Spoken control for user construction of complex behaviors

Patent metadata

Field	Value
Publication number	US-9324327-B2
Application number	US-201514694878-A
Country	US
Kind code	B2
Filing date	Apr 23, 2015
Priority date	Feb 29, 2012
Publication date	Apr 26, 2016
Grant date	Apr 26, 2016

Abstract

A device interface system is presented. Contemplated device interfaces allow for construction of complex device behaviors by aggregating device functions. The behaviors are triggered based on conditions derived from environmental data about the device.

First claim

What is claimed is:

1. A virtual assistant device comprising:
a memory;
at least one processor;
a dialog interface including at least one sensor and configured to:
accept a digital representation of a dialog interaction with a user via the at least sensor; and
derive an interpretation of the dialog interaction from signal characteristics of the digital representation; and

a behavior triggering module comprising software instruction stored in the memory and that configures the at least one processor to:
receive the interpretation from the dialog interface;
determine if the interpretation from dialog interface has sufficient information to construct a future device behavior;
instruct the dialog interface to construct a query to be presented to the user to collect additional information when it is determined that the interpretation does not have sufficient information;
identify a set of primitive device functions from a device function database based on the interpretation;
construct a future device behavior from the set of primitive device functions and the interpretation;
generate a trigger for the future device behavior as a function of the future device behavior and a device state associated with a target device;
query the device state associated with a target device to determine satisfaction of the trigger; and
configure the target device to exhibit the future device behavior upon satisfaction of the trigger.

2. The device of claim 1 , wherein the digital representation comprises a representation of a spoken utterance.

3. The device of claim 2 , wherein the digital representation comprise at least one of the following representations from the spoken utterance: a word, a token, a syntax, a modulation, a frequency, a tone, and an accent.

4. The device of claim 1 , wherein the digital representation comprises a representation of at least one of the following input signals: haptic data, tactile data, motion data, gesture data, and location data.

5. The device of claim 1 , wherein the interpretation comprises a set of key-value pairs.

6. The device of claim 1 , wherein the interpretation comprises a concept identifier.

7. The device of claim 1 , wherein the behavior triggering module further configures the processor to:
identify missing pieces of information with respect to the future device behavior; and
cause the dialog interface to construct a query for the missing pieces of information from the user.

8. The device of claim 1 , wherein the trigger comprises a primary trigger.

9. The device of claim 1 , wherein the trigger comprises an optional condition.

10. The device of claim 1 , wherein the behavior triggering module further configures the processor to query the device state at regular time intervals.

11. The device of claim 1 , wherein the device state comprises a past device state.

12. The device of claim 1 , wherein the device state comprises a further device state.

13. The device of claim 1 , wherein the device state includes at least one of the following at attributes: a location, a time, a battery level, a ringer mode, a ringer volume, a device environment attribute, a temperature, and a change in location.

14. The device of claim 1 , wherein the future device behavior is a member of a queue of device behaviors.

15. The device of claim 1 , further comprising a cell phone that includes the memory, the at least one processor, the dialog interface, and the behavior triggering module.

16. The device of claim 1 , further comprising a server that includes the memory, the at least one processor, the dialog interface, and the behavior triggering module.

17. The device of claim 1 , wherein the future device behavior comprises at least one of the following: a device command, a reservation, a temperature change, and a multimodal interaction.

18. The device of claim 1 , wherein the behavior triggering module further configures the processor to resolve ambiguities of a future device behavior based on an interaction history stored in an interaction history database.

19. The device of claim 1 , wherein the target device comprises the virtual assistant device.

Assignees

• Nant Holdings Ip Llc

Inventors

• Ehsani Farzad
• Witt-Ehsani Silke Maren
• Master Demitrios

Classifications

• G06F3/167 Primary

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• H04M1/72563

  Electricity · mapped topic

• H04M1/72566

  Electricity · mapped topic

• H04M2250/12

  including a sensor for measuring a physical value, e.g. temperature or motion · CPC title

• H04M1/72572

  Electricity · mapped topic