Amazon technologies, inc. (20240347050). USER-SYSTEM DIALOG EXPANSION simplified abstract

USER-SYSTEM DIALOG EXPANSION

Organization Name

amazon technologies, inc.

Inventor(s)

Ruhi Sarikaya of Redmond WA (US)

Hung Tuan Pham of Kirkland WA (US)

Savas Parastatidis of Kirkland WA (US)

Dean Curtis of Seattle WA (US)

Pushpendre Rastogi of Seattle WA (US)

Nitin Ashok Jain of Seattle WA (US)

John Arland Nave of Bellevue WA (US)

Abhinav Sethy of Seattle WA (US)

Arpit Gupta of Seattle WA (US)

Mayank Kumar of Sammamish WA (US)

Nakul Dahiwade of Seattle WA (US)

Arshdeep Singh of Seattle WA (US)

Nikhil Reddy Kortha of Seattle WA (US)

Rohit Prasad of Lexington MA (US)

USER-SYSTEM DIALOG EXPANSION - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240347050 titled 'USER-SYSTEM DIALOG EXPANSION

The abstract describes techniques for recommending a skill experience to a user after a user-system dialog session has ended.

• The system uses machine learning models to determine potential intents and specific skills to recommend to the user.
• The user is prompted to accept the recommended skill and intent, and if accepted, the system calls the skill to execute.
• The system sends at least one entity from the user input of the ended dialog session to the skill, enabling it to skip welcome prompts and provide a response based on the intent and entity.

Potential Applications: - Personalized skill recommendations in user-system interactions - Enhancing user experience by providing relevant skills based on past interactions

Problems Solved: - Improving user engagement by recommending relevant skills - Streamlining the process of skill recommendation after dialog sessions

Benefits: - Increased user satisfaction through personalized recommendations - Efficient utilization of machine learning models to enhance user-system interactions

Commercial Applications: - Customer service chatbots - E-learning platforms

Questions about the technology: 1. How does the system determine which skill and intent to recommend to the user? 2. What are the potential limitations of using machine learning models for skill recommendations in user-system interactions?

Frequently Updated Research: - Stay updated on advancements in machine learning algorithms for skill recommendation systems.

Original Abstract Submitted

techniques for recommending a skill experience to a user after a user-system dialog session has ended are described. upon a dialog session ending, the system uses a first machine learning model to determine potential intents to recommend to a user. the system then uses a second machine learning model to determine a particular skill and intent to recommend. the system then prompts the user to accept the recommended skill and intent. if the user accepts, the system calls the recommended skill to execute. as part of calling the skill, the system sends to the skill at least one entity provided in a natural language user input of the ended dialog session. this enables the skill to skip welcome prompts, and initiate processing to output a response based on the intent and the at least one entity of the ended dialog session.