Back to results
US 2026/0219947 A1Published application
system and method for classifying computing nodes of a computing network
AssigneeBank of America Corporation
InventorsJemlin Lucas, Suryanarayana Adivi, Pushkar Taneja, Sujatha Ambati, Niroop Reddy Patimeedi
Life of this patent
Estimating the term…
Abstract
In response to determining that a real-time latency associated with performing a process workflow in a computing network equals or exceeds a threshold, an artificial intelligence (AI) model determines a sequence of tasks associated with the process workflow, determines a server of the computing network that can perform each identified task, and establishes a server group including the identified servers. The server group is configured to perform the process workflow. Upon receiving a subsequent request, the process workflow is performed based on the configuration of the server group.
Claims20
A system comprising:
- a memory storing an Artificial Intelligence (AI) model that comprises an AI algorithm;
- and
- a processor communicatively coupled to the memory and configured to:
- receive a first latency associated with performing a process workflow in a computing network, wherein:
- the process workflow comprises a sequence of tasks;
- each task of the sequence of tasks is performed by a particular server of a plurality of servers of the computing network;
- and
- the first latency associated with the process workflow indicates a speed of processing the process workflow;
- input the first latency associated with the process workflow to the AI model, wherein:
- the AI algorithm associated with the AI model is trained, based at least on a relation matrix and a dependency matrix, to determine a first group of servers for performing the process workflow;
- the relation matrix comprises information relating to a task performed by each server of the plurality of servers, data stored at each server, and logical connections configured between pairs of the servers;
- and
- the dependency matrix comprises information relating to tasks that are dependent on other tasks;
- execute the AI model with the trained AI algorithm to:
- detect that the first latency associated with performing the process workflow equals or exceeds a first threshold latency;
- in response to detecting that the first latency equals or exceeds a first threshold latency:
- determine, based at least on the dependency matrix, the sequence of tasks that are to be performed to complete the process workflow, wherein the sequence of tasks comprises a first task followed by a second task;
- determine, based on the relation matrix, a first server that is configured to perform the first task;
- determine, based on the relation matrix, a second server that is configured to perform the second task;
- and
- establish the first group of servers to include the first server and the second server;
- configure the first group of servers to perform the process workflow, wherein the configuration of the first group of servers causes the first server to perform the first task and the second server to perform the second task;
- after configuring the first group of servers, receive a first request to perform the process workflow;
- in response to receiving the first request, issue a first machine-initiated call to the first server to perform the first task of the sequence of tasks in the process workflow;
- and
- issue a second machine-initiated call to the second server to perform the second task of the sequence of tasks in the process workflow.
23 more elements
A method comprising:
- receiving a first latency associated with performing a process workflow in a computing network, wherein:
- the process workflow comprises a sequence of tasks;
- each task of the sequence of tasks is performed by a particular server of a plurality of servers of the computing network;
- and
- the first latency associated with the process workflow indicates a speed of processing the process workflow;
- inputting the first latency associated with the process workflow to an Artificial Intelligence (AI) model, wherein:
- an AI algorithm associated with the AI model is trained, based at least on a relation matrix and a dependency matrix, to determine a first group of servers for performing the process workflow;
- the relation matrix comprises information relating to a task performed by each server of the plurality of servers, data stored at each server, and logical connections configured between pairs of the servers;
- and
- the dependency matrix comprises information relating to tasks that are dependent on other tasks;
- executing the AI model with the trained AI algorithm to:
- detect that the first latency associated with performing the process workflow equals or exceeds a first threshold latency;
- in response to detecting that the first latency equals or exceeds a first threshold latency:
- determine, based at least on the dependency matrix, the sequence of tasks that are to be performed to complete the process workflow, wherein the sequence of tasks comprises a first task followed by a second task;
- determine, based on the relation matrix, a first server that is configured to perform the first task;
- determine, based on the relation matrix, a second server that is configured to perform the second task;
- and
- establish the first group of servers to include the first server and the second server;
- configuring the first group of servers to perform the process workflow, wherein the configuration of the first group of servers causes the first server to perform the first task and the second server to perform the second task;
- after configuring the first group of servers, receiving a first request to perform the process workflow;
- in response to receiving the first request, issuing a machine-initiated first call to the first server to perform the first task of the sequence of tasks in the process workflow;
- and
- issuing a machine-initiated second call to the second server to perform the second task of the sequence of tasks in the process workflow.
20 more elements
A non-transitory computer-readable medium storing instructions that when executed by a processor cause the processor to:
- receive a first latency associated with performing a process workflow in a computing network, wherein:
- the process workflow comprises a sequence of tasks;
- each task of the sequence of tasks is performed by a particular server of a plurality of servers of the computing network;
- and
- the first latency associated with the process workflow indicates a speed of processing the process workflow;
- input the first latency associated with the process workflow to an Artificial Intelligence (AI) model, wherein:
- an AI algorithm associated with the AI model is trained, based at least on a relation matrix and a dependency matrix, to determine a first group of servers for performing the process workflow;
- the relation matrix comprises information relating to a task performed by each server of the plurality of servers, data stored at each server, and logical connections configured between pairs of the servers;
- and
- the dependency matrix comprises information relating to tasks that are dependent on other tasks;
- execute the AI model with the trained AI algorithm to:
- detect that the first latency associated with performing the process workflow equals or exceeds a first threshold latency;
- in response to detecting that the first latency equals or exceeds a first threshold latency:
- determine, based at least on the dependency matrix, the sequence of tasks that are to be performed to complete the process workflow, wherein the sequence of tasks comprises a first task followed by a second task;
- determine, based on the relation matrix, a first server that is configured to perform the first task;
- determine, based on the relation matrix, a second server that is configured to perform the second task;
- and
- establish the first group of servers to include the first server and the second server;
- configure the first group of servers to perform the process workflow, wherein the configuration of the first group of servers causes the first server to perform the first task and the second server to perform the second task;
- after configuring the first group of servers, receive a first request to perform the process workflow;
- in response to receiving the first request, issue a machine-initiated first call to the first server to perform the first task of the sequence of tasks in the process workflow;
- and
- issue a machine-initiated second call to the second server to perform the second task of the sequence of tasks in the process workflow.
20 more elements
Dependencies are inferred from the claim text.