PERSONNEL KNOWLEDGE SEARCH SYSTEM

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