A semantic analysis approach for identifying patent infringement based on a product–patent map

Abstract

Identifying patent infringement beforehand is highly important for reducing the risk of damages. However, as the approach to patents is changing from the technological and legal approaches of the past to the business approach, strategic patent infringement litigation and securement of patents can be important tools for companies. From various viewpoints, companies can consider an aggressive patent infringement litigation as well as evasion strategy of patent infringement litigation to keep competitors in check. Previous research on patent infringement identification only considered the possibility of infringement between patents. However, infringement cases between patent and product are prevalent. Thus, this research aims to suggest an automated method for identifying patent infringement between the patent and product in business. To this end, this paper proposes the subject–action–object (SAO) semantic technological similarity-based product–patent method for generating infringement maps. Several indices and subgrouping methods are suggested to interpret the map. As an exemplary case, data on technology and products related to the light emitting diode (LED) lamp are collected and exploited.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 20 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.