Patents Assigned to discourse.ai, Inc.
  • Publication number: 20200265339
    Abstract: A system and method for visualizing, exploring and shaping conversational data within a corpus for selective export to train an artificial intelligence-based interlocutor platform, which includes selecting, according to user inputs, a plurality of the conversations for generation of an interactive radial space-filling sunburst-style diagram; responsive to user navigation controls, revising the sunburst diagram to allow provide selection, filtering and modification of the of the text-based interlocutory conversations; and, according to user export controls, formatting and saving at least a portion of the selected and filtered plurality of text-based interlocutory conversations into training data for an artificial intelligence-based automated interlocutor platform.
    Type: Application
    Filed: May 6, 2020
    Publication date: August 20, 2020
    Applicant: discourse.ai, Inc.
    Inventor: Jonathan E. Eisenzopf
  • Publication number: 20190172069
    Abstract: An improved data processing system that continuously analyzes and automates a process of identifying statistically significant patterns of customer behavior linked to a specific set of customer outcomes and presenting these visually in a graph with linkages to the root causes, customer events, each step in the customer behavior, and the customer outcome. The improved computing system provides a set of hypotheses and recommendations based on the pattern matching solutions in a computer database and allows the user of the system to simulate the anticipated outcomes.
    Type: Application
    Filed: December 5, 2018
    Publication date: June 6, 2019
    Applicant: discourse.ai, Inc.
    Inventor: Jonathan E. Eisenzopf
  • Publication number: 20190171712
    Abstract: Computer-based natural language understanding of input and output for a computer interlocutor is improved using a method of classifying conversation segments from transcribed conversations. The improvement includes one or more methods of splitting transcribed conversations into groups related to a conversation ontology using metadata; identifying dominant paths of conversational behavior by counting the frequency of occurrences of the behavior for a given path; creating a conversation model comprising conversation behaviors, metadata, and dominant paths; and using the conversation model to assign a probability score for a matched input to the computer interlocutor or a generated output from the computer interlocutor.
    Type: Application
    Filed: November 27, 2018
    Publication date: June 6, 2019
    Applicant: discourse.ai, Inc.
    Inventor: Jonathan E. Eisenzopf