PROVIDING A PERSONAL ASSISTANT MODULE WITH A SELECTIVELY-TRAVERSABLE STATE MACHINE

• US 20170359707A1
• Filed: 06/08/2016
• Published: 12/14/2017
• Est. Priority Date: 06/08/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Diaconu, Adrian, Qian, Jing, Whyte, Jack, Ma, Ning, Yehoshua, Shir
• Granted Patent: US 10,462,619 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 9/54 Interprogram communication
• 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 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: H04W 4/16 Communication-related supplementary services, e.g. call-transfer or call-hold
• CPC Class Codes: H04W 76/10 Connection setup
• CPC Class Codes: H04W 88/02 Terminal devices

Abstract

Techniques are described herein for leveraging an online semantic processor to generate a finite state machine to be delivered to and implemented on a resource-constrained device. In various implementations, a user request may be received by a personal assistant module. Data indicative of the user request may be uploaded, e.g., by the personal assistant module, to an online semantic processor. Data may be received, e.g., by the personal assistant module, from the online semantic processor. The received data may represent a state machine having a plurality of candidate states of the personal assistant module. Each candidate state may be potentially responsive to the request. Resources local to the resource-constrained device may be analyzed to ascertain signal(s) unavailable to the online semantic processor. The personal assistant module may then transition to a given state of the plurality of candidate states. The given state may be selected based on the signal(s).

Claims

1. A computer-implemented method, comprising:

receiving, by a personal assistant module operated by a resource-constrained device, a request;

uploading, by the personal assistant module, data indicative of the request to an online semantic processor;

receiving, by the personal assistant module, from the online semantic processor, data representing a state machine comprising a plurality of candidate states of the personal assistant module, wherein each candidate state is potentially responsive to the request;

analyzing, by the personal assistant module, one or more resources local to the resource-constrained device to ascertain one or more signals unavailable to the online semantic processor; and

transitioning, by the personal assistant module, to a given state of the plurality of candidate states, wherein the given state is selected based on the one or more signals.

2. The computer-implemented method of claim 1, wherein the given state comprises an output to be delivered by the personal assistant module, wherein the output includes a solicitation for one or more inputs.

3. The computer-implemented method of claim 2, further comprising transitioning, by the personal assistant module, from the given state to another state of the plurality of candidate states based on one or more inputs received by the personal assistant module in response to the solicitation.

4. The computer-implemented method of claim 2, wherein the one or more resources local to the resource-constrained device comprise a contact list of a user that operates the resource-constrained device.

5. The computer-implemented method of claim 4, further comprising disambiguating, by the personal assistant module, between two or more contacts in the contact list based on the one or more inputs.

6. The computer-implemented method of claim 4, further comprising disambiguating, by the personal assistant module, between two or more addresses or telephone numbers associated with a single contact in the contact list based on the one or more inputs.

7. The computer-implemented method of claim 4, wherein the request comprises a request to initiate a telephone call with an individual in the contact list.

8. The computer-implemented method of claim 4, wherein the request comprises a request to send a message to an individual in the contact list.

9. The computer-implemented method of claim 4, wherein the request comprises a request for directions to a location associated with an individual in the contact list.

10. The computer-implemented method of claim 2, wherein the one or more resources local to the resource-constrained device comprise a plurality of applications installed on the resource-constrained device, and the method further comprises disambiguating, by the personal assistant module, between two or more of the plurality of applications based on the one or more inputs.

11. The computer-implemented method of claim 2, wherein the one or more resources local to the resource-constrained device comprise a plurality of media files stored in memory of the resource-constrained device, and the method further comprises disambiguating, by the personal assistant module, between two or more of the plurality of media files based on the one or more inputs.

12. The computer-implemented method of claim 1, wherein the one or more signals comprise one or more records of an interaction history between a user and the personal assistant module.

13. The computer-implemented method of claim 1, wherein the one or more signals comprise one or more statistics based on the one or more records of an interaction history between a user and the personal assistant module.

14. The computer-implemented method of claim 1, wherein the one or more signals comprise position coordinates of the resource-constrained device.

16. The online semantic processor of claim 14, further comprising instructions to analyze one or more online resources associated with the user to ascertain one or more information signals, wherein the state machine is generated based at least in part on the one or more information signals.

15. An online semantic processor, comprising:

a communication interface;

one or more processors operably coupled with the communication interface; and

memory operably coupled with the one or more processors, the memory storing instructions that, when executed by the one or more processors, cause the one or more processors to;

receive, from a personal assistant module operating on a resource-constrained device, via the communication interface, data indicative of a user request;

generate a state machine comprising a plurality of candidate states of the personal assistant module, wherein each candidate state is potentially responsive to the request depending on one or more signals that are unavailable to the online semantic processor and ascertainable from resources local to the resource-constrained device; and

download, to the resource-constrained device, via the communication interface, data representing the state machine.

17. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by a resource-constrained device, cause the resource constrained device to operate a personal assistant module that performs the following operations:

receiving a user request;

uploading data indicative of the user request to an online semantic processor;

receiving, from the online semantic processor, data representing a state machine comprising a plurality of candidate states of the personal assistant module, wherein each candidate state is potentially responsive to the request;

analyzing one or more resources local to the resource-constrained device to ascertain one or more signals unavailable to the online semantic processor; and

transitioning to a given state of the plurality of candidate states, wherein the given state is selected based on the one or more signals.

18. The at least one non-transitory computer-readable medium of claim 17, wherein the given state comprises an output to be delivered by the personal assistant module, wherein the output includes a solicitation for one or more inputs.

19. The at least one non-transitory computer-readable medium of claim 18, wherein the personal assistant module is further configured to transition from the given state to another state of the plurality of candidate states based on one or more inputs received by the personal assistant module in response to the solicitation.

20. The at least one non-transitory computer-readable medium of claim 18, wherein the one or more resources local to the resource-constrained device comprise a contact list of a user that operates the resource-constrained device.