Abstract: A skill-gap analysis and recommender system and method is described that serves as a personalized education and skill (PES) map. It provides a comprehensive presentation of the opportunities afforded by the University along with a detailed analysis of trends for placements and career goals. It conducts a comprehensive analysis of past student data and current market trends to make recommendations that are adapted to each student's profile in line with their individual career goals. This is accomplished using an algorithm for adaptive association pattern mining with a built-in mechanism for creation of meta-categories and drill-down for specifics, so as to meet the needs of every student and not miss infrequent patterns or rare opportunities afforded by the system. For the recommendations generated, the system also provides an assessment of the time-sensitivity of a goal and a mechanism for students to track their progress through prioritizing short and long term goals.
Abstract: Described herein is a method and system for automated, context sensitive and non-intrusive insertion of consumer-adaptive content in video. It assesses ‘context’ in the video that a consumer is viewing through multiple modalities and metadata about the video. The method and system described herein analyzes relevance for a consumer based on multiple factors such as the profile information of the end-user, history of the content, social media and consumer interests and professional or educational background, through patterns from multiple sources. The system also implements local-context through search techniques for localizing sufficiently large, homogenous regions in the image that do not obfuscate protagonists or objects in focus but are viable candidate regions for insertion for the intended content. This makes relevant, curated content available to a user in the most effortless manner without hampering the viewing experience of the main video.
Type:
Grant
Filed:
September 23, 2021
Date of Patent:
February 28, 2023
Assignee:
PES UNIVERSITY
Inventors:
Gowri Srinivasa, Atmik Ajoy, Dhanya Gowrish, Chethan U Mahindrakar
Abstract: Matrix multipliers are computationally complex, and memory intensive algorithms used frequently in a variety of applications, such as deep-learning and scientific computations. Accelerating matrix multiplication involves an inter-play of algorithm-architecture co-design and context-specific design parameters. A performance optimizer intelligently arrives at the right combination of algorithm (203)-architecture specifications (201, 202) for the input design parameters that arrive during real-time for a target-specific design constraint. The run-time customization leads to optimal power-performance-area optimization.
Abstract: Described herein is a method and system for automated, context sensitive and non-intrusive insertion of consumer-adaptive content in video. It assesses ‘context’ in the video that a consumer is viewing through multiple modalities and metadata about the video. The method and system described herein analyzes relevance for a consumer based on multiple factors such as the profile information of the end-user, history of the content, social media and consumer interests and professional or educational background, through patterns from multiple sources. The system also implements local-context through search techniques for localizing sufficiently large, homogenous regions in the image that do not obfuscate protagonists or objects in focus but are viable candidate regions for insertion for the intended content. This makes relevant, curated content available to a user in the most effortless manner without hampering the viewing experience of the main video.
Type:
Application
Filed:
September 23, 2021
Publication date:
January 19, 2023
Applicant:
PES University
Inventors:
Gowri Srinivasa, Atmik Ajoy, Dhanya Gowrish, Chethan U. Mahindrakar