US 12,748,782 B1Granted

Systems for and methods of natural language classification and adaptive routing of domain-specific data objects

AssigneeCrisp, Inc.

InventorMichael Mogill

Life of this patent

Estimating the term…

Loading patent…

Abstract

A system includes at least a processor and a memory communicatively connected to the at least a processor. The memory contains instructions configuring the at least a processor to: receive a domain-specific data object including natural-language content and associated metadata, map, using a language processing module, the domain-specific data object into a vector space representation, and classify, using a classification module, the vector space representation to at least one node of a ontology structure defining a plurality of hierarchical specialization nodes. The processor is further configured to generate, using a routing module, a routing confidence score as a function of a specialty coefficient, which is associated with the at least one node of the ontology structure and is derived from destination-specific metadata, and route, using the routing module, the vector space representation to a destination node as a function of the routing confidence score.

Claims16

Dependent claims

A system for natural language classification and adaptive routing of domain-specific data objects, the system comprising:

at least a processor;
and
a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to:
receive a domain-specific data object comprising natural-language content and associated metadata;
map, using a language processing module, the domain-specific data object into a vector space representation;
classify, using a classification module, the vector space representation to at least one node of an ontology structure, wherein the ontology structure defines a plurality of hierarchical specialization nodes;
generate, using a routing module, a routing confidence score as a function of a specialty coefficient associated with the at least one node of the ontology structure, wherein the specialty coefficient is derived from destination-specific metadata;
route, using the routing module, the vector space representation to a destination node as a function of the routing confidence score;
and
update the routing module as a function of performance outcomes, wherein updating the routing module comprises:
receiving feedback data associated with the domain-specific data object and the destination node;
generating destination-level performance features as a function of the feedback data;
generating an updated value for the specialty coefficient associated with the at least one node of the ontology structure by correlating the destination-level performance features with the at least one node of the ontology structure;
recalibrating the routing module as a function of the updated value for the specialty coefficient, wherein recalibrating the routing module comprises maintaining an exponential decay function over specialty coefficient updates to avoid overfitting to short-term fluctuations;
detecting a recalibration trigger;
updating the specialty coefficient of the at least one node of the ontology structure using the updated value for the specialty coefficient;
and
storing updated routing model parameters within the routing module for use in subsequent generation of routing confidence scores.

15 more elements

A method of natural language classification and adaptive routing of domain-specific data objects, the method comprising:

receiving, using at least a processor, a domain-specific data object comprising natural-language content and associated metadata;
mapping, using the at least a processor and a language processing module, the domain-specific data object into a vector space representation;
classifying, using the at least a processor and a classification module, the vector space representation to at least one node of an ontology structure, wherein the ontology structure defines a plurality of hierarchical specialization nodes;
generating, using the at least a processor and a routing module, a routing confidence score as a function of a specialty coefficient associated with the at least one node of the ontology structure, wherein the specialty coefficient is derived from destination-specific metadata;
routing, using the at least a processor and the routing module, the vector space representation to a destination node as a function of the routing confidence score;
and
updating, using the at least a processor, the routing module as a function of performance outcomes, wherein updating the routing module comprises:
receiving feedback data associated with the domain-specific data object and the destination node;
generating destination-level performance features as a function of the feedback data;
generating an updated value for the specialty coefficient associated with the at least one node of the ontology structure by correlating the destination-level performance features with the at least one node of the ontology structure;
recalibrating the routing module as a function of the updated value for the specialty coefficient, wherein recalibrating the routing module comprises maintaining an exponential decay function over specialty coefficient updates to avoid overfitting to short-term fluctuations;
detecting a recalibration trigger;
updating the specialty coefficient of the at least one node of the ontology structure using the updated value for the specialty coefficient;
and
storing updated routing model parameters within the routing module for use in subsequent generation of routing confidence scores.

12 more elements

Dependencies are inferred from the claim text.