With the increasing number of patent applications over the years, instances of patent infringement cases have become more frequent. However, traditional manual patent infringement detection models are no longer suitable for large-scale infringement detection. Existing automated models mainly focus on detecting one-to-one patent infringements, but neglect the many-to-one scenarios. The many-to-one patent infringement detection model faces some major challenges. First, the diversity of patent domains, complexity of content and ambiguity of features make it difficult to extract and represent patent features. Second, patent infringement detection relies on the correlation between patents and the comparison of contextual information as the key factors, but modeling the process and drawing conclusions present challenges. To address these challenges, we propose a many-to-one patent graph (MPG) embedding base infringement detection model. Our model extracts the relationship between keywords and patents, as well as association relation between keywords from many-to-one patent texts (MPTs), to construct a MPG. We obtain patent infringement features through graph embedding of MPG. By using these embedding features as input, the many-to-one infringement detection (MOID) model outputs the conclusion on whether a patent is infringed or not. The comparative experimental results indicate that our model improves accuracy, precision and F-measure by 3.81%, 11.82% and 5.37%, respectively, when compared to the state-of-the-art method.

With the development of intellectual property rights in recent years, the number of patent applications has been increasing.At the same time, the number of patent infringement cases has also increased.When there is infringement between patents, the traditional method is for patent examiners to manually search for infringing features to determine whether there is infringement between patents according to the patent law.Since a patent is a complex semi-structured text and involves a wide range of fields, most of the current infringement detection methods cannot determine the infringement features well, and most of the methods only study one-to-one patent infringement and do not solve the problem of one-to-many patent infringement well.In order to solve the above problems, a patent infringement detection method based on convolutional neural network is proposed.The method extracts and represents infringement features from patents, patent claims and independent patent claims respectively, represents patents by different patent text vectorization methods, combines and filters features based on convolutional neural networks so as to obtain semantic information of different abstraction layers of patents, and finally tests the evaluation model on a one-to-many patent infringement data set.The results show that the model has greatly improved the infringement detection accuracy.