Systems and methods for parsing multiple intents in natural language speech
A system for parsing separate intents in natural language speech configured to (i) receive, from the user computer device, a verbal statement of the user including a plurality of words; (ii) translate the verbal statement into text; (iii) label each of the plurality of words in the verbal statement; (iv) detect one or more potential splits in the verbal statement; (v) divide the verbal statement into a plurality of intents based upon the one or more potential splits; and (vi) generate a response based upon the plurality of intents.
1. A computer system for parsing separate intents in natural language speech, the computer system including 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, wherein the verbal statement is a compound statement including a plurality of intents;
generate a constituency tree structure based upon the verbal statement, the constituency tree structure including a plurality of nodes representing words of the verbal statement;
detect one or more potential 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 potential splits, wherein each of the plurality of utterances comprises a phrase;
analyze each of the plurality of utterances to identify the plurality of intents of the compound statement, wherein each of the plurality of intents comprises a single idea;
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.
2. The computer system in accordance with claim 1 , wherein the at least one processor is further programmed to:
detect one or more potential splits in the verbal statement by parsing the verbal statement based upon at least one of a plurality of grammar-related rules, 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.
3. The computer system in accordance with claim 1 , wherein the at least one processor is further programmed to:
generate a response to the verbal statement of the user based upon the plurality of intents;
translate the response into speech; and
transmit the response in speech to the user via an audio stream.
4. The computer system in accordance with 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.
5. The computer system in accordance with claim 1 , wherein the verbal statement is received via at least one of a phone call, a chat program, and a video chat.
6. The computer system in accordance with claim 1 , wherein the at least one processor is further programmed to detect the one or more potential splits based upon a word structure of the verbal statement.
7. The computer system in accordance with 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 a plurality of potential splits based on the one or more labels associated with the plurality of words in the verbal statement.
8. The computer system in accordance with claim 7 , wherein the at least one processor is further programmed to reduce the plurality of potential splits based upon a distance between each of the plurality of potential splits within the verbal statement.
9. A computer-implemented method for parsing separate intents in natural language speech, the method implemented by a computer device including at least one processor in communication with at least one memory device, the method comprising:
receiving a verbal statement of a user including a plurality of words, wherein the verbal statement is a compound statement including a plurality of intents;
generating a constituency tree structure based upon the verbal statement, the constituency tree structure including a plurality of nodes representing words of the verbal statement;
detecting one or more potential splits in the verbal statement by parsing the verbal statement based upon at least one of a plurality of grammar-related rules;
dividing the verbal statement into a plurality of utterances based upon the one or more potential splits, wherein each of the plurality of utterances comprises a phrase;
analyze each of the plurality of utterances to identify the plurality of intents of the compound statement, wherein each of the plurality of intents comprises a single idea;
determining an order in which to process each the plurality of intents based upon stored business logic and pre-requisites; and
processing each of the plurality of intents in the determined order.
10. The computer-implemented method in accordance with claim 9 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.
11. The computer-implemented method in accordance with claim 9 further comprising:
generating a response to the verbal statement of the user based upon the plurality of intents;
translating the response into speech; and
transmitting the response in speech to the user via an audio stream.
12. The computer-implemented method in accordance with claim 9 further comprising:
determining additional data needed from the user based upon the plurality of intents;
generating a request for the additional data;
translating the request into speech; and
transmitting the request in speech to a user computer device.
13. The computer-implemented method in accordance with claim 9 , wherein the verbal statement is received via at least one of a phone call, a chat program, and a video chat.
14. The computer-implemented method in accordance with claim 9 further comprising detecting the one or more potential splits based upon a word structure of the verbal statement.
15. The computer-implemented method in accordance with claim 9 further comprising:
labeling each of the plurality of words in the verbal statement using one or more labels; and
detecting a plurality of potential splits based on the one or more labels associated with the plurality of words in the verbal statement.
16. The computer-implemented method in accordance with claim 15 , further comprising reducing the plurality of potential splits based upon a distance between each of the plurality of potential splits within the verbal statement.
17. A non-transitory computer readable medium having computer-executable instructions embodied thereon for parsing separate intents in natural language speech, wherein when executed by at least one processor, the computer-executable instructions cause the at least one processor to:
receive a verbal statement of a user including a plurality of words, wherein the verbal statement is a compound statement including a plurality of intents;
generate a constituency tree structure based upon the verbal statement, the constituency tree structure including a plurality of nodes representing words of the verbal statement;
detect one or more potential splits in the verbal statement by parsing the verbal statement 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 potential splits, wherein each of the plurality of utterances comprises a phrase;
analyze each of the plurality of utterances to identify the plurality of intents of the compound statement, wherein each of the plurality of intents comprises a single idea;
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.
18. The computer readable medium in accordance with claim 17 , wherein the computer-executable instructions further cause the at least one processor to:
detect one or more potential splits in the verbal statement by parsing the verbal statement based upon at least one of a plurality of grammar-related rules, 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; and
generate a response to the verbal statement of the user based upon the plurality of intents.
19. The computer readable medium in accordance with claim 17 , wherein the computer-executable instructions further cause the at least one processor 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.
20. The computer readable medium in accordance with claim 17 , wherein the computer-executable instructions further cause the at least one processor to:
receive the verbal statement via at least one of a phone call, a chat program, and a video chat; and
detect the one or more potential splits based upon a word structure of the verbal statement.