Semantics graphs for enterprise communication networks
AssigneeHewlett-Packard Development Company, L.P.
InventorsMehmet Kivanc Ozonat, Claudio Bartolini
Life of this patent
Estimating the term…
Abstract
Building a semantics graph for an enterprise communication network can include calculating a distance metric between a first signifier and a second signifier associated with an enterprise communication network, wherein the distance metric includes a plurality of relationships defined based on a frequency of co-occurrences of the first signifier and the second signifier, and building a semantics graph for the enterprise communication network using the calculated distance metric.
Claims9
A non-transitory computer-readable medium storing a set of instructions executable by a processing resource, wherein the set of instructions can be executed by the processing resource to:
- calculate a ratio of co-related services associated with a first signifier and a second signifier associated with an enterprise communication network;
- calculate a ratio of co-related phrases associated with the first signifier and the second signifier;
- average a location of the first signifier and the second signifier on a enterprise network;
- and
- build a semantics graph for the enterprise communication network using a distance metric between the first signifier and the second signifier, wherein the distance metric is defined using the ratio of co-related services, the ratio of co-related phrases, and the average location.
A system for building a semantics graph for an enterprise communication network comprising:
- a processing resource;
- and
- a memory resource communicatively coupled to the processing resource containing instructions executable by the processing resource to:
- extract a plurality of signifiers from an enterprise network using an extraction tool;
- define a distance metric between pairs of related signifiers among the plurality of signifiers, wherein defining a distance metric between each pair of related signifiers includes:
- calculate a ratio of co-related services associated with both a first signifier and a second signifier and services related independently to the first signifier and services related independently to the second signifier;
- calculate a ratio of co-related phrases associated with both the first signifier and the second signifier and phrases related independently to the first signifier and phrases related independently to the second signifier;
- average a location of the first signifier and the second signifier on the enterprise network;
- and
- define the distance metric as a sum of the ratio of co-related services, the ratio of co-related phrases, and the average location;
- and
- build a semantics graph for the enterprise communication network using the defined distance metrics between pairs of related signifiers, including the defined distance metric of the first signifier and the second signifier.
Dependencies are inferred from the claim text.