A Review on the Determination of Semantic Similarity of Patent Documents

Patent mining studies are gaining importance in the processing of patent data, which contains the most up-to-date technical information, has a great potential in terms of information discovery with its high volume, and plays a key role in the field of technology management. Although all the structured or unstructured data in the patent data are important, the most critical goal of patent mining studies is to determine the semantic similarity of patent documents. With the semantic similarity detection of patents, it will be possible to automatically determine the patentability criteria, which is the most difficult and time-consuming phase of the patent application process. In this article, the studies carried out in the literature about determination the semantic similarity of patent documents were examined and the methods used were categorized into two groups: text mining and deep learning -based methods. Set theory approaches, vector space model approaches or ontology etc. are used to determine how similar patent texts are to each other by structuralizing them with text mining methods. There are approaches that make use of information sources. However, due to the complex structure and unique terminology of patent texts, the targeted efficiency cannot be obtained from these methods. In order to overcome this deficiency, artificial intelligence methods, which have shown great success in every field they are used, should also be utilized in the semantic comparison of patent texts. Especially with the high capacity of deep learning methods, a significant distance can be achieved in determining the patentability criteria, which is a complex problem. Although studies have been carried out in this area, models that can effectively detect patentability are still in their infancy. The objective of this study is to demonstrate that developing a qualified model capable of conducting patentability assessments and automatically generating patent search reports will be a significant step towards fulfilling the substantial needs in the field of technology management.