17897887. DETECTING OUT-OF-DOMAIN TEXT DATA IN DIALOG SYSTEMS USING ARTIFICIAL INTELLIGENCE simplified abstract (International Business Machines Corporation)

From WikiPatents
Jump to navigation Jump to search

DETECTING OUT-OF-DOMAIN TEXT DATA IN DIALOG SYSTEMS USING ARTIFICIAL INTELLIGENCE

Organization Name

International Business Machines Corporation

Inventor(s)

Cheng Qian of Markham (CA)

Haode Qi of Cambridge MA (US)

Saloni Potdar of Cambridge MA (US)

Ladislav Kunc of Cambridge MA (US)

DETECTING OUT-OF-DOMAIN TEXT DATA IN DIALOG SYSTEMS USING ARTIFICIAL INTELLIGENCE - A simplified explanation of the abstract

This abstract first appeared for US patent application 17897887 titled 'DETECTING OUT-OF-DOMAIN TEXT DATA IN DIALOG SYSTEMS USING ARTIFICIAL INTELLIGENCE

Simplified Explanation

The patent application describes methods, systems, and computer program products for detecting out-of-domain text data in dialog systems using artificial intelligence techniques.

  • Updating artificial intelligence techniques for out-of-domain text data detection based on encoding training data and generating regularized representations.
  • Encoding input text data.
  • Computing out-of-domain scores for the encoded input text data using updated artificial intelligence techniques.
  • Performing automated actions based on the computed out-of-domain scores.

Potential Applications

  • Improving the accuracy and efficiency of dialog systems.
  • Enhancing user experience in chatbots and virtual assistants.
  • Streamlining customer service interactions.

Problems Solved

  • Identifying and handling out-of-domain text data in dialog systems.
  • Ensuring that responses are relevant and appropriate.
  • Minimizing errors and misunderstandings in communication.

Benefits

  • Increased accuracy in detecting out-of-domain text data.
  • Enhanced performance of dialog systems.
  • Improved user satisfaction and engagement.


Original Abstract Submitted

Methods, systems, and computer program products for detecting out-of-domain text data in dialog systems using artificial intelligence techniques are provided herein. A computer-implemented method includes updating artificial intelligence techniques related to out-of-domain text data detection, the updating based on encoding training data and generating regularized representations of at least a portion of the encoded training data by combining the at least a portion of the encoded training data and at least one intent centroid associated with the updated artificial intelligence techniques; encoding input text data; computing out-of-domain scores, in connection with the at least one dialog system, for at least a portion of the encoded input text data by processing the at least a portion of encoded input data using at least a portion of the one or more updated artificial intelligence techniques; and performing one or more automated actions based on the computed out-of-domain scores.