IP Library Granted Patent US 11,734,515
Granted Patent B2
US 11,734,515 · App. 17/492,863 · Granted Aug 22, 2023

Adaptive natural language steganography and watermarking for virtual assistants

Inventors: Sebastian Millius (Zurich, CH); Sandro Feuz (Zurich, CH)
Assignee: GOOGLE LLC
G06F40/30G10L15/1815G10L15/22G10L2015/223
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,734,515
App. No.
17/492,863
Granted
Aug 22, 2023
Kind
B2
Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for announcing and detecting automated conversation are disclosed. One of the methods includes initiating, over a natural language communication channel, a conversation with a communication participant using a natural language communication method that includes a dialogue of natural language communications. The communication participant is determined to be automated using a pre-defined adaptive interactive protocol that specifies natural language linguistic transformations defined in a sequence. The conversation can be transitioned to a communication method that is different form the natural language communication method in response to determining that the communication participant is automated.

Claims (55)

1. A method implemented by one or more processors, the method comprising:

monitoring a conversation between a bot and a communication participant, the conversation being initiated over a natural language communication channel, and the conversation being conducted using a natural language communication method that includes a dialogue of natural language communications;

determining that the communication participant is automated using a pre-defined adaptive interactive protocol that specifies a plurality of natural language linguistic transformations for the dialogue of natural language communications; and

in response to determining that the communication participant is automated, causing the conversation to be transitioned to a communication method that is different from the natural language communication method with which the conversation was initiated.

2. The method of claim 1 , further comprising:

in response to determining that the communication participant is not automated, causing the conversation to be continued using natural language communications that are unaltered.

3. The method of claim 1 , wherein the adaptive interactive protocol specifies the plurality of natural language communications in a sequence.

4. The method of claim 3 , wherein determining that the communication participant is automated comprises:

defining a confidence level that the communication participant is automated;

for each natural language communication to be sent to the communication participant, and until the confidence level exceeds a pre-defined confidence level that the communication participant is automated,

prior to sending a natural language communication to the communication participant, causing the natural language communication to be altered based on a next natural language linguistic transformation in the sequence; and

causing, using the natural language communication method, the altered natural language communication to be sent to the communication participant;

for each natural language communication received from the communication participant,

determining that a natural language communication response is in an expected format based on the pre-defined adaptive interactive protocol; and

updating the confidence level to indicate a greater confidence that the communication participant is automated; and

determining that the communication participant is automated once the confidence level exceeds the pre-defined confidence level.

5. The method of claim 1 , wherein causing the conversation to be transitioned to a communication method that is different from the natural language communication method comprises:

causing the conversation to be transitioned to a structured data transfer communication method for subsequent communication to and from the communication participant.

6. The method of claim 1 , wherein causing the conversation to be transitioned to a communication method that is different from the natural language communication method comprises:

determining that the communication participant knows about an alternative channel for communication; and

causing any subsequent communication to be directed to the alternative channel.

7. The method of claim 1 , wherein causing the conversation to be transitioned to a communication method that is different from the natural language communication method comprises:

determining that the communication participant does not know about an alternative channel for communication; and

causing computer-optimized communication to be directed through the natural language communication channel.

8. The method of claim 1 , wherein at least one said natural language linguistic transformation of the pre-defined adaptive interactive protocol presents text of a natural language communication in a different order or with a different grammatical structure.

9. The method of claim 1 , wherein at least one said natural language linguistic transformation of the pre-defined adaptive interactive protocol is one of passivization, topicalization, clefting, extraposition, preposing, there-construction, pronominalization, or fronting.

10. The method of claim 1 , wherein prior to causing the conversation to be transitioned to a communication method that is different from the natural language communication method, causing an option to switch to an alternative communication method to be presented to the communication participant.

11. The method of claim 10 , wherein after causing the option the option to switch to an alternative communication method to be presented, the communication participant declines to switch communication methods.

12. The method of claim 1 , further comprising:

prior to monitoring the conversation between the bot and the communication participant:

receiving a command requiring natural language conversation; and

continuing the conversation until a task specified by the command is complete.

13. The method of claim 12 , wherein the command is received from an utterance of a user.

14. The method of claim 12 , wherein the command is a request to perform a task for a user.

15. The method of claim 14 , wherein the task is a task to book a haircut, make a reservation, or order food delivery.

16. A system comprising one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

monitoring a conversation between a bot and a communication participant, the conversation being initiated over a natural language communication channel, and the conversation being conducted using a natural language communication method that includes a dialogue of natural language communications;

determining that the communication participant is automated using a pre-defined adaptive interactive protocol that specifies a plurality of natural language linguistic transformations for the dialogue of natural language communications; and

in response to determining that the communication participant is automated, causing the conversation to be transitioned to a communication method that is different from the natural language communication method with which the conversation was initiated.

17. The system of claim 16 , wherein the operations comprise:

in response to determining that the communication participant is not automated, causing the conversation to be continued using natural language communications that are unaltered.

18. The system of claim 16 in which the adaptive interactive protocol specifies the plurality of natural language communications in a sequence.

19. The system of claim 18 , wherein determining that the communication participant is automated comprises:

defining a confidence level that the communication participant is automated;

for each natural language communication to be sent to the communication participant, and until the confidence level exceeds a pre-defined confidence level that the communication participant is automated,

prior to sending a natural language communication to the communication participant, causing the natural language communication to be altered based on a next natural language linguistic transformation in the sequence; and

causing, using the natural language communication method, the altered natural language communication to be sent to the communication participant;

for each natural language communication received from the communication participant,

determining that a natural language communication response is in an expected format based on the pre-defined adaptive interactive protocol; and

updating the confidence level to indicate a greater confidence that the communication participant is automated; and

determining that the communication participant is automated once the confidence level exceeds the pre-defined confidence level.

20. A non-transitory computer program product encoded on one or more computer storage devices, the computer program product comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

monitoring a conversation between a bot and a communication participant, the conversation being initiated over a natural language communication channel, and the conversation being conducted using a natural language communication method that includes a dialogue of natural language communications;

determining that the communication participant is automated using a pre-defined adaptive interactive protocol that specifies a plurality of natural language linguistic transformations for the dialogue of natural language communications; and

in response to determining that the communication participant is automated, causing the conversation to be transitioned to a communication method that is different from the natural language communication method with which the conversation was initiated.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 20, 2022
From: MILLIUS, SEBASTIAN; FEUZ, SANDRO
To: GOOGLE LLC
Reel/Frame 059649/0219 →
Continuity (4)
Continuation 16662755 · Oct 24, 2019
Continuation PCTUS2019015414 · Jan 28, 2019
Provisional Application 62751172 · Oct 26, 2018
Related Publication 20220027568A1 · Jan 27, 2022
Cited By (2)
US 12,190,064 US 12,425,446