Capturing and Tracking Performance of Patent Portfolio Using $h$ -Complement Area Centroid

Abstract

Assuming that only the bibliometric information contained in patent databases is available and that the citations received by a patent indicate the patent's value or quality, we propose to characterize the performance of a patent assignee's patent portfolio, in terms of both the quantity and quality of its cited and uncited patents, by the centroid of a so-called h-complement area from the assignee's citation distribution. This approach is capable of producing a snapshot to a large number of assignees' portfolio performance by simultaneously depicting their h-complement area centroids in a 2-D graph. With this 2-D view, these assignees' relative performance, where the performance difference lies, and the degree of such difference can also be quickly determined. In addition, a trajectory manifesting the evolution of an assignee's portfolio performance over a window of time can be obtained by connecting the h-complement area centroids at successive epochs within the time window. The pattern revealed by the trajectory provides significant insight into how the assignee's portfolio performance has varied over time. When there is some abrupt pattern change, an analyst should be alarmed to conduct further investigation. A steady pattern, on the other hand, allows forecast to the assignee's future performance.

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 — 8 citations exist upstream.

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