’s full text with existing patents using machine learning and natural language processing.

patent applications and existing patents describing potentially similar inventions

automatic full-text similarity-based detection and quality improvement of patent prior art searches

Publication Details
Publication Date
2019-03-04
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Lea Helmers
Franziska Horn
Franziska Biegler
Tim Oppermann
Klaus‐Robert Müller
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%