Systems and methods for determining embedding vector for heterogeneous and asynchronous it operations event data

A system for determining a signature embedding vector for information technology events, the system comprising:

• a memory having processor-readable instructions stored therein;
• and
• at least one processor configured to access the memory and execute the processor-readable instructions to perform operations including:
• receiving a current data object representing an occurrence of an information technology event associated with a configurable item;
• obtaining a graph database of logical associations of the configurable item;
• applying a clustering algorithm to the graph database to determine a subset of graphs;
• extracting associated data of the subset of graphs;
• applying an embedding model to the extracted associated data to determine an embedding vector for each subset of graphs, wherein the embedding model includes a transformer with a graph attention network encoder and a future node embedding predictor, wherein applying an embedding model to the extracted associated data to determine an embedding vector for each subset of graphs further includes:
• encoding and decoding, using the graph attention network encoder, the extracted associated data from each subset of graphs, producing a respective linear output layer for each graph;
• and
• reshaping, using the future node embedding predictor, the respective linear output layer for each subset of graphs into the embedding vector for each subset of graphs;
• aggregating the embedding vector for each subset of graphs to determine a signature embedding vector;
• and
• utilizing the signature embedding vector to perform further analysis of the current data object.

A non-transitory computer readable medium storing processor-readable instructions which, when executed by at least one processor, cause the at least one processor to perform operations including:

• receiving a current data object representing an occurrence of an information technology event associated with a configurable item;
• obtaining a graph database of logical associations of the configurable item;
• applying a clustering algorithm to the graph database to determine a subset of graphs;
• extracting associated data of the subset of graphs;
• applying an embedding model to the extracted associated data to determine an embedding vector for each subset of graphs, wherein the embedding model includes a transformer with a graph attention network encoder and a future node embedding predictor, wherein applying an embedding model to the extracted associated data to determine an embedding vector for each subset of graphs further includes:
• encoding and decoding, using the graph attention network encoder, the extracted associated data from each subset of graphs, producing a respective linear output layer for each graph;
• and
• reshaping, using the future node embedding predictor, the respective linear output layer for each subset of graphs into the embedding vector for each subset of graphs;
• aggregating the embedding vector for each subset of graphs to determine a signature embedding vector;
• and
• utilizing the signature embedding vector to perform further analysis of the current data object.