US 12,079,584 B2
Systems and methods for conversation modeling
Suneet Dua, St. Petersburg, FL (US); Luis Beaumier, St. Petersburg, FL (US); Marc Nadeau, St. Petersburg, FL (US); Ryan Edley, Chicago, IL (US); Robert Coen, Tampa, FL (US); Jason Victor Randall, Dunedin, FL (US); and Shannon M. Robinson, Memphis, TN (US)
Assigned to PwC Product Sales LLC, New York, NY (US)
Filed by PwC Product Sales LLC, New York, NY (US)
Filed on Mar. 31, 2020, as Appl. No. 16/836,634.
Prior Publication US 2021/0303801 A1, Sep. 30, 2021
Int. Cl. G06F 40/40 (2020.01); G06F 3/0482 (2013.01); G06F 3/0486 (2013.01); G06F 3/16 (2006.01); G06N 5/02 (2023.01)
CPC G06F 40/40 (2020.01) [G06F 3/0482 (2013.01); G06F 3/16 (2013.01); G06N 5/02 (2013.01); G06F 3/0486 (2013.01)] 29 Claims
OG exemplary drawing
 
1. A modeling system for creating interactive conversation models for use by an intelligent assistant system, the modeling system comprising one or more processors, one or more displays, and memory storing instructions configured to be executed by the one or more processors to cause the modeling system to:
display a canvas region of a graphical user interface for creating conversation models;
display a conversation-element menu comprising a plurality of graphical conversation-element menu objects each representing a respective conversation-element type;
create a visual representation of a conversation, the visual representation comprising one or more graphical conversation-element objects, wherein creating the visual representation comprises:
detecting a conversation-element placement input from a user, wherein the input comprises selection of one of the conversation-element menu objects and indication of a location on the canvas region; and
in response to detecting the conversation-element placement input, displaying, at the indicated location on the canvas region, a graphical conversation-element object within the visual representation of the conversation, wherein the graphical conversation-element object indicates that a conversation-element represented by the graphical conversation-element object is of a conversation-element type corresponding to the selected conversation-element menu object;
in response to detecting the conversation-element placement input, display a conversation-element fields menu separate from the canvas region, wherein the conversation-element fields menu comprises one or more field portions prompting the user to enter condition information for a first condition of a plurality of conditions, wherein the first condition is associated with the conversation-element, and to enter evaluation order information specifying a position of the first condition in an evaluation order in which the plurality of conditions are arranged;
detect a data entry input for the one or more field portions of the conversation-element, wherein the data entry input indicates the first condition;
determine whether the data entry input indicates the position of the first condition in the evaluation order in which the plurality of conditions are arranged;
in accordance with a determination that the data entry input indicates the position of the first condition in the evaluation order, generate and store a model of the conversation in accordance with the one or more graphical conversation-element objects of the visual representation of the conversation and based at least in part on the data entry input indicating the first condition and indicating the position of the first condition in the evaluation order, such that the conversation model is configured to evaluate the first condition associated with the conversation-element in accordance with the evaluation order information specifying the position of the first condition in the evaluation order in which the plurality of conditions are arranged; and
in accordance with a determination that the data entry input does not indicate the position of the first condition in the evaluation order, generate and store the model of the conversation in accordance with the one or more graphical conversation-element objects of the visual representation of the conversation and based at least in part on the data entry input indicating the first condition, such that the conversation model is configured to evaluate the plurality of conditions in a random order.