Servicenow, Inc.

Jeevan Anand Anne

Manjeet Singh

Omer Anil Turkkan

Bruce Walthers

Lingzhu Li

Sagar Davasam Suryanarayan

An embodiment may involve: obtaining textual content including a plurality of token strings, wherein each of the plurality of token strings includes one or more tokens; determining, for the plurality of token strings, respectively corresponding sets of n-gram tuples; assigning respective weights to the plurality of token strings, wherein, for each of the plurality of token strings, the assignment is based on the respectively corresponding set of n-gram tuples; identifying a subset of the plurality of token strings, wherein each of the subset of the plurality of token strings is characterized by a respective weight that exceeds a predetermined threshold weight; and storing sets of n-gram tuples respectively corresponding to the subset of the plurality of token strings.

Language model preprocessing with weighted n-grams

A system may include persistent storage containing representations of requests associated with a managed network. The persistent storage may include lists of capabilities associated with agents, and each request may include a textual description of a situation experienced by a user and a resolution of the situation by a particular agent. A computing device may obtain a set of requests from the persistent storage, apply an unsupervised machine learning clustering technique to textual descriptions included in the set of requests, and arrange the requests into groups such that each group contains requests including textual descriptions with at least a threshold degree of similarity to one another. The computing device may perform, for the requests in a particular group, a textual analysis on associated resolutions to identify capabilities used by agents to resolve the requests, and update the lists of capabilities to associate the capabilities with agents that used them.

Growing community of inventors

Santa Clara, CA, United States of America

Jeevan Anand Anne