Interactive AI-Based System

An Interactive AI-Based System is an AI-based system that is an interactive system and can support interactive AI tasks (that can engage in bi-directional interaction).

• Context:
  • It can (typically) adapt its behavior based on user input or feedback.
  • It can (typically) respond within a short time frame after System Interaction Events.
  • It can be a part of User Interface-based AI System.
  • It can range from being a Rule-based Interactive AI-Based System to being a Learning Interactive AI-Based System.
  • It can range from being a Interactive AI-Based Application to being a Interactive AI-Based Platform.
  • It can integrate with other systems or databases to provide real-time information during interactions.
  • It can (typically) be a Complex AI-based System.
  • …
• Example(s):
  • an Interactive AI-Supported App, such as: LinkedIn AIbot.
  • An Interactive AI-based Platform, such as: Vertex AI, OpenAI Gym, and Facebook's ParlAI.
  • A Conversational AI System, such as: ...
    • An AI Chatbot that answers customer queries and learns from user feedback.
    • A Voice-activated Assistant like Amazon's Alexa or Apple's Siri.
    • A Real-Time Recommendation System on e-commerce sites that suggests products based on user's current browsing pattern.
    • An AI-based Augmented Reality Application that provides real-time information overlay based on what the camera perceives.
  • …
• Counter-Example(s):
  • a Non-Interactive AI-Based System, such as:
    • a Batch Processing AI System that analyzes data without real-time user interaction.
    • an Trained AI Model, that only provides outputs once trained, without ongoing interaction?
    • A Database Query System that doesn’t adapt or respond based on user behavior.
  • …
• See: Real-time AI System, User/AI Experience Design, Autonomous AI System.

---

---

References

2023

• (Y.R. Wang et al., 2023) ⇒ Y.R. Wang, J. Duan, S. Talia, H. Zhu. (2023). "A Study of Comfortability between Interactive AI and Human.” In: arXiv preprint arXiv:2302.14360. Link
  • QUOTE: As the use of interactive AI systems becomes increasingly prevalent in our daily lives, it is important to the growing body of literature on interactive AI systems, and it emphasizes the need to …
  • NOTE: Explores the relationship between humans and interactive AI systems, particularly the comfortability and integration of such systems in daily routines.

2022

• (K.M. Liao et al., 2022) ⇒ K.M. Liao, S.C. Ko, C.F. Liu, K.C. Cheng, C.M. Chen, M.I. Sung, …. (2022). "Development of an interactive ai system for the optimal timing prediction of successful weaning from mechanical ventilation for patients in respiratory care ….” In: Diagnostics.
  • QUOTE: Our study aimed to develop an interactive AI system for the optimal timing prediction of successful weaning among patients who received invasive MV while in a RCC. A preliminary AI …
  • NOTE: Describes the creation of an interactive AI system designed for medical applications, specifically to predict weaning times for patients on mechanical ventilation.

2019

• (M.M. Çelikok et al., 2019) ⇒ M.M. Çelikok, T. Peltola, P. Daee, S. Kaski. (2019). "Interactive AI with a Theory of Mind.” In: arXiv preprint arXiv:1912.05284.
  • QUOTE: Understanding each other is the key to success in collaboration. For humans, attributing mental states to others, the theory of mind, provides the crucial advantage. We argue for …
  • NOTE: Discusses the significance of "Theory of Mind" in interactive AI systems for enabling better collaboration and mutual understanding.

2019

• (X. Xie et al., 2019) ⇒ X. Xie, H. Liu, Z. Zhang, Y. Qiu, F. Gao, S. Qi, …. (2019). "Vrgym: A virtual testbed for physical and interactive ai.” In: Proceedings of the ….
  • QUOTE: We propose VRGym, a virtual reality (VR) testbed for realistic human-robot interaction. Different from existing toolkits and VR environments, the VRGym emphasizes on building and …
  • NOTE: Introduces VRGym as a testbed for interactive AI systems in the context of human-robot interactions, emphasizing its differences from existing tools.

1982

• (P.E. Gerring et al., 1982) ⇒ P.E. Gerring, E.H. Shortliffe, W. van Melle. (1982). "Interviewer/Reasoner Model: An Approach to Improving System Responsiveness in Interactive AI Systems.” In: AI Magazine.
  • QUOTE: Interactive intelligent systems often suffer from a basic conflict between their computationally intensive nature and the need for responsiveness to a user. This paper introduces the …
  • NOTE: Highlights challenges faced by interactive AI systems, particularly the balance between computational demands and user responsiveness, and proposes a solution.

---