IP Library Granted Patent US 12,190,064
Granted Patent B2
US 12,190,064 · App. 18/217,351 · Granted Jan 7, 2025

Monitoring communication by a bot to determine a human or an additional bot

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 12,190,064
App. No.
18/217,351
Granted
Jan 7, 2025
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 (45)

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

causing a bot to initiate a phone call with a communication participant, the phone call being initiated over a natural language communication channel, and the phone call being conducted using a natural language communication method that includes a dialogue of natural language communications;

determining, based on monitoring the phone call between the bot and the communication participant, whether the communication participant is a human or an additional bot; and

in response to determining that the communication participant is an additional bot, causing the phone call to be transitioned to a machine communication method that is different from the natural language communication method with which the phone call was initiated.

2. The method of claim 1 , wherein causing the phone call to be transitioned to a machine communication method that is different from the natural language communication method comprises:

causing the bot to provide access to an application programming interface (API) for the machine communication method that is different from the natural language communication method with which the phone call was initiated.

3. The method of claim 1 , further comprising:

prior to causing the bot to initiate the phone call with the communication participant:

receiving a command for the bot to initiate the phone call; and

continuing the phone call until a task specified by the command is complete.

4. The method of claim 3 , wherein the command is received from an utterance of a user, and wherein the command is a request to perform the task on behalf the user.

5. The method of claim 4 , wherein the task is a task to book a haircut, make a reservation, or order food delivery.

6. The method of claim 1 , further comprising:

in response to determining that the communication participant is a human, causing the phone call to be continued using the natural language communication method.

7. The method of claim 1 , wherein determining whether the communication participant is a human or an additional bot and based on monitoring the phone call between the bot and the communication participant is based on using an adaptive interactive protocol to monitor the phone call between the bot and the communication participant.

8. The method of claim 7 , wherein using an adaptive interactive protocol to monitor the phone call between the bot and the communication participant comprises:

defining a confidence level that the communication participant is the additional bot;

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 the natural language communication to the communication participant, causing the natural language communication to be altered based on a next natural language linguistic transformation in a 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 the additional bot; and determining that the communication participant is the additional bot in response to the confidence level exceeding the pre-defined confidence level.

9. The method of claim 1 , wherein causing the phone call to be transitioned to the machine communication method that is different from the natural language communication method comprises:

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

10. A system comprising:

one or more processors; and

memory storing instructions that, when executed by the one or more processors, cause the one or more processors to:

cause a bot to initiate a phone call with a communication participant, the phone call being initiated over a natural language communication channel, and the phone call being conducted using a natural language communication method that includes a dialogue of natural language communications;

determine, based on monitoring the phone call between the bot and the communication participant, whether the communication participant is a human or an additional bot; and

in response to determining that the communication participant is an additional bot, cause the phone call to be transitioned to a machine communication method that is different from the natural language communication method with which the phone call was initiated.

11. The system of claim 10 , wherein the instructions to cause the phone call to be transitioned to the machine communication method that is different from the natural language communication method comprise instructions to:

cause the bot to provide access to an application programming interface (API) for the machine communication method that is different from the natural language telephonic communication method with which the phone call was initiated.

12. The system of claim 10 , wherein the instructions further cause the one or more processors to:

prior to causing the bot to initiate the phone call with the communication participant:

receive a command for the bot to initiate the phone call; and

continue the phone call until a task specified by the command is complete.

13. The system of claim 12 , wherein the command is received from an utterance of a user, and wherein the command is a request to perform the task on behalf the user.

14. The system of claim 13 , wherein the task is a task to book a haircut, make a reservation, or order food delivery.

15. The system of claim 10 , wherein the instructions further cause the one or more processors to:

in response to determining that the communication participant is a human, cause the phone call to be continued using the natural language communication method.

16. A non-transitory computer-readable storage medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:

causing a bot to initiate a phone call with a communication participant, the phone call being initiated over a natural language communication channel, and the phone call being conducted using a natural language communication method that includes a dialogue of natural language communications;

determining, based on monitoring the phone call between the bot and the communication participant, whether the communication participant is a human or an additional bot; and

in response to determining that the communication participant is an additional bot, causing the phone call to be transitioned to a machine communication method that is different from the natural language communication method with which the phone call was initiated.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jul 13, 2023
From: MILLIUS, SEBASTIAN; FEUZ, SANDRO
To: GOOGLE LLC
Reel/Frame 064246/0470 →
Continuity (5)
Continuation 17492863 · Oct 4, 2021
Continuation 16662755 · Oct 24, 2019
Continuation PCTUS2019015414 · Jan 28, 2019
Provisional Application 62751172 · Oct 26, 2018
Related Publication 20230342554A1 · Oct 26, 2023
References Cited (55)
US 6397188B1 · Iwasawa · 2002 [cited by applicant]
US 7356463B1 · Isabelle · 2008 [cited by applicant]
US 8589148B2 · Atallah et al. · 2013 [cited by applicant]
US 8725818B1 · Covitz et al. · 2014 [cited by applicant]
US 8996635B1 · Byttow et al. · 2015 [cited by applicant]
US 9595034B2 · Van Rooyen · 2017 [cited by applicant]
US 10108605B1 · Leighton · 2018 [cited by applicant]
US 10162816B1 · Banerjee · 2018 [cited by applicant]
US 10466885B2 · Yaseen et al. · 2019 [cited by applicant]
US 10482554B1 · Vukich · 2019 [cited by examiner]
US 10587408B2 · Ooi · 2020 [cited by applicant]
US 10971144B2 · Mahajan · 2021 [cited by applicant]
US 11107141B1 · Nagarajappa · 2021 [cited by examiner]
US 11138384B2 · Millius · 2021 [cited by applicant]
US 11146598B1 · Palihakkara · 2021 [cited by examiner]
US 11468893B2 · Aharoni · 2022 [cited by examiner]
US 11734515B2 · Millius · 2023 [cited by examiner]
US 20080043986A1 · Darby · 2008 [cited by applicant]
US 20080147406A1 · Da Palma et al. · 2008 [cited by applicant]
US 20090319274A1 · Gross · 2009 [cited by applicant]
US 20130007137A1 · Azzam · 2013 [cited by applicant]
US 20140032220A1 · Lerner · 2014 [cited by applicant]
US 20150381740A1 · Gwin · 2015 [cited by applicant]
US 20170034226A1 · Bostick · 2017 [cited by applicant]
US 20170126631A1 · Vikramaratne · 2017 [cited by applicant]
US 20170324867A1 · Tamblyn et al. · 2017 [cited by applicant]
US 20170359463A1 · Segalis et al. · 2017 [cited by applicant]
US 20170366479A1 · Ladha · 2017 [cited by examiner]
US 20180048594A1 · de Silva · 2018 [cited by examiner]
US 20180078843A1 · Tran · 2018 [cited by applicant]
US 20180096686A1 · Borsutsky · 2018 [cited by examiner]
US 20180218732A1 · Grant · 2018 [cited by examiner]
US 20180240473A1 · Baracaldo Angel · 2018 [cited by examiner]
US 20190089655A1 · Uppala · 2019 [cited by examiner]
US 20190287513A1 · Alameh et al. · 2019 [cited by applicant]
US 20200028803A1 · Helmy · 2020 [cited by examiner]
US 20200073982A1 · Kolluri Venkata Sesha · 2020 [cited by examiner]
US 20200082816A1 · Mahajan · 2020 [cited by applicant]
US 20200311204A1 · Gupta · 2020 [cited by applicant]
US 20220027568A1 · Millius et al. · 2022 [cited by applicant]
CA 2649011 · 2007 [cited by applicant]
CN 101207656 · 2008 [cited by applicant]
CN 107209757 · 2017 [cited by applicant]
CN 107491929 · 2017 [cited by applicant]
CN 107797725 · 2018 [cited by applicant]
CN 107978313 · 2018 [cited by applicant]
WO WO2018066000A1 · 2018 [cited by examiner]
WO WO2019063389A1 · 2019 [cited by examiner]
Bergmair et al., “Towards human interactive proofs in the text-domain,” International Conference on Information Securit, 12 pages; dated Sep. 2004. [cited by applicant]
PCT International Search Report and Written Opinion in International Appl. No. PCTAJS2019/01541; 16 pages; dated Jul. 11, 2019. [cited by applicant]
phrasee.com [online], “How to tell if you are talking to a chatbot,” retrieved on Jul. 3, 2019, retrieved from URL<https://phrasee.co/how-to-tell-if-you-are-talking-to-a-chatbot/>, 10 pages; dated Jul. 2017. [cited by applicant]
talkspace.com [online], “How to Tell If You're Talking to a Bot: The Complete Guide to Chatbots,” via Internet Archive: Wayback Machine URL<http://web .archive .org/web/20160125115828/https://www .talkspace.com/blog/201… [cited by applicant]
China National Intellectual Property Administration; Notification of First Office Action issued in Application No. 201980039744.5, 13 pages; dated Dec. 12, 2023. [cited by applicant]
China National Intellectual Property Administration; Notice of Grant issued in Application No. 201980039744.5; 6 pages; dated Feb. 28, 2024. [cited by applicant]
European Patent Office; Examination Report issued for Application No. 19704181.7, 6 pages, dated Jun. 26, 2024. [cited by applicant]
Cited By (3)
US 12,334,049 US 12,436,978 US 12,488,190