Facilitating user device and/or agent device actions during a communication session

Patent metadata

Field	Value
Publication number	US-11269666-B2
Application number	US-201816621769-A
Country	US
Kind code	B2
Filing date	Aug 22, 2018
Priority date	Aug 22, 2017
Publication date	Mar 8, 2022
Grant date	Mar 8, 2022

Abstract

Implementations are directed to facilitating user device and/or agent device actions during a communication session. An interactive communications system provides outputs, as outlined below, that are tailored to enhance the functionality of the communication session, reduce the number of dialog “turns” of the communications session and/or the number of user inputs to devices involved in the session, and/or otherwise mitigate consumption of network and/or hardware resources during the communication session. In various implementations, the communication session involves user device(s) of a user, agent device(s) of an agent, and the interactive communications system. The interactive communications system can analyze various communications from the user device(s) and/or agent device(s) during a communication session in which the user (via the user device(s)) directs various communications to the agent, and in which the agent (via the agent device(s)) optionally directs various communications to the user. The interactive communications system provides action performance element(s) and/or other output(s) that are each specific to a corresponding current intent and corresponding current action of the communication session.

First claim

The invention claimed is:

1. A method implemented by one or more processors, comprising:
receiving one or more instances of natural language input during a communication session that includes a user computing device and an interactive communications system implemented by one or more of the processors, the instances of the natural language inputs including free-form input formulated by a user of the user computing device via a user interface input device of the user computing device;
processing the natural language input to generate annotations of the natural language input;
selecting, from a set of candidate intents, at least one current intent of the communication session, wherein selecting the current intent is based on processing the natural language input and the annotations using one or more intent models, the one or more intent models each being a trained machine learning model;
determining an action for the selected current intent;
resolving an agent for the action;
determining that agent specific parameters, that are specific to the resolved agent, are not available for the action;
in response to determining that the agent specific parameters are not available for the action:
generating an action performance element based on the action and stored parameters for a domain of the agent, the domain being a domain that encompasses the agent and a plurality of additional agents; and
causing the action performance element to be rendered at the user computing device, wherein selection of the action performance element at the user computing device causes the user computing device to initiate performance of the action with the stored parameters for the domain of the agent;

in response to determining that agent specific parameters are not available for the action;
generating a prompt that solicits parameters for the action;
transmitting the prompt to an agent computing device associated with the agent;
receiving responsive content from the agent computing device in response to transmitting the prompt;
resolving the agent specific parameters, for the action and for the agent, based on the responsive content; and
defining the agent specific parameters, for the action and for the agent, in one or more computer readable media.

2. The method of claim 1 , further comprising:
determining that the action has been invoked in association with the agent in a threshold quantity of communications sessions;
wherein transmitting the prompt is based on determining that the action has been invoked in association with the agent in the threshold quantity of communication sessions.

3. The method of claim 1 , further comprising, subsequent to defining the agent specific parameters for the action and for the agent:
determining the action and resolving the agent during a subsequent communication session between an additional computing device and the interactive communications system;
based on the agent specific parameters being defined for the action and for the agent:
transmitting, to the additional computing device, a subsequent action performance element that is based on the action and the defined agent specific parameters.

4. The method of claim 3 , wherein selection of the subsequent action performance element causes the additional computing device to initiate performance of the action with the parameters that are specific to the agent.

5. The method of claim 1 , wherein resolving the agent comprises resolving the agent based on the natural language input, the selected current intent, or the determined action.

6. The method of claim 1 , wherein resolving the agent comprises:
determining one or more of: an availability measure of the agent, an expertise measure of the agent, and an experience measure of the agent; and
resolving the agent based on one of more of: the availability measure, the expertise measure, and the experience measure.

7. The method of claim 1 , further comprising:
prior to the communication session, causing an agent initiation interface element to be rendered at the client device; and
resolving the agent and establishing the communication session in response to selection of the agent initiation interface element.

8. The method of claim 1 , wherein causing the action performance element to be rendered at the user computing device comprises causing the action performance element to be rendered during the communication session.

9. The method of claim 8 , wherein causing the action performance element to be rendered during the communication session comprises causing the action performance element to be rendered by an application utilized for the communication session.

10. The method of claim 8 , wherein causing the action performance element to be rendered during the communication session comprises causing the action performance element to be rendered by an additional application that is in addition to an application utilized for the communication session.

11. The method of claim 1 , wherein causing the action performance element to be rendered at the user computing device occurs subsequent to the communication session and is by an additional application that is in addition to an application utilized for the communication session.

12. A method implemented by one or more processors, comprising:
receiving natural language input during a communications session that includes a user computing device, the natural language input including free-form input formulated by a user of the user computing device via a user interface input device of the user computing device;
processing the natural language input to generate annotations of the natural language input;
selecting, from a set of candidate intents, at least one current intent of the communications session, wherein selecting the current intent is based on applying the natural language input and the annotations to one or more intent models, the one or more intent models each being a trained machine learning model;
determining an action for the selected current intent;
generating an action performance element based on the action and stored parameters for the action that are specific to the agent;
transmitting, to an agent computing device associated with the agent, an indication of the action performance element; and
receiving an affirmative response from the agent computing device in response to transmitting the indication of the action performance element;
subsequent to and contingent on receiving the affirmative response from the agent computing device:
transmitting the action performance element to the user computing device,
wherein selection of the action performance element causes the user computing device to initiate performance of the action with the stored parameters for the action that are specific to the agent; and

based on receiving the affirmative response from the agent computing device, transmitting a subsequent action performance element, that is based on the action and the parameters that are specific to the agent, without first transmitting any indication of the action performance element to the agent computing device.

13. A system, comprising:
memory storing instructions;
one or more processors executing the instructions stored in the memory to cause the one or more processors to:
receive one or more instances of natural language input during a communication session that includes a user computing device and the system, the instances of the natural language inputs including free-form input formulated by a user of the user computing device via a user interface input device of the user computing device;
process the natural language input to generate ann

Assignees

• Google Llc

Inventors

• Dua Robin
• Tomkins Andrew
• Ravi Sujith

Classifications

• H04L67/60 Primary

  Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources (admission control or resource allocation H04L47/70) · CPC title

• G06F40/20

  Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F3/0481

  based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance · CPC title

• G06F40/30

  Semantic analysis · CPC title