Abstract
With the intense competition of global intellectual property, the increasing number of patents promotes the potential of patent transactions. However,an unknown patent value degrades the patent transaction rate. Automatic patent valuation faces some challenges, including the following: (1) how to represent a valuation object, (2) how to construct the valuation scenario, and (3) how to generate and measure the patent value. To solve the above issues, we propose a probabilistic graph-based patent valuation model. In the model, the textual parts are combined with some structured parts of patents to represent a valuation object. A heterogeneous association network is constructed as the valuation scenario. Thereafter, a patent valuation model is formed by a generative process, which is represented by a probabilistic graphical model.The patent value distribution is learned by making inference using the valuation model. We evaluate our model by comparing it with state-of-the-art models on patent data sets. The results show that our model outperforms other models in the evaluation measurements.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.