CPC G06F 16/3344 (2019.01) [G06F 16/35 (2019.01); G06N 5/02 (2013.01); G06N 20/00 (2019.01)] | 20 Claims |
1. A method, comprising:
receiving, by a device and in near-real time, unstructured data associated with an application or a system;
extracting, by the device, textual data from the unstructured data;
parsing, by the device, the textual data to generate parsed textual data;
performing, by the device, natural language processing on the parsed textual data to generate processed textual data;
processing, by the device, the processed textual data, with a clustering model, to identify topical data associated with the processed textual data;
processing, by the device, the topical data, with a classification model, to group the topical data into categories;
generating, by the device, a knowledge graph based on the categories;
storing, by the device, the knowledge graph in a data structure;
receiving, by the device, a question associated with the application or the system;
determining, by the device, that a search of the knowledge graph failed to identify an answer to the question;
automatically connecting, by the device, a first client device, associated with a subject matter expert for the answer to the question, and a second client device associated with the question based on determining that the search of the knowledge graph failed to identify the answer to the question,
wherein the first client device and the second client device are automatically connected based on the search of the knowledge graph failing to identify the answer to the question;
monitoring, by the device, information exchanged between the first client device and the second client device;
updating, by the device, the knowledge graph based on the information exchanged between the first client device and the second client device; and
generating, by the device, one or more analytics based on a quantity of times the subject matter expert revised the topical data in the knowledge graph.
|