Abstract
People within large originations have difficulty finding individuals or groups who have expertise
or products for any specific domain. This is largely due to the difficulty of tracking what each
individual or group is working on in a dynamic environment. The proposed solution is to create a
Search Engine which can query individuals based off their domain expertise. The proposed
solution uses the 2 model to produce topic vectors for every email or other textual
communication by employees. The communication topic vectors provide spatial correlated topics
where similar topics will be found close together, and dissimilar topics will be found far apart from
each other. Converting textual communication into spatial related topic vectors allows for the use
of well proven and robust correlation models such as K Nearest Neighbors (K‐NN) to find
appropriate similarities.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.
Recommended Citation
INC, HP, "PERSONNEL KNOWLEDGE SEARCH SYSTEM", Technical Disclosure Commons, (September 12, 2018)
https://www.tdcommons.org/dpubs_series/1499