US 11,671,444 B2
Matching configuration items with machine learning
Brian James Waplington, San Diego, CA (US)
Assigned to ServiceNow, Inc., Santa Clara, CA (US)
Filed by ServiceNow, Inc., Santa Clara, CA (US)
Filed on Sep. 12, 2022, as Appl. No. 17/931,381.
Application 17/931,381 is a continuation of application No. 16/897,991, filed on Jun. 10, 2020, granted, now 11,470,107.
Prior Publication US 2023/0007039 A1, Jan. 5, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04L 9/40 (2022.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06N 3/08 (2023.01)
CPC H04L 63/1433 (2013.01) [G06N 5/04 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computing system comprising:
persistent storage containing configuration items (CIs) representing a plurality of attribute values of computing resources; and
a processor configured to perform operations comprising:
obtaining two or more attribute values of a particular computing resource;
generating, using a machine learning model and based on one or more attribute values of the two or more attribute values of the particular computing resource, an embedding vector representing the one or more attribute values of the particular computing resource;
comparing the embedding vector to one or more candidate embedding vectors, wherein each respective candidate embedding vector of the one or more candidate embedding vectors represents at least one attribute value of a corresponding CI of the CIs contained in the persistent storage;
based on comparing the embedding vector to the one or more candidate embedding vectors, selecting a particular CI of the CIs contained in the persistent storage; and
updating the particular CI to additionally represent at least one of the two or more attribute values of the particular computing resource.