Systems and methods for natural language processing using a plurality of natural language models
A virtual assistant server receives an utterance provided by an end user via a channel of a virtual assistant rendered in a client device. The virtual assistant server identifies a current-node of execution from a plurality of nodes of a conversation definition of the virtual assistant and identifies a first set of language models from a group of language models of the virtual assistant to interpret the utterance. Further, the virtual assistant server executes the first set of language models in an order based on the current-node until an intent of the utterance is determined. Subsequently, the virtual assistant server generates a response based on the intent and outputs the response to the client device.
1. A natural language processing method comprising:
receiving, by a virtual assistant server, an utterance provided by an end user via a channel of a virtual assistant rendered in a client device;
identifying, by the virtual assistant server, a current-node of execution from a plurality of nodes of a conversation definition of the virtual assistant;
identifying, by the virtual assistant server, a first set of language models from a group of language models of the virtual assistant based on the current-node to interpret the utterance;
executing, by the virtual assistant server, the first set of language models in an order based on the current-node until an intent of the utterance is determined;
generating, by the virtual assistant server, a response based on the intent; and
outputting, by the virtual assistant server, the response to the client device.
2. The method of claim 1 , wherein the first set of language models comprise one or more current-node language models or one or more global language models.
3. The method of claim 2 , further comprising determining the order by prioritizing the one or more current-node language models over the one or more global language models, when an execution of the conversation definition is at a node level.
4. The method of claim 2 , further comprising determining the order by prioritizing the one or more global language models over the one or more current-node language models when an execution of the conversation definition is not at a node level.
5. The method of claim 2 , wherein the one or more current-node language models comprise: a first language model associated with the current-node, a second language model associated with a group of nodes including the current-node, a third language model associated with a current-node intent, or a fourth language model associated with a group of intents including the current-node intent.
6. The method of claim 2 , wherein the one or more global language models comprise one or more language models of the virtual assistant.
7. The method of claim 1 , further comprising:
creating, by the virtual assistant server, the group of language models based on training provided to the virtual assistant.
8. A virtual assistant server comprising:
a processor; and
a memory coupled to the processor which is configured to be capable of executing programmed instructions stored in the memory to:
receive an utterance provided by an end user via a channel of a virtual assistant rendered in a client device;
identify a current-node of execution from a plurality of nodes of a conversation definition of the virtual assistant;
identify a first set of language models from a group of language models of the virtual assistant based on the current-node to interpret the utterance;
execute the first set of language models in an order based on the current-node until an intent of the utterance is determined;
generate a response based on the intent; and
output the response to the client device.
9. The virtual assistant server of claim 8 , wherein the first set of language models comprise one or more current-node language models or one or more global language models.
10. The virtual assistant server of claim 9 , wherein the processor is further configured to determine the order by prioritizing the one or more current-node language models over the one or more global language models, when an execution of the conversation definition is at a node level.
11. The virtual assistant server of claim 9 , wherein the processor is further configured to determine the order by prioritizing the one or more global language models over the one or more current-node language models when an execution of the conversation definition is not at a node level.
12. The virtual assistant server of claim 9 , wherein the one or more current-node language models comprise: a first language model associated with the current-node, a second language model associated with a group of nodes including the current-node, a third language model associated with a current-node intent, or a fourth language model associated with a group of intents including the current-node intent.
13. The virtual assistant server of claim 8 , wherein the one or more global language models comprise one or more language models of the virtual assistant.
14. The virtual assistant server of claim 8 , wherein the processor is further configured to create the group of language models based on training provided to the virtual assistant.
15. A non-transitory computer-readable medium having stored thereon instructions for enabling and orchestrating enterprise automation which when executed by a processor, causes the processor to:
receive an utterance provided by an end user via a channel of a virtual assistant rendered in a client device;
identify a current-node of execution from a plurality of nodes of a conversation definition of the virtual assistant;
identify a first set of language models from a group of language models of the virtual assistant based on the current-node to interpret the utterance;
execute the first set of language models in an order based on the current-node until an intent of the utterance is determined;
generate a response based on the intent; and
output the response to the client device.
16. The non-transitory computer-readable medium of claim 15 , wherein the first set of language models comprise one or more current-node language models or one or more global language models.
17. The non-transitory computer-readable medium of claim 16 , wherein the executable instructions when executed by the processor further causes the processor to: determine the order by prioritizing the one or more current-node language models over the one or more global language models, when an execution of the conversation definition is at a node level.
18. The non-transitory computer-readable medium of claim 16 , wherein the executable instructions when executed by the processor further causes processor to: determine the order by prioritizing the one or more global language models over the one or more current-node language models when an execution of the conversation definition is not at a node level.
19. The non-transitory computer-readable medium of claim 16 , wherein the one or more current-node language models comprise: a first language model associated with the current-node, a second language model associated with a group of nodes including the current-node, a third language model associated with a current-node intent, or a fourth language model associated with a group of intents including the current-node intent.
20. The non-transitory computer-readable medium of claim 15 , wherein the one or more global language models comprise one or more language models of the virtual assistant.
21. The non-transitory computer-readable medium of claim 15 , wherein the executable instructions when executed by the processor further causes processor to create the group of language models based on training provided to the virtual assistant.