Workflow based communications routing

Patent metadata

Field	Value
Publication number	US-10469665-B1
Application number	US-201615340022-A
Country	US
Kind code	B1
Filing date	Nov 1, 2016
Priority date	Nov 1, 2016
Publication date	Nov 5, 2019
Grant date	Nov 5, 2019

Abstract

Disclosed are various embodiments for routing communications to service agents based on a workflow. A computing device identifies a user intent object corresponding to a user interaction with the computing device. The computing device then identifies a workflow corresponding to the user intent object. Later, the computing device identifies a service agent capable of completing the workflow. Then, the computing device routes a user to the service agent.

First claim

Therefore, the following is claimed:

1. A system, comprising:
a computing device comprising a processor and a memory; and
a first application comprising machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
receive a plurality of transcripts generated from a plurality of user conversations with a chat bot;
process the plurality of transcripts with a recurrent neural network to associate a first text string with a user intent object;
store the first text string as a search criterion in the user intent object;
search for a second text string within a transcript of a conversation between a user and a second application;
determine that the second text string matches the first text string specified by the search criterion stored in the user intent object, wherein the user intent object further specifies a workflow item that identifies a workflow and a service agent for the workflow; and
initiate a connection between a first instance of a messaging application executing on a first client device associated with the user and a second instance of the messaging application executing on a second client device associated with the service agent.

2. The system of claim 1 , wherein:
the transcript of the conversation comprises a first transcript;
the conversation between the user and the second application comprises a first conversation;
the service agent comprises a first service agent; and
the first application further comprises the machine readable instructions stored in the memory that, when executed by the processor, cause the processor to at least:
perform natural language analysis on a second transcript of a second conversation between the user and the first service agent;
reroute the connection from the first instance of the messaging application to a third instance of the messaging application executing on a third client device associated with a second service agent; and
forward the second transcript to the third client device associated with the second service agent.

3. The system of claim 1 , wherein the search criterion comprises a regular expression.

4. The system of claim 1 , wherein the second application comprises the chat bot configured to operate as a portion of an automated service agent.

5. A system, comprising:
a computing device comprising a processor and a memory; and
an application comprising machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
identify a user intent object corresponding to a user interaction with a chat bot, wherein the user intent object is identified based at least in part on a transcript of a conversation between a user and the chat bot;
select a workflow object based at least in part on the user intent object, wherein the workflow object specifies a workflow that comprises a series of steps to be performed to complete the workflow and a human service agent to process the workflow; and
route the user to the human service agent specified by the workflow object by initiating a connection between a first instance of a messaging application executing on a first client device associated with the user and a second instance of the messaging application executing on a second client device associated with the human service agent.

6. The system of claim 5 , wherein:
the human service agent comprises a first human service agent;
the workflow object further specifies a first portion of the workflow, a second portion of the workflow, and a second human service agent designated to process the second portion of the workflow; and
the application further comprises the machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
determine that the first portion of the workflow specified by the workflow object is complete; and
route the user to the second human service agent specified by the workflow object in response to a determination that the first portion of the workflow is complete.

7. The system of claim 5 , wherein:
the user intent object comprises a first user intent object;
the user interaction comprises a first user interaction;
the workflow object comprises a first workflow object;
the human service agent comprises a first human service agent; and
the application further comprises the machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to further:
identify a second user intent object corresponding to a second user interaction with the application;
select a second workflow object based at least in part on the second user intent object; and
reroute the user from the first human service agent to a second human service agent specified by the second workflow object.

8. The system of claim 5 , wherein the user intent object is a first user intent object and the machine readable instructions that further cause the computing device to identify the first user intent object corresponding to the user interaction with the application further comprise machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
determine that the user interaction falls within a class of user interactions corresponding to the first user intent object;
compare the user interaction with a second user intent object that is a child object of the first user intent object to determine that the user interaction corresponds to an intent that matches the second user intent object; and
identify the second user intent object as corresponding to the user interaction with the application.

9. The system of claim 5 , wherein the user interaction comprises a selection of an option presented in a user interface.

10. The system of claim 5 , wherein the user interaction comprises a recorded sequence of interactions with the chat bot.

11. The system of claim 5 , wherein the machine readable instructions that cause the computing device to at least route the user to the human service agent specified by the workflow object further comprises the machine readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least initiate a telephone connection between a phone identified in a user profile and a phone associated with the human service agent.

12. A method, comprising:
processing, with a computing device, a first transcript of a first conversation between a first user and a chat bot in order to associate a text string with a user intent object;
identifying, with the computing device, the user intent object in a second transcript of a second conversation between a second user and a chat bot application based at least in part on a user interaction of the second user with the computing device, wherein the user intent object is identified based at least in part on identifying the text string in the second transcript;
identifying, with the computing device, a workflow corresponding to the user intent object;
identifying, with the computing device, a service agent capable of completing the workflow; and
routing, with the computing device, the second user to the service agent by initiating a connection between a first instance of a messaging application executing on a first client device associated with the second user and a second instance of the messaging application executing on a second client device associated with the service agent.

13. The method of claim 12 , further comprising:
identifying, with the computing device, a subsequ

Assignees

• Amazon Tech Inc

Inventors

• Bell Kristopher William
• Bhardwaj Vikas Seshagiri Rao
• Dos Santos Ariel Grob
• Gavenman Kathleen Ann Mitchell
• Jayaraman Gunashekar
• Raza Farrukh
• Sutherland Andrew Gardiner

Classifications

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06N3/08

  Learning methods · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• H04M3/527

  Centralised call answering arrangements not requiring operator intervention · CPC title

• H04M3/42382

  Text-based messaging services in telephone networks such as PSTN/ISDN, e.g. User-to-User Signalling or Short Message Service for fixed networks · CPC title