Hybrid learning system for natural language understanding
First Claim
1. An agent automation system, comprising:
- a memory configured to store an intent/entity model and a natural language understanding (NLU) framework, wherein the intent/entity model associates defined intents with sample utterances, and wherein the sample utterances encode defined entities as parameters of the defined intents within the intent/entity model; and
a processor configured to execute instructions of the NLU framework to cause the agent automation system to perform actions comprising;
generating a meaning representation from an annotated utterance tree of an utterance by combining a plurality of vectors of the annotated utterance tree using stored coefficients to calculate a respective subtree vector for each intent subtree of the annotated utterance tree, wherein each of the plurality of vectors is associated with a particular node or subtree that depends from each intent subtree, wherein the stored coefficients provide focus, attention, and magnification (FAM) to the calculation of each respective subtree vector, and wherein the meaning representation has a tree structure that indicates a syntactic structure of the utterance and has one or more subtree vectors indicating a semantic meaning of one or more intent subtrees of the meaning representation;
searching the meaning representation of the utterance against an understanding model to extract intents and entities of the utterance based on the one or more subtree vectors of the meaning representation, wherein the understanding model comprises a plurality of meaning representations derived from the sample utterances of the intent/entity model; and
providing the intents and entities of the utterance to a behavior engine (BE) of the agent automation system, wherein the BE is configured to perform one or more actions in response to the intents and entities of the utterance.
1 Assignment
0 Petitions
Accused Products
Abstract
An agent automation system includes a memory configured to store a natural language understanding (NLU) framework, and a processor configured to perform actions, including: generating a meaning representation from an annotated utterance tree of an utterance, wherein a structure of the meaning representation indicates a syntactic structure of the utterance and one or more subtree vectors of the meaning representation indicate a semantic meaning of one or more intent subtrees of the meaning representation; searching the meaning representation of the utterance against an understanding model to extract intents/entities of the utterance based on the one or more subtree vectors of the meaning representation, wherein the understanding model includes a plurality of meaning representations derived from the intent/entity model; and providing the intents/entities of the utterance to a reasoning agent/behavior engine (RA/BE) of the agent automation system that performs one or more actions in response to the intents/entities of the utterance.
57 Citations
20 Claims
-
1. An agent automation system, comprising:
-
a memory configured to store an intent/entity model and a natural language understanding (NLU) framework, wherein the intent/entity model associates defined intents with sample utterances, and wherein the sample utterances encode defined entities as parameters of the defined intents within the intent/entity model; and a processor configured to execute instructions of the NLU framework to cause the agent automation system to perform actions comprising; generating a meaning representation from an annotated utterance tree of an utterance by combining a plurality of vectors of the annotated utterance tree using stored coefficients to calculate a respective subtree vector for each intent subtree of the annotated utterance tree, wherein each of the plurality of vectors is associated with a particular node or subtree that depends from each intent subtree, wherein the stored coefficients provide focus, attention, and magnification (FAM) to the calculation of each respective subtree vector, and wherein the meaning representation has a tree structure that indicates a syntactic structure of the utterance and has one or more subtree vectors indicating a semantic meaning of one or more intent subtrees of the meaning representation; searching the meaning representation of the utterance against an understanding model to extract intents and entities of the utterance based on the one or more subtree vectors of the meaning representation, wherein the understanding model comprises a plurality of meaning representations derived from the sample utterances of the intent/entity model; and providing the intents and entities of the utterance to a behavior engine (BE) of the agent automation system, wherein the BE is configured to perform one or more actions in response to the intents and entities of the utterance. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10)
-
-
11. A method of operating an agent automation system, comprising:
-
generating at least one meaning representation from an annotated utterance tree of an utterance by combining a plurality of vectors of the annotated utterance tree using stored coefficients to calculate a respective subtree vector for each intent subtree of the annotated utterance tree, wherein each of the plurality of vectors is associated with a particular node or subtree that depends from each intent subtree, wherein the stored coefficients provide focus, attention, and magnification (FAM) to the calculation of each respective subtree vector, and wherein the at least one meaning representation comprises a tree structure representative of a grammatical structure of the utterance and a plurality of subtree vectors representative of semantic meanings of a plurality of intent subtrees of the at least one meaning representation; searching the at least one meaning representation of the utterance against an understanding model to extract intents and entities of the utterance, wherein the understanding model comprises plurality of meaning representations derived from sample utterances of an intent/entity model, wherein the intent/entity model associates defined intents with the sample utterances, and wherein the sample utterances encode defined entities as parameters of the defined intents within the intent/entity model; and providing the intents and entities of the utterance to a behavior engine (BE) of the agent automation system to perform at least one action in response to the intents and entities of the utterance. - View Dependent Claims (12, 13, 14, 15, 16)
-
-
17. A non-transitory, computer-readable medium storing instructions of an agent automation system executable by one or more processors of a computing system, wherein the instructions comprise:
-
instructions to generate a plurality of meaning representations of an understanding model for sample utterances of an intent/entity model, wherein the intent/entity model associates defined intents with the sample utterances, and wherein the sample utterances encode defined entities as parameters of the defined intents within the intent/entity model, and wherein each meaning representation of the plurality of meaning representations of the understanding model comprises at least one subtree vector; instructions to generate a meaning representation of an utterance model for an annotated utterance tree of a user utterance by combining a plurality of vectors of the annotated utterance tree using stored coefficients to calculate a respective subtree vector for each intent subtree of the annotated utterance tree, wherein each of the plurality of vectors is associated with a particular node or subtree that depends from each intent subtree, wherein the stored coefficients provide focus, attention, and magnification (FAM) to the calculation of each respective subtree vector, and wherein the meaning representation of the utterance model comprises a tree structure that indicates a syntactic structure of the user utterance and has at least one subtree vector indicating a semantic meaning of at least one intent subtree of the meaning representation; instructions to compare the at least one subtree vector of the meaning representation of the utterance model to the at least one subtree vector of the plurality of meaning representations of the understanding model to extract intents and entities of the user utterance; and instructions to provide the intents and entities of the utterance to a behavior engine (BE) of the agent automation system, wherein the BE performs one or more actions in response to the intents and entities of the user utterance. - View Dependent Claims (18, 19, 20)
-
Specification