18206987. GENERATIVE ARTIFICIAL INTELLIGENCE ASSISTANT simplified abstract (Adobe Inc.)
Contents
GENERATIVE ARTIFICIAL INTELLIGENCE ASSISTANT
Organization Name
Inventor(s)
Jennifer Jiaying Qian of New York NY (US)
Mateus De Araujo Lopes of Naperville IL (US)
GENERATIVE ARTIFICIAL INTELLIGENCE ASSISTANT - A simplified explanation of the abstract
This abstract first appeared for US patent application 18206987 titled 'GENERATIVE ARTIFICIAL INTELLIGENCE ASSISTANT
Simplified Explanation: The patent application describes a system for identifying instances of digital content based on keywords associated with entity segments.
Key Features and Innovation:
- Computing device implements a content system to receive input data describing attributes of an entity segment and associated keywords.
- Machine-learning model determines semantically similar keywords to compile a set of matchable keywords.
- Candidate instances of digital content are identified based on content keywords and matchable keywords.
- An indication of an instance of digital content is generated for display in a user interface.
Potential Applications: This technology can be used in digital content management systems, search engines, and recommendation systems.
Problems Solved: This technology helps in efficiently identifying relevant digital content based on keywords and attributes associated with entity segments.
Benefits:
- Improved accuracy in identifying instances of digital content.
- Enhanced user experience in content discovery.
- Increased efficiency in content management.
Commercial Applications: Potential commercial applications include content recommendation platforms, digital marketing tools, and online advertising systems.
Prior Art: Prior art related to this technology may include research on machine learning models for keyword classification and content identification systems.
Frequently Updated Research: Stay updated on advancements in machine learning algorithms for keyword classification and content recognition.
Questions about the Technology: 1. How does the machine-learning model determine semantically similar keywords? 2. What are the potential limitations of this system in identifying instances of digital content accurately?
Original Abstract Submitted
In implementations of systems for identifying instances of digital content, a computing device implements a content system to receive input data describing attributes of an entity segment and keywords that are associated with the attributes of the entity segment. The content system determines additional keywords that are semantically similar to the keywords using a machine-learning model trained on training data to classify semantically similar keywords. A set of matchable keywords is compiled that includes the keywords and the additional keywords. The content system identifies candidate instances of digital content based on content keywords assigned to the candidate instances of digital content and the set of matchable keywords. An indication of an instance of digital content is generated for display in a user interface based on the candidate instances of digital content.
