Robust useful and general task-oriented virtual assistants

Description:

Reference #: 01532

The University of South Carolina is offering licensing opportunities for Robust useful and general task-oriented virtual assistants.

Background:

The use of voice assistants (VA) for various tasks is on the rise. It is estimated that by 2024, the number of voice assistants will reach 8.4 billion units - a number higher than the world population. From general chit-chat to controlling smart home appliances, the VAs are currently capable of performing a wide-array of tasks. However, the tasks are atomic and are only compatible with a single-turn instruction.

Invention Description: 

The described system incorporates user-specific knowledge for personalization and domain-specific knowledge for context adaptation to recommend and assist the users over procedural tasks. The approach also focuses on content curation for fault-tolerant execution to ensure the end goal is reached.

Potential Applications:

In the real world, a successful completion of the task would require multi-turn conversation, accommodating failures, seeking out alternatives and if possible, encouraging the human to complete the task. Appling this technology to various voice assistants could prove to be revolutionary.

Advantages and Benefits:

Technology is capable of content discovery and selection, content curation, instruction execution orchestration, fault tolerant execution, dynamic recommendation, human modeling in collaboration, value added ontology, and human centric values.

Patent Information:
Title App Type Country Serial No. Patent No. File Date Issued Date Expire Date Patent Status
Robust Useful and General Task-Oriented Virtual Assistants Utility United States 17/714,508   4/6/2022     Notice of Publication
Category(s):
Software and Computing
For Information, Contact:
Technology Commercialization
University of South Carolina
technology@sc.edu
Inventors:
Biplav Srivastava
Kausik Lakkaraju
Revathy Venkataramanan
Vishal Pallagani
Vedant Khandelwal
Hong Yung Yip
Keywords:
chatbots
collaborative assistants
discovering instructions
failure recovery
proactive assistance
recipes
task bot
© 2024. All Rights Reserved. Powered by Inteum