US 11,775,894 B2Granted

Intelligent routing framework

AssigneeDell Products L.P.

InventorsBijan Kumar Mohanty, Nanjundaiah Champakadhama Swamy Shreeram, Manasa Kaushik Panduranga, Harish Mysore Jayaram

Life of this patent

Estimating the term…

patentgrep

Loading patent…

Abstract

A method comprises receiving at least one natural language input corresponding to at least one task, and analyzing the at least one natural language input using one or more machine learning models to determine one or more parameters of the at least one task. One or more skills and/or availabilities of respective ones of a plurality of resources are identified. The method further comprises identifying at least a subset of the plurality of resources to perform the at least one task based at least in part on the one or more parameters and on the one or more skills and/or the availabilities. The at least one task is routed to one or more resources of the subset.

Claims20

Dependent claims

A method comprising:

receiving at least one natural language input corresponding to at least one task;
analyzing the at least one natural language input using one or more machine learning models to determine one or more parameters of the at least one task;
identifying at least one of one or more skills and availabilities of respective ones of a plurality of resources, wherein the plurality of resources comprise a plurality of computing resources;
identifying at least a subset of the plurality of resources to perform the at least one task based at least in part on the one or more parameters and on the at least one of the one or more skills and the availabilities;
and
routing the at least one task to one or more resources of the subset, wherein the routing comprises:
transmitting the at least one task to a first computing resource of the one or more resources via one or more application programming interfaces, wherein the at least one task is transmitted with one or more requests for a computing resource receiving the at least one task to execute one or more computing operations associated with the at least one task;
determining whether the routing of the at least one task to the first computing resource has failed;
identifying a second computing resource of the one or more resources to which to route the at least one task in response to determining that the routing of the at least one task to the first computing resource has failed;
and
transmitting the at least one task with the one or more requests to the second computing resource via the one or more application programming interfaces;
wherein the one or more parameters comprise at least an intent of the at least one task and one or more skills needed to perform the at least one task;
wherein the analyzing comprises:
performing natural language processing using one or more neural networks to classify the intent of the at least one task;
and
using a content-based machine learning algorithm to compare the at least one natural language input to a plurality of historical tasks, and to match the at least one natural language input with one or more of the plurality of historical tasks to determine the one or more skills needed to perform the at least one task;
wherein the routing further comprises inputting at least a result of classifying the intent of the at least one task and the one or more skills needed to perform the at least one task to a routing engine, the routing engine routing the at least one task to the one or more resources of the subset based at least in part on the result of classifying the intent of the at least one task and the one or more skills needed to perform the at least one task;
and
wherein the steps of the method are executed by a processing device operatively coupled to a memory.

16 more elements

An apparatus comprising:

a processing device operatively coupled to a memory and configured:
to receive at least one natural language input corresponding to at least one task;
to analyze the at least one natural language input using one or more machine learning models to determine one or more parameters of the at least one task;
to identify at least one of one or more skills and availabilities of respective ones of a plurality of resources, wherein the plurality of resources comprise a plurality of computing resources;
to identify at least a subset of the plurality of resources to perform the at least one task based at least in part on the one or more parameters and on the at least one of the one or more skills and the availabilities;
and
to route the at least one task to one or more resources of the subset, wherein, in routing the at least one task to the one or more resources, the processing device is configured:
to transmit the at least one task to a first computing resource of the one or more resources via one or more application programming interfaces, wherein the at least one task is transmitted with one or more requests for a computing resource receiving the at least one task to execute one or more computing operations associated with the at least one task;
to determine whether the routing of the at least one task to the first computing resource has failed;
to identify a second computing resource of the one or more resources to which to route the at least one task in response to determining that the routing of the at least one task to the first computing resource has failed;
and
to transmit the at least one task with the one or more requests to the second computing resource via the one or more application programming interfaces, wherein the one or more parameters comprise at least an intent of the at least one task and one or more skills needed to perform the at least one task;
wherein the analyzing comprises:
performing natural language processing using one or more neural networks to classify the intent of the at least one task;
and
using a content-based machine learning algorithm to compare the at least one natural language input to a plurality of historical tasks, and to match the at least one natural language input with one or more of the plurality of historical tasks to determine the one or more skills needed to perform the at least one task:
and
wherein, in routing the at least one task to the one or more resources, the processing device is further configured to input at least a result of classifying the intent of the at least one task and the one or more skills needed to perform the at least one task to a routing engine, the routing engine routing the at least one task to the one or more resources of the subset based at least in part on the result of classifying the intent of the at least one task and the one or more skills needed to perform the at least one task.

15 more elements

An article of manufacture comprising a non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes said at least one processing device to perform the steps of:

receiving at least one natural language input corresponding to at least one task;
analyzing the at least one natural language input using one or more machine learning models to determine one or more parameters of the at least one task;
identifying at least one of one or more skills and availabilities of respective ones of a plurality of resources, wherein the plurality of resources comprise a plurality of computing resources;
identifying at least a subset of the plurality of resources to perform the at least one task based at least in part on the one or more parameters and on the at least one of the one or more skills and the availabilities;
and
routing the at least one task to one or more resources of the subset, wherein, in routing the at least one task to the one or more resources, the program code causes said at least one processing device to perform the steps of:
transmitting the at least one task to a first computing resource of the one or more resources via one or more application programming interfaces, wherein the at least one task is transmitted with one or more requests for a computing resource receiving the at least one task to execute one or more computing operations associated with the at least one task;
determining whether the routing of the at least one task to the first computing resource has failed;
identifying a second computing resource of the one or more resources to which to route the at least one task in response to determining that the routing of the at least one task to the first computing resource has failed;
and
transmitting the at least one task with the one or more requests to the second computing resource via the one or more application programming interfaces;
wherein the one or more parameters comprise at least an intent of the at least one task and one or more skills needed to perform the at least one task;
wherein the analyzing comprises:
performing natural language processing using one or more neural networks to classify the intent of the at least one task;
and
using a content-based machine learning algorithm to compare the at least one natural language input to a plurality of historical tasks, and to match the at least one natural language input with one or more of the plurality of historical tasks to determine the one or more skills needed to perform the at least one task;
and
wherein, in routing the at least one task to the one or more resources, the program code further causes said at least one processing device to perform the step of inputting at least a result of classifying the intent of the at least one task and the one or more skills needed to perform the at least one task to a routing engine, the routing engine routing the at least one task to the one or more resources of the subset based at least in part on the result of classifying the intent of the at least one task and the one or more skills needed to perform the at least one task.

15 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/237,482Filed 22 Apr 2021
Published: US 2022/0343257 A127 Oct 2022
Granted: 3 Oct 2023
Term ends: Not estimatedThe source records don’t support an estimate.

Classification12 codes

G06Q 10/063112
Scheduling, planning or task assignment for a person or group: skill-based matching of a person or a group to a task
G06F 40/30
Handling natural language data: semantic analysis
G06N 3/044
Architecture, e.g. interconnection topology: recurrent networks, e.g. Hopfield networks
G06N 5/04
Computing arrangements using knowledge-based models: inference or reasoning models