Personal virtual assistant

• US 6,757,362 B1
• Filed: 03/06/2000
• Issued: 06/29/2004
• Est. Priority Date: 03/06/2000
• Status: Expired due to Term

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Technology Corporation Miami Lakes FLA US
• Inventors: Sanders, Derek, Cooper, Robert S., Ulmer, Richard M., Peebles, Edward, McElroy, Jeff F., Rolandi, Walter
• Primary Examiner(s): FOSTER, ROLAND G
• Application Number:
  US09/519,075
• Time in Patent Office: 1,576 Days
• Field of Search: 379/70, 379/71, 379/72, 379/88.01, 379/88.04, 379/88.13, 379/88.16, 379/88-2-, 379/275, 704/231, 704/246, 704/270, 704/270.1
• US Class Current: 379/88.01
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04M 3/527 Centralised call answering arrangements not requiring operator intervention

Abstract

A computer-based virtual assistant the behavior of which can be changed by the user, comprising a voice user interface for inputting information into and receiving information from the virtual assistant by speech, a communications network, a virtual assistant application running on a remote computer, the remote computer being electronically coupled to the user interface via the communications network, wherein the behavior of the virtual assistant changes responsive to user input. A computer-based virtual assistant that also automatically adapts its behavior is disclosed, comprising a voice user interface for inputting information into and receiving information from the virtual assistant by speech, a communications network, a virtual assistant application running on a remote computer, the remote computer being electronically coupled to the user interface via the communications network, wherein the remote computer is programmed to automatically change the behavior of the virtual assistant responsive to input received by the virtual assistant. As detailed below, the virtual assistant adapts to the user in many different ways based on the input the virtual assistant receives. Such input could be user information, such as information about the user'"'"'s experience, the time between user sessions, the amount of time a user pauses when recording a message, the user'"'"'s emotional state, whether the user uses words associated with polite discourse, and the amount of time since a user provided input to the virtual assistant during a session.

Claims

1. A computer-based virtual assistant comprising:

a virtual assistant application running on a computer capable of receiving human voice communications from a remote user interface and transmitting a vocalization to a user interface;

the virtual assistant application determining a response to a verbal query or instruction received from a user interface, and the virtual assistant application selecting from amongst a plurality of word patterns each of which can communicate the response to the verbal query or instruction;

the plurality of word patterns including at least a first pattern of words and an alternative, second pattern of words, wherein the first pattern of words includes different words than the second pattern of words; and

the virtual assistant application selecting one of the first or second patterns of words and transmitting a vocalization of the selected one of the first or second patterns of words, wherein the selection between the first pattern of words and the second pattern of words is based upon a user controllable event, wherein the user controllable event is a perceived emotional state derived from an analysis of the received human voice communications.

2. The computer-based virtual assistant according to claim 1, wherein if the emotional state is determined to be angry, the virtual assistant application selects the first pattern of words, and wherein the first pattern of words includes more submissive words or phrases as compared to the second pattern of words.

3. The computer-based virtual assistant according to claim 2, wherein the submissive words or phrases include at least one of “

sorry,”

“

regret,” and

“

apologize.”

4. The computer-based virtual assistant according to claim 1, wherein the first pattern of words includes polite words or phrases as compared to the second pattern of words.

5. The computer-based virtual assistant according to claim 4, wherein the polite words or phrases include at least one of “

please,”

“

thank you,”

“

excuse,”

“

pardon,”

“

may I,” and

“

would you remind.”

6. The computer-based virtual assistant according to claim 1, wherein the first pattern of words uses less detail to convey the answer as compared to the second pattern of words.

7. The computer-based virtual assistant according to claim 1, wherein the virtual assistant includes a communications interface to communicate over a network, and the network is one of a public switched telephone network, a packet switched telephone network, and a wireless telecommunications network.

8. The computer-based virtual assistant according to claim 7, wherein the communication interface is configured to receive DTMF tones over the network.

19. The computer-based virtual assistant according to claim 1, wherein the response communicated by the first or second plurality of words conveys at least one of a voice-mail, a page, an email, a fax, a scheduled appointment, weather data, travel data, financial data, and news.

20. The computer-based virtual assistant according to claim 1, wherein the response communicated by the first or second plurality of words is obtained from the user'"'"'s company'"'"'s intranet and conveys at least one of customer data, shipping data, inventory information, sales reports, and financial data.

9. A method of operating a computer-based virtual assistant application program comprising:

receiving human voice communications from a user interface;

determining a response to a verbal query or instruction received from the user interface;

selecting from amongst a plurality of word patterns which can communicate the response to the verbal query or instruction, the plurality of word patterns including at least a first pattern of words and an alternative, second pattern of words, wherein the first pattern of words includes different words than the second pattern of words;

evaluating a user controllable event;

selecting one of the first or second patterns or words, with the selection being based upon the user controllable event; and

transmitting a vocalization of the selected one of the first or second patterns of words to the user interface, wherein said evaluating step includes evaluating a perceived emotional state of the user, based upon the received human voice communications.

10. The method according to claim 9, wherein if the emotional state is evaluated to be angry, the virtual assistant selects the first pattern of words, and wherein the first pattern of words includes more submissive words or phrases as compared to the second pattern of words.

11. The method according to claim 10, wherein the submissive words or phrases include at least one of “

sorry,”

“

regret,” and

“

apologize.”

12. The method according to claim 9, wherein the first pattern of words includes polite words or phrases as compared to the second pattern of words.

13. The method according to claim 12, wherein the polite words or phrases include at least one of “

please,”

“

thank you,”

“

excuse,”

“

pardon,”

“

may I,” and

“

would you remind.”

14. The method according to claim 9, wherein the first pattern of words uses less detail to convey the answer as compared to the second pattern of words.

15. The method according to claim 9, wherein said transmitting step occurs over a network.

16. The method according to claim 9, wherein said transmitting step occurs over a public switched telephone network.

17. The method according to claim 9, wherein said transmitting step occurs over a packet switched telephone network.

18. The method according to claim 9, wherein said transmitting step occurs over a wireless telecommunications network.

45. The method according to claim 9, wherein the response communicated by the first or second plurality of words conveys at least one of a voice-mail, a page, an email, a fax, a scheduled appointment, weather data, travel data, financial data, and news.

46. The method according to claim 9, wherein the response communicated by the first or second plurality of words is obtained from the user'"'"'s company'"'"'s intranet and conveys at least one of customer data, shipping data, inventory information, sales reports, and financial data.

21. A computer-based virtual assistant comprising:

a virtual assistant application running on a computer capable of receiving human voice communications from a remote user interface and transmitting a vocalization to a user interface;

the virtual assistant application determining a response to a verbal query or instruction received from a user interface, and the virtual assistant application selecting from amongst a plurality of word patterns each of which can communicate the response to the verbal query or instruction;

the plurality of word patterns including at least a first pattern of words and an alternative, second pattern of words, wherein the first pattern of words includes different words than the second pattern of words; and

the virtual assistant application selecting one of the first or second patterns of words and transmitting a vocalization of the selected one of the first or second patterns of words, wherein the selection between the first pattern of words and the second pattern of words is based upon a user controllable event, wherein the user controllable event is the number of times the virtual assistant is queried in a given interval of time by the user.

22. The computer-based virtual assistant according to claim 21, wherein after the virtual assistant is queried more than a predetermined number of times in the given interval of time, the virtual assistant selects the first pattern of words, and wherein the first pattern of words uses less detail to convey the response as compared to the second pattern of words.

23. The computer-based virtual assistant according to claim 21, wherein the number of times the virtual assistant is queried in the given interval of time is used to set a variable indicative a competence level of the user in dealing with the virtual assistant.

24. The computer-based virtual assistant according to claim 23, wherein the competence level is one of novice, experienced and expert.

25. The computer-based virtual assistant according to claim 21, wherein the given interval of time is one day.

26. The computer-based virtual assistant according to claim 21, wherein the first pattern of words includes polite words or phrases as compared to the second pattern of words.

27. The computer-based virtual assistant according to claim 26, wherein the polite words or phrases include at least one of “

please,”

“

thank you,”

“

excuse,”

“

pardon,”

“

may I,” and

“

would you remind.”

28. The computer-based virtual assistant according to claim 21, wherein the first pattern of words uses less detail to convey the answer as compared to the second pattern of words.

29. The computer-based virtual assistant according to claim 21, wherein the virtual assistant includes a communications interface to communicate over a network, and the network is one of a public switched telephone network, a packet switched telephone network, and a wireless telecommunications network.

30. The computer-based virtual assistant according to claim 29, wherein the communication interface is configured to receive DTMF tones over the network.

47. The computer-based virtual assistant according to claim 21, wherein the response communicated by the first or second plurality of words conveys at least one of a voice-mail, a page, an email, a fax, a scheduled appointment, weather data, travel data, financial data, and news.

48. The computer-based virtual assistant according to claim 21, wherein the response communicated by the first or second plurality of words is obtained from the user'"'"'s company'"'"'s intranet and conveys at least one of customer data, shipping data, inventory information, sales reports, and financial data.

31. A method of operating a computer-based virtual assistant application program comprising:

receiving human voice communications from a user interface;

determining a response to a verbal query or instruction received from the user interface;

selecting from amongst a plurality of word patterns which can communicate the response to the verbal query or instruction, the plurality of word patterns including at least a first pattern of words and an alternative, second pattern of words, wherein the first pattern of words includes different words than the second pattern of words;

evaluating a user controllable event;

selecting one of the first or second patterns or words, with the selection being based upon the user controllable event; and

transmitting a vocalization of the selected one of the first or second patterns of words to the user interface, wherein the user controllable event is the number of times the virtual assistant is queried in a given interval of time by the user.

32. The method according to claim 31, wherein after the virtual assistant is queried more than a predetermined number of times in the given interval of time, the virtual assistant selects the first pattern of words, and wherein the first pattern of words uses less detail to convey the response as compared to the second pattern of words.

33. The method according to claim 31, wherein the number of times the virtual assistant is queried in a given interval of time is used to set a variable indicative of a competence level of the user in dealing with the virtual assistant.

34. The method according to claim 33, wherein the competence level is one of novice, experienced and expert.

35. The method according to claim 31, wherein the given interval of time is one day.

36. The method according to claim 31, wherein the first pattern of words includes polite words or phrases as compared to the second pattern of words.

37. The method according to claim 36, wherein the polite words or phrases include at least one of “

please,”

“

thank you,”

“

excuse,”

“

pardon,”

“

may I,” and

“

would you remind.”

38. The method according to claim 31, wherein the first pattern of words uses less detail to convey the answer as compared to the second pattern of words.

39. The method according to claim 31, wherein said transmitting step occurs over a network.

40. The method according to claim 31, wherein said transmitting step occurs over a public switched telephone network.

41. The method according to claim 31, wherein said transmitting step occurs over a packet switched telephone network.

42. The method according to claim 31, wherein said transmitting step occurs over a wireless telecommunications network.

43. The method according to claim 31, wherein the response communicated by the first or second plurality of words conveys at least one of a voice-mail, a page, an email, a fax, a scheduled appointment, weather data, travel data, financial data, and news.

44. The method according to claim 31, wherein the response communicated by the first or second plurality of words is obtained from the user'"'"'s company'"'"'s intranet and conveys at least one of customer data, shipping data, inventory information, sales reports, and financial data.