Evaluating the risk of patent infringement by means of semantic patent analysis: the case of DNA chips

Abstract

In this paper, we are going to present a method for detecting the risks of patent infringement by evaluating similarities between patent documents on the basis of semantic patent analysis. This approach enables the user to visualize similarities in the contents on a semantic patent map by means of multi‐dimensional scaling. The effectiveness of the semantic patent map has already been demonstrated by Dressler (2006) with regard to patents of seal technology, in which documents are commonly kept short and the extracted contents are concise. This paper will open out to the field of biotechnology, where patents can easily comprise several hundreds of pages. The method presented here conveys an interdisciplinary approach and combines computer‐aided natural language processing with domain‐specific expertise of biochemical processes. This is illustrated by an authentic case of infringement involving two manufacturers of DNA chips. Our experiment will show how the infringement case is visualized on a patent map based on semantic patent analysis. This experiment can be compared with the search for a needle in a haystack, the two competitive patents representing significantly conflicting ‘needles.’ From an approximate number of 4,000 patents in the current US Class 435/6, a set of patents was selected that included the ‘needles’ mentioned. This paper will point out how such mutual interference can be detected by way of semantic patent analysis, and what advice may be given to R&D managers who are faced with the risk of patent infringement.

Should we manage the process of inventing? Designing for patentability

“…By indicating that the contradictions and corresponding inventive principles are too abstract and general, the authors claim to help innovators by using text mining to relate directly examples of published patents in patent design activity using TRIZ related methodology. Authors explore how to ensure patent search and use text mining and semantic analyses methods to automatically analyze the existing IP databases and relate them to the new innovative challenges, to verify the risks of patent infringements (Cascini and Russo, 2007, Liang et al, 2008, Bergmann et al, 2008. TRIZ is also to deal with local innovations of an existing patent -design around.…”

A Function-Based Knowledge Base for Technology Intelligence

“…In addition, it can express the means-end relationship in a problem-solving format; the AO states the problem to be done, and the S forms the solution (Moehrle et al, 2005). For this reason, the SAO structures found in the specification and claims of patents have been considered to represent the know-how and expertise of the inventor of a patent and may even reflect the key concepts of the invention (Bergmann et al, 2008;Yoon et al, 2013).…”

“…In the study, they extracted SAO structures from patents and mapped the patents onto a two-dimensional space by comparing similarities among patent SAO structures. Others proposed systematic methods to identify the risk of patent infringement (Bergmann et al, 2008;Park et al, 2012). The underlying concept behind the methods was that a high similarity between a pair of patents is likely to involve a high possibility of infringement.…”

“…Therefore, technology intelligence studies have proposed systematic technology opportunity discovery processes of collecting and processing specific patent data. In particular, regarding the textual analysis of patents, some studies have visualized technological objects, such as patents and technological key concepts related to specific products and technologies, in the forms of maps and networks to identify the competition trends of research and development (R&D) Lee and Hong, 2014), technology packages (Yoon et al, 2002), and the possibility of patent infringement (Bergmann et al, 2008;Cascini and Zini, 2008;Park et al, 2012). Some have attempted to forecast promising technological applications and future R&D directions by applying novelty detection algorithms and network analysis indicators Geum et al, 2013), and to find new technological items through idea generation approaches, including morphological analysis and technology vacuum analysis (Yoon and Park, 2005;Yoon and Park, 2007;Lee et al, 2009).…”

Measures for textual patent similarities: a guided way to select appropriate approaches

“…Unfortunately, three aspects reduce technology manager's ability to deal with patents efficiently: (i) numbers of patent applications all over the world are steadily growing, there exists a massive information overflow in patent literature (Bergmann et al 2008), (ii) analyzing patents (in the meaning of reading and understanding) is a timeconsuming task, which can only be handled with a large quantum of manpower (Yanhong and Runhua 2007), (iii) to make the situation even worse some studies show, that the patent assessment quality is not as good as it could be (see Burke and Reitzig 2007) and also seems to decline (Philipp 2006), because of reduced assessment times for patent examiners in the patent offices.…”