GENERATING DIALOG RECOMMENDATIONS FOR CHAT INFORMATION SYSTEMS BASED ON USER INTERACTION AND ENVIRONMENTAL DATA

• US 20160217784A1
• Filed: 06/27/2013
• Published: 07/28/2016
• Est. Priority Date: 06/27/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Ooo Speaktoit
• Inventors: GELFENBEYN, llya, GONCHARUK, Artem, PLATONOV, IIya Andreevich, SIROTIN, Pavel Aleksandrovich, GELFENBEYN, Olga Aleksandrovna
• Granted Patent: US 10,026,400 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/32 Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Disclosed is the technology for dynamic and intelligent generation of dialog recommendations for the users of chat information systems based on multiple criteria. An example method may include receiving a speech-based user input, recognizing at least a part of the speech-based user input to generate a recognized input, and providing at least one response to the recognized input. The method may further include identifying at least one triggering event, generating at least one dialog recommendation based at least in part on the identification, and presenting the at least one dialog recommendation to a user via a user device.

Claims

1. A method for delivering dialog recommendations in a chat information system (CIS), the method comprising:

receiving, by a processor operatively coupled to a memory, a speech-based user input;

recognizing, by the processor, at least a part of the speech-based user input to generate a recognized input;

providing, by the processor, at least one response to the recognized input;

identifying, by the processor, at least one triggering event;

based at least in part on the identification, generating, by the processor, at least one dialog recommendation; and

presenting, by the processor, the at least one dialog recommendation to a user via a user device.

2. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, one or more predetermined words in the recognized input.

3. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, a type of user-CIS dialog context.

4. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, one or more CIS operating modes never used by the user.

5. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, one or more CIS operating modes, which the user has not used over a predetermined period of time.

6. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, one or more events associated with at least one social networking or blogging site.

7. The method of claim 1, further comprising:

determining, by the processor, a current time associated with the user device; and

wherein the identifying of the at least one triggering event is based at least in part on the current time.

8. The method of claim 7, wherein the identifying of the at least one triggering event includes recognizing, by the processor, one or more calendar events scheduled within a predetermined time period from the current time.

9. The method of claim 1, further comprising:

determining, by the processor, a current geographical location associated with the user device; and

wherein the identifying of the at least one triggering event is based at least in part on the current geographical location.

10. The method of claim 9, wherein the identifying of the at least one triggering event includes establishing, by the processor, presence of the user device within a predetermined geographical area.

11. The method of claim 9, wherein the identifying of the at least one triggering event includes recognizing, by the processor, presence of one or more peripheral electronic devices within a predetermined distance from the current geographical location associated with the user device.

12. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, presence of the user device within one or more wireless networks.

13. The method of claim 1, wherein the identifying of the at least one triggering event includes recognizing, by the processor, behavior similar to user-CIS interactions associated with at least one another user.

14. The method of claim 1, further comprising:

receiving, by the processor, a second speech-based user input, wherein the second speech-based user input is associated with the at least one dialog recommendation;

performing, by the processor, automatic speech recognition of at least a part of the second speech-based user input to generate a second recognized input; and

providing, by the processor, a second response to the second recognized input.

15. The method of claim 1, wherein the at least one dialog recommendation is delivered to the user device as an actionable message.

16. The method of claim 15, further comprising:

receiving, by the processor, a user selection of the at least one dialog recommendation; and

generating, by the processor, a response to the user selection.

17. The method of claim 1, wherein the recognizing of the at least a part of the speech-based user input to generate a recognized input includes performing automatic speech recognition utilizing one or more speech recognizers.

18. The method of claim 17, wherein the one or more speech recognizers include one or more of the following:

a pattern-based speech recognizer, a free-dictation recognizer, an address book based recognizer, and a dynamically created recognizer.

19. A chat information system (CIS), the method comprising:

a speech recognition module configured to receive a speech-based user input and recognize at least a part of the speech-based user input and generate a recognized input;

a dialog manager configured to generate at least one response to the recognized input;

an event manager configured to identify at least one triggering event; and

a recommendation manager configured to generate at least one dialog recommendation based at least in part on the identification of the at least one triggering event.

20. The CIS of claim 19, further comprising an output renderer configured to provide the least one response and the at least one dialog recommendation to a user via a user device.

21. The CIS of claim 20, wherein the output renderer includes a text-to-speech generator.

22. The CIS of claim 20, wherein the output renderer is configured to provide the at least one response as an audio message.

23. The CIS of claim 20, wherein the output renderer is configured to provide the at least one dialog recommendation as a text message or an image message.

24. The CIS of claim 19, wherein the speech recognition module includes a plurality of speech recognizers.

25. The CIS of claim 19, wherein at least one of the speech recognition module, the dialog manager, the event manager, and the recommendation manager is a distributed computing module.

26. The CIS of claim 19, wherein at least one of the speech recognition module, the dialog manager, the event manager, and the recommendation manager is a cloud computing module.

27. A non-transitory processor-readable medium having instructions stored thereon, which when executed by one or more processors, cause the one or more processors to implement a method for delivering dialog recommendations in a chat information system (CIS), the method comprising:

receiving a speech-based user input;

recognizing at least a part of the speech-based user input to generate a recognized input;

providing at least one response to the recognized input;

identifying at least one triggering event;

based at least in part on the identification, generating at least one dialog recommendation; and

presenting the at least one dialog recommendation to a user via a user device.