SYSTEMS AND METHODS FOR PARSING MULTIPLE INTENTS IN NATURAL LANGUAGE SPEECH

1 . A computer system for generating responses to a verbal input by parsing separate intents in natural language speech, the computer system comprising at least one processor in communication with at least one memory device, the at least one processor is programmed to:

receive a verbal statement of a user including a plurality of words;

generate a constituency tree structure based upon the verbal statement;

detect one or more splits in the verbal statement by parsing the constituency tree structure based upon at least one of a plurality of grammar-related rules;

divide the verbal statement into a plurality of utterances based upon the one or more splits;

analyze each of the plurality of utterances to identify a plurality of intents, wherein each of the plurality of intents corresponds to one of the plurality of utterances; and

generate a response based on the plurality of intents.

2 . The computer system of claim 1 , wherein the constituency tree structure includes a plurality of nodes representing the plurality of words of the verbal statement.

3 . The computer system of claim 1 , wherein the at least one processor is further configured to:

determine an order in which to process each the plurality of intents based upon stored business logic and pre-requisites; and

process each of the plurality of intents in the determined order to generate the response.

4 . The computer system of claim 1 , wherein the plurality of grammar-related rules includes a coordinating conjunction rule, a preposition or subordinating conjunction rule, a wh-adverb rule, and a word ‘to’ rule.

5 . The computer system of claim 1 , wherein the at least one processor is further programmed to:

translate the generated response into speech; and

transmit the response in speech to the user via an audio stream.

6 . The computer system of claim 1 , wherein the at least one processor is further programmed to:

determine additional data needed from the user based upon the plurality of intents;

generate a request for the additional data;

translate the request into speech; and

transmit the request in speech to a user computer device.

7 . The computer system of claim 1 , wherein the verbal statement is received via at least one of a phone call, a chat program, and a video chat.

8 . The computer system of claim 1 , wherein the at least one processor is further programmed to:

label each of the plurality of words in the verbal statement using one or more labels; and

detect the one or more splits further based upon the one or more labels associated with the plurality of words in the verbal statement.

9 . The computer system of claim 8 , wherein the at least one processor is further programmed to reduce the one or more splits based upon a distance between each of the one or more splits within the verbal statement.

10 . A computer-implemented method for generating responses to a verbal input by parsing separate intents in natural language speech, the computer-implemented performed by a computer system including at least one processor in communication with at least one memory device, the computer-implemented method comprising:

receiving, by the at least one processor, a verbal statement of a user including a plurality of words;

generating, by the at least one processor, a constituency tree structure based upon the verbal statement;

detecting, by the at least one processor, one or more splits in the verbal statement by parsing the constituency tree structure based upon at least one of a plurality of grammar-related rules;

dividing, by the at least one processor, the verbal statement into a plurality of utterances based upon the one or more splits;

analyzing, by the at least one processor, each of the plurality of utterances to identify a plurality of intents, wherein each of the plurality of intents corresponds to one of the plurality of utterances; and

generating, by the at least one processor, a response based on the plurality of intents.

11 . The computer-implemented method of claim 10 , wherein the constituency tree structure includes a plurality of nodes representing the plurality of words of the verbal statement.

12 . The computer-implemented method of claim 10 , further comprising:

determining, by the at least one processor, an order in which to process each the plurality of intents based upon stored business logic and pre-requisites; and

processing, by the at least one processor, each of the plurality of intents in the determined order to generate the response.

13 . The computer-implemented method of claim 10 , wherein the plurality of grammar-related rules includes a coordinating conjunction rule, a preposition or subordinating conjunction rule, a wh-adverb rule, and a word ‘to’ rule.

14 . The computer-implemented method of claim 10 , further comprising:

translating, by the at least one processor, the generated response into speech; and

transmitting, by the at least one processor, the response in speech to the user via an audio stream.

15 . The computer-implemented method of claim 10 , further comprising:

determining, by the at least one processor, additional data needed from the user based upon the plurality of intents;

generating, by the at least one processor, a request for the additional data;

translating, by the at least one processor, the request into speech; and

transmitting, by the at least one processor, the request in speech to a user computer device.

16 . The computer-implemented method of claim 10 , wherein the verbal statement is received via at least one of a phone call, a chat program, and a video chat.

17 . The computer-implemented method of claim 10 , further comprising:

labeling, by the at least one processor, each of the plurality of words in the verbal statement using one or more labels; and

detecting, by the at least one processor, the one or more splits further based upon the one or more labels associated with the plurality of words in the verbal statement.

18 . The computer-implemented method of claim 17 , further comprising reducing, by the at least one processor, the one or more splits based upon a distance between each of the one or more splits within the verbal statement.

19 . At least one non-transitory computer-readable media having computer-executable instructions embodied thereon for generating responses to a verbal input by parsing separate intents in natural language speech, wherein when executed by at least one processor in communication with at least one memory device, the computer-executable instructions cause the at least one processor to:

receive a verbal statement of a user including a plurality of words;

generate a constituency tree structure based upon the verbal statement;

detect one or more splits in the verbal statement by parsing the constituency tree structure based upon at least one of a plurality of grammar-related rules;

divide the verbal statement into a plurality of utterances based upon the one or more splits;

analyze each of the plurality of utterances to identify a plurality of intents, wherein each of the plurality of intents corresponds to one of the plurality of utterances; and

generate a response based on the plurality of intents.

20 . The at least one non-transitory computer-readable media of claim 19 , wherein the constituency tree structure includes a plurality of nodes representing the plurality of words of the verbal statement.