US 12,436,735 B2
Machine learning-based interactive conversation system with topic-specific state machines
Damiano Bolzoni, Los Angeles, CA (US); and Leone Baruh, Castelmassa (IT)
Assigned to ItsAllAbout, Inc., Los Angeles, CA (US)
Filed by ItsAllAbout, Inc., Los Angeles, CA (US)
Filed on Aug. 26, 2022, as Appl. No. 17/896,878.
Prior Publication US 2024/0069858 A1, Feb. 29, 2024
Int. Cl. G06F 3/16 (2006.01); G06F 9/448 (2018.01)
CPC G06F 3/167 (2013.01) [G06F 9/4498 (2018.02)] 24 Claims
OG exemplary drawing
 
1. A method comprising:
providing an interactive conversation application having a plurality of topic specific state machines, wherein each of the plurality of topic specific state machines comprises a set of states corresponding to a particular topic;
providing a user interface (UI) for selecting one of the plurality of topic specific state machines;
in response to receiving via the UI, a selection of a topic specific state machine from the plurality of topic specific state machines, loading, by the interactive conversation application, the selected topic specific state machine; and
initiating a user session by outputting a prompt associated with an initial state of the selected topic specific state machine, wherein the initial state is one of a plurality of states that the selected topic specific state machine may operate in, and each of the plurality of states corresponds to a particular conversational objective to advance conversation with a user and includes an associated prompt that achieves the particular conversational objective that corresponds to the state, and wherein the particular conversational objective corresponding to each of the plurality of states is different from the particular conversational objective corresponding to other states of the plurality of states.