Escalation to a human operator

• US 10,560,575 B2
• Filed: 06/13/2017
• Issued: 02/11/2020
• Est. Priority Date: 06/13/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Segalis, Eyal, Walevski, Daniel, Leviathan, Yaniv, Matias, Yossi
• Primary Examiner(s): Singh, Satwant K
• Application Number:
  US15/621,923
• Publication Number:
  US 20170358296A1
• Time in Patent Office: 973 Days
• Field of Search: None
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/222 Barge in, i.e. overridable guidance for interrupting prompts
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: H04M 2242/18 Automated outdialling systems
• CPC Class Codes: H04M 3/42042 Notifying the called party of information on the calling party details within substation equipment H04M1/57, signalling details H04Q3/72
• CPC Class Codes: H04M 3/42093 Notifying the calling party of information on the called or connected party
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: H04M 3/58 Arrangements for transferring received calls from one subscriber to another; Arrangements affording interim conversations between either the calling or the called party and a third party substation line holding circuits H04M1/80
• CPC Class Codes: H04M 3/60 Semi-automatic systems, i.e. in which the numerical selection of the outgoing line is under the control of an operator

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, relating to synthetic call initiations and bailouts. In some implementations, a method includes analyzing, by a call initiating system, a real-time conversation between a first human and the bot during a phone call between the first human on a first end of the phone call and the bot on a second end of the phone call. The call initiating system can determine, based on the analysis of the real-time conversation, whether the phone call should be transitioned from the bot to a second human on the second end of the phone call. In response to determining that the phone call should be transitioned to a second human on the second end of the phone call, the call initiating system transitions the phone call from the bot to the second human.

Claims

1. A method for transitioning a phone call away from a bot, comprising:

analyzing, by a call initiating system, a real-time conversation between a first human and the bot during a phone call between the first human on a first end of the phone call and the bot on a second end of the phone call;

determining, by the call initiating system based on analysis of the real-time conversation, whether the phone call should be transitioned from the bot to a second human, whose voice characteristics match those of the bot, on the second end of the phone call; and

in response to determining that the phone call should be transitioned to a second human on the second end of the phone call, transitioning, by the call initiating system, the phone call from the bot to the second human.

2. The method of claim 1, wherein analyzing the real-time conversation between the first human and the bot during the phone call comprises:

determining strain during the phone call based on conduct, demeanor, tone, annoyance level, language, or word choice of the first human.

3. The method of claim 2, further comprising:

determining an increase in strain during the phone call when the bot repeats itself, apologizes, or asks for clarification.

4. The method of claim 2, further comprising:

determining an increase in strain during the phone call when the human corrects the bot or complains about the quality of the call.

5. The method of claim 2, further comprising:

determining a decrease in strain during the phone call when the bot appropriately responds to dialog of the first human.

6. The method of claim 1, wherein analyzing the real-time conversation between the first human and the bot during the phone call comprises:

determining a confidence level of the call initiating system that a task of the phone call will be completed by the bot.

7. The method of claim 1, wherein analyzing the real-time conversation between the first human and the bot during the phone call comprises:

determining that the first human asked for the phone call to be transitioned to another human.

8. The method of claim 1, wherein analyzing the real-time conversation between the first human and the bot during the phone call comprises:

determining that the first human has mocked the bot or asked if the bot is a robot.

9. The method of claim 2, wherein determining whether the phone call should be transitioned from the bot to a second human comprises:

determining that the strain is above a predefined threshold; and

in response to the strain being above a predefined threshold, determining that the phone call should be transitioned from the bot to the second human.

10. The method of claim 1, wherein analyzing the real-time conversation between the first human and the bot during the phone call comprises:

keeping track of one or more events in the conversation.

11. The method of claim 10, wherein determining whether the phone call should be transitioned from the bot to a second human comprises:

using a feature-based rule set that determines whether the one or more events in the conversation meet the criteria of a rule; and

in response to determining that the one or more events in the conversation meet the criteria of a rule, determining that the phone call should be transitioned from the bot to the second human.

12. The method of claim 1, wherein analyzing the real-time conversation between the first human and the bot during the phone call comprises:

identifying intents from the conversation; and

identifying historical intents and historical outcomes from previous conversations.

13. The method of claim 12, wherein determining whether the phone call should be transitioned from the bot to a second human comprises:

sending intents from the conversation, historical intents, or historical outcomes to one or more machine learning models; and

determining whether the phone call should be transitioned based on the intents, historical intents, or historical outcomes.

14. The method of claim 1, wherein the second human is a human operator.

15. The method of claim 1, wherein the second human is the user for which the bot is conducting the phone call.

16. The method of claim 1, further comprising:

terminating the phone call when transitioning the phone call from the bot to the second human takes longer than a predetermined amount of time.

17. The method of claim 1, further comprising:

terminating the phone call instead of transitioning the phone call to a human.

18. A call initiating system for placing calls, conducting conversations between a bot of the call initiating system and a first human during the phone calls, and for transitioning a phone call away from a bot, that performs operations comprising:

analyzing, by a call initiating system, a real-time conversation between a first human and the bot during a phone call between the first human on a first end of the phone call and the bot on a second end of the phone call;

determining, by the call initiating system based on analysis of the real-time conversation, whether the phone call should be transitioned from the bot to a second human, whose voice characteristics match those of the bot, on the second end of the phone call; and

in response to determining that the phone call should be transitioned to a second human on the second end of the phone call, transitioning, by the call initiating system, the phone call from the bot to the second human.

19. At least one non-transitory computer-readable storage medium encoded with executable instructions that, when executed by at least one processor, cause the at least one processor to perform operations comprising:

analyzing, by a call initiating system, a real-time conversation between a first human and the bot during a phone call between the first human on a first end of the phone call and the bot on a second end of the phone call;

determining, by the call initiating system based on analysis of the real-time conversation, whether the phone call should be transitioned from the bot to a second human, whose voice characteristics match those of the bot, on the second end of the phone call; and

in response to determining that the phone call should be transitioned to a second human on the second end of the phone call, transitioning, by the call initiating system, the phone call from the bot to the second human.