Weighted meta paths and networking embedding for patent technology trade recommendations among subjects

作者：

Highlights：

• A meta path and network embedding method of patent technology trade was innovatively proposed in HIN.

• Inspired by the DFS, the traversal methods were designed in a HIN to calculate the meta paths.

• The recommendation performance of weighted PSR-vec was found to be better than that of the other methods.

摘要

•A meta path and network embedding method of patent technology trade was innovatively proposed in HIN.•Inspired by the DFS, the traversal methods were designed in a HIN to calculate the meta paths.•The recommendation performance of weighted PSR-vec was found to be better than that of the other methods.

论文关键词：Trade recommendation,Patent technology,Heterogeneous information network,Network embedding

论文评审过程：Received 9 January 2019, Revised 25 July 2019, Accepted 28 July 2019, Available online 21 August 2019, Version of Record 11 October 2019.

论文官网地址：https://doi.org/10.1016/j.knosys.2019.104899