Deriving user intent from a prior communication

• US 10,795,944 B2
• Filed: 01/23/2017
• Issued: 10/06/2020
• Est. Priority Date: 09/22/2009
• Status: Active Grant

• Current Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Original Assignee: Verint Americas Incorporated (Verint Systems Incorporated)
• Inventors: Brown, Fred, Zartler, Mark, Miller, Tanya M.
• Primary Examiner(s): Chau, Dung K
• Application Number:
  US15/412,573
• Publication Number:
  US 20170132220A1
• Time in Patent Office: 1,352 Days
• Field of Search: 707737, 707771, 707706, 707755, 707999001, 707999002, 707999004, 704 9, 704275, 706 45
• CPC Class Codes: G06F 16/243 Natural language query formulation
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/258 Data format conversion from or to a database
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 16/43 Querying
• CPC Class Codes: G06F 16/93 Document management systems
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces

Abstract

User intent may be derived from a previous communication. For example, a text string for user input may be obtained. The text string may include a pronoun. Information from a communication received prior to receipt of the user input may be derived. The information may identify an individual. User intent may be derived from the text string and the information. This may include determining that the pronoun refers to the individual.

Claims

1. A method for operating a virtual agent, comprising:

obtaining, by an electronic computing device, a text string from a speech input received from a user, the text string including a pronoun;

deriving, by the electronic computing device, information from a communication received at the electronic device prior to receipt of the speech input, the information identifying an individual;

deriving, by the electronic computing device, a user intent from the text string and the information, the deriving the user intent including determining that the pronoun refers to the individual;

determining a response to the speech input; and

providing the response to the user via the virtual agent.

2. The method of claim 1, further comprising:

determining that the speech input is ambiguous user input; and

determining to use the communication based at least in part on determining that the speech input is ambiguous user input;

wherein the deriving the user intent is performed based at least in part on determining to use the communication.

3. The method of claim 2, wherein the determining that the speech input is ambiguous user input includes determining that the text string includes the pronoun.

4. The method of claim 1, further comprising:

providing for display information regarding the virtual agent to facilitate an interactive session between the virtual agent and the user;

wherein the response to the speech input is based at least in part on the user intent; and

wherein the response is provided via the virtual agent for display to the user.

5. The method of claim 1, further comprising:

performing a first task using a first parameter;

providing the response to the user based at least in part on performing the first task using the first parameter;

obtaining another text string from other speech input received from the user;

determining that the other text string is related to a second task different from the first task;

performing the second task using the first parameter; and

providing a second response to the user based at least in part on performing the second task using the first parameter.

6. The method of claim 1, wherein the communication comprises a message.

7. The method of claim 1, wherein the communication comprises a telephone call.

8. One or more non-transitory computer-readable media having computer-readable instructions thereon which, when executed by one or more processors, cause the one or more processors to perform operations comprising:

providing a virtual agent to facilitate an interactive session with a user;

obtaining user input, the user input identifying a pronoun;

deriving information from a communication received prior to receipt of the user input;

deriving a user intent from the user input and the information, the deriving the user intent including determining that the pronoun refers to the information;

determining a response to the speech input; and

providing the response via the virtual agent.

9. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

determining that the user input is ambiguous user input; and

determining to use the communication based at least in part on determining that the user input is ambiguous user input.

10. The one or more non-transitory computer-readable media of claim 9, wherein the determining that the user input is ambiguous user input includes determining that the user input includes the pronoun.

11. The one or more non-transitory computer-readable media of claim 8, wherein the operations further comprise:

performing a first task using a first parameter;

providing a first response to the user based at least in part on performing the first task using the first parameter;

obtaining other user input received from the user;

determining that the other user input is related to a second task different from the first task;

performing the second task using the first parameter; and

providing a second response to the user based at least in part on performing the second task using the first parameter.

12. The one or more non-transitory computer-readable media of claim 8, wherein the communication comprises a message.

13. The one or more non-transitory computer-readable media of claim 8, wherein the communication comprises a telephone call.

14. A system comprising:

one or more processors; and

memory communicatively coupled to the one or more processors and storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising;

obtaining a text string from a speech input received from a user, the text string including a pronoun;

deriving information from a communication received prior to receipt of the speech input, the information identifying an individual;

deriving a user intent from the text string and the information, the deriving the user intent including determining that the pronoun refers to the individual;

determining a response to the speech input; and

providing the response to the user via the virtual agent.

15. The system of claim 14, wherein the operations further comprise:

determining that the speech input is ambiguous user input; and

determining to use the communication based at least in part on determining that the speech input is ambiguous user input;

wherein the deriving the user intent is performed based at least in part on determining to use the communication.

16. The system of claim 15, wherein the determining that the speech input is ambiguous user input includes determining that the text string includes the pronoun.

17. The system of claim 14, wherein the operations further comprise:

providing for display information regarding the virtual agent to facilitate an interactive session between the virtual agent and the user;

wherein the response to the speech input is based at least in part on the user intent; and

wherein the response is provided via the virtual agent for display to the user.

18. The system of claim 14, wherein the operations further comprise:

performing a first task using a first parameter;

providing the response to the user based at least in part on performing the first task using the first parameter;

obtaining another text string from other speech input received from the user;

determining that the other text string is related to a second task different from the first task;

performing the second task using the first parameter; and

providing a second response to the user based at least in part on performing the second task using the first parameter.

19. The system of claim 14, wherein the communication comprises a message.

20. The system of claim 14, wherein the communication comprises a telephone call.