Abstract: A real-time AI-based cheating detection system and process for detecting unauthorized assistance during online learning sessions. The process begins by receiving input data from user device. The input data is pre-processed to ensure user is on a valid online learning platform and enrolled in the correct program. If validation is successful, the data is sent for further analysis. Proving one or more prompts a plurality of AI tools for specific tasks. The system and process employ visual recognition algorithm to detect additional individuals in the webcam feed, audio analysis algorithm to identify multiple voices of unauthorized help, and screen activity analysis algorithm to uncover anomalies during the session. Upon detecting unauthorized assistance, AI-based cheating detection systems and process compiles evidence, including video feeds and textual AI-generated transcripts of the session.

Abstract: A sensitive content detection system and method to enhance the accuracy and reliability of sensitive content detection by analyzing videos using multiple AI engines is disclosed. The sensitive content detection method receives video data from a cloud database, where all recorded videos are stored. A video extractor extracts video frames at pre-defined intervals, each representing a video segment for analysis. A batch of frames is sent to a primary AI engine utilizing machine learning algorithms to detect sensitive content. If sensitive content is found, the corresponding frames are marked positive and sent to secondary AI engines, each specialized in detecting specific types of sensitive content. The results from the primary and secondary AI engines are then aggregated using a consensus mechanism, with the final result based on a predefined agreement threshold.

Abstract: A real-time focus score calculation and visualization system and method for guiding an Artificial Intelligence (AI) Engine to generate a real-time focus score and visualize it for a user are disclosed. The real-time focus score calculation and visualization process involves receiving input data from multiple sources including webcam, screen content, and app usage, and providing the analyzed data to the Artificial Intelligence (AI) Engine to determine the presence, idleness, and focus of the user by utilizing a plurality of multiple machine learning algorithms. The focus score is recalculated every second by the AI Engine to determine the user's current level of engagement and is presented to the user in real-time along with an issue count, current status, or ongoing issue related to the user's current level of engagement, visually color-coded feedback.

Abstract: An artifact generation platform can generate project artifacts by implementing extended context windows on an artificial intelligence model (e.g., a trained neural network). Project artifacts can be generated by processing a set of files (e.g., transcript, audio recording, video recording, audiovisual recording) to extract or generate transcript and/or context tokens. Using user-provided output type instructions and the tokens, a trained neural network can generate a project artifact according to the specific output type and context (e.g., project type, user role, domain, technology stack descriptor). The platform can include a chat bot to enable users to query the project artifact and/or cause computer systems to perform automatic actions using the generated project artifact.