System and method of generating responses to text-based messages

• US 8,082,151 B2
• Filed: 09/18/2007
• Issued: 12/20/2011
• Est. Priority Date: 09/18/2007
• Status: Active Grant

• Current Assignee: Interactions, LLC
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Bangalore, Srinivas, Gilbert, Mazin, Gupta, Narendra
• Primary Examiner(s): Abebe, Daniel D
• Application Number:
  US11/857,036
• Publication Number:
  US 20090076795A1
• Time in Patent Office: 1,554 Days
• Field of Search: 704/251, 704/257, 709/223
• US Class Current: 704/251
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

In accordance with one aspect of the present invention, an automated method of and system for generating a response to a text-based natural language message is disclosed. The method includes identifying a sentence in the text-based natural language message. Also, identifying an input clause in the sentence. Further, comparing the input clause to a previously received clause, where the previously received clause is correlated with a previously generated response message. Additionally, generating an output response message based on the previously generated response message. The system includes means for performing the method steps.

Claims

1. A method of generating a response to a text-based natural language message, comprising:

identifying a sentence in the text-based natural language message;

identifying an input clause in the sentence;

comparing the input clause to a previously received clause, the previously received clause being correlated with a previously generated response message; and

generating an output response message based on the previously generated response message, the output response message being derived from a plurality of previously generated response clauses.

2. A method according to claim 1, further comprising storing the previously received clause and the previously generated response in a database.

3. A method according to claim 1, further comprising parsing the input clause, thereby defining a relationship between words in the input clause.

4. A method according to claim 1, further comprising identifying a best match clause for the input clause, the best match clause having a threshold degree of match and being non-identical to the input clause, the best match clause being derived from the previously received clause.

5. A method according to claim 4, wherein the best match clause is identified using two or more associated clauses from the text-based natural language message to match similarly associated clauses from a previously received message associated with the previously received clause.

6. A method according to claim 1, further comprises correlating the previously received clause with a one of the plurality of previously generated response clauses.

7. A method according to claim 1, further comprising:

associating a semantic tag with the input clause, the semantic tag being an abbreviation associated with the input clause; and

identifying an output response clause based on the associated semantic tag.

8. A method according to claim 7, further comprising correlating the semantic tag with the previously received clause.

9. A method according to claim 1, further comprising displaying the output response message.

10. A method according to claim 9, further comprising transmitting the output response message displayed to the customer service agent.

11. A method according to claim 1, wherein the plurality of previously generated response clauses include a first response clause and a second response clause, the first response clause being derived from a first previously generated response message, the second response clause being derived from a second previously generated response message different from the first previously generated response message.

12. A method according to claim 1, wherein the comparison of the input clause and the previously received clause includes matching a first classifier generated for the input clause with a second classifier generated for the previously received clause.

13. A non-transitory computer-readable storage medium storing instructions that, when executed by a processing device, causes the processing device to generate a response to a text-based natural language message by:

identifying a sentence in the text-based natural language message;

identifying an input clause in the sentence;

comparing the input clause to a previously received clause, the previously received clause being correlated with a previously generated response message; and

generating an output response message based on the previously generated response message, the output response message being derived from a plurality of previously generated response clauses.

14. A non-transitory computer-readable storage medium according to claim 13, wherein storing instructions that, when executed by a processing device, causes the processing device to generate a response to a text-based natural language message by parsing the input clause, thereby defining a relationship between words in the input clause.

15. A non-transitory computer-readable storage medium according to claim 13 storing instructions that, when executed by a processing device, causes the processing device to generate a response to a text-based natural language message by identifying a best match clause for the input clause, the best match clause having a threshold degree of match and being non-identical to the input clause, the best match clause being derived from the previously received clause.

16. A non-transitory computer-readable storage medium according to claim 13 storing instructions that, when executed by a processing device, causes the processing device to generate a response to a text-based natural language message by associating a semantic tag with the input clause, the semantic tag being an abbreviation associated with the input clause;

and

identifying an output response clause based on the associated semantic tag.

17. A non-transitory computer-readable storage medium according to claim 16 storing instructions that, when executed by a processing device, causes the processing device to generate a response to a text-based natural language message by correlating the semantic tag with the previously received clause.

18. A non-transitory computer-readable storage medium according to claim 13 storing instructions that, when executed by a processing device, causes the processing device to generate a response to a text-based natural language message by, wherein the plurality of previously generated response clauses include a first response clause and a second response clause, the first response clause being derived from a first previously generated response message, the second response clause being derived from a second previously generated response message different from the first previously generated response message.

19. A non-transitory computer-readable storage medium according to claim 13 storing instructions that, when executed by a processing device, causes the processing device to match a first classifier generated for the input clause with a second classifier generated for the previously received clause.

20. A non-transitory computer-readable storage medium according to claim 15 storing instructions that, when executed by a processing device, causes the processing device to identify the best match clause using two or more associated clauses from the text-based natural language message to match similarly associated clauses from a previously received message associated with the previously received clause.