Processing folder extracting and summarizing content
A system includes a processor that executes computer executable components stored in a memory. The computer executable components can comprise a user input component that receives user input pertaining to a subject; a collection component that obtains media files pertaining to the subject populates a knowledge base with the obtained files; an extraction component that determined a media type for each obtained file and extracts relevant features and metadata; an analysis component that utilizes a large language model to extract key information from the obtained files; a categorization component that categorizes and tags the files; a summarization component that generates a summary of each file; a generation component that determines a chronological order of the obtained files to be reviewed by a user and generates a graph displaying the determined chronological order; and a feedback component that receives feedback from a user and updates the determined chronological order and graph.
1 . A system, comprising:
a processor that executes computer executable components stored in memory, wherein the computer executable components comprise:
a user input component that receives input from a user pertaining to a subject of interest;
a collection component that obtains media files pertaining to the subject of interest for the user, and populates a knowledge base with the obtained media files;
an extraction component that determines a type of media for each of the obtained media files and extracts relevant features and metadata from each of the obtained media files, based on the determined media type of each of the obtained media files, wherein the extraction component utilizes media-type-specific feature extraction pipelines including extracting bag-of-words representations or sentiment analysis for text documents, performing object detection or classification for image files, or performing speech recognition or audio classification for audio files;
an analysis component that utilizes a large language model to extract key information from the obtained media files and to generate embeddings representing content of the obtained media files;
a data component that stores the embeddings in a vector database configured to enable comparison of the obtained media files based on the embeddings;
a categorization component that categorizes and tags the obtained media files based on complexity, length, or target audience of the obtained media files;
a summarization component that generates a summary of each of the obtained media files, based on the extracted key information;
a generation component that determines relationships between the obtained media files based on the extracted key information and the embeddings, and determines a chronological order of the obtained media files to be reviewed by a user, based on the generated summary, the extracted key information, and the determined relationships, and generates a graph displaying the determined chronological order; and
a feedback component that receives feedback from a user and updates the determined chronological order and graph, based on the received feedback.
2 . The system of claim 1 , wherein the media further comprise at least one of documents, text, images, audio, or video.
3 . The system of claim 1 , wherein the extraction component utilizes a feature engineering module to extract features specific to the type of media.
4 . The system of claim 3 , wherein the extraction component extracts bag-of-words representation and sentiment analysis for text documents, object detection and classification for images, or speech recognition and audio classification for audio files.
5 . The system of claim 3 , wherein the extraction component applies text preprocessing, image resizing, or audio noise reduction to improve accuracy and reliability of extracted features.
6 . The system of claim 1 , wherein the analysis component employs a large multi-modal model trained on diverse data sources to extract summarizations, entities, and topics from the obtained media files.
7 . The system of claim 6 , wherein the analysis component uses the extracted entities and topics to determine relationships between the media files.
8 . The system of claim 1 , wherein the categorization component assigns metadata-based labels to the media files.
9 . The system of claim 8 , wherein the metadata-based labels further comprise a complexity level, a length, or a target audience.
10 . The system of claim 9 , wherein the metadata further comprises a creation date, author, or reference to related materials.
11 . The system of claim 1 , wherein the generation component further determines the chronological order of files based on a document citation, difficulty level, or publication time of a file.
12 . The system of claim 1 , wherein the feedback component collects user input in the form of ratings, comments, or interaction metrics to refine the chronological order, and updates the knowledge base based on the collected user input.
13 . The system of claim 1 , wherein the feedback component employs reinforcement learning techniques to optimize the chronological order based on user engagement or learning outcomes.
14 . The system of claim 1 , further comprising a data component that utilizes a vector database to store embeddings of extracted features, metadata, or user interactions.
15 . The system of claim 1 , further comprising an artificial intelligence component that analyses progress of a user and updates the chronological order based on the user progress.
16 . A computer-implemented method that utilizes a processor that executes computer executable components stored in memory to perform the following acts:
receiving input from a user pertaining to a subject of interest;
obtaining media files pertaining to the subject of interest;
populating a knowledge base with the obtained media files;
determining a type of media for each of the obtained media files;
extracting relevant features and metadata from each of the obtained media files, based on the determined media type of each of the obtained media files, wherein extracting the relevant features and metadata comprises utilizing media-type-specific feature extraction pipelines including extracting bag-of-words representations or sentiment analysis for text documents, performing object detection or classification for image files, or performing speech recognition or audio classification for audio files;
utilizing a large language model to extract key information from the obtained media files and to generate embeddings representing content of the obtained media files;
storing the embeddings in a vector database configured to enable comparison of the obtained media files based on the embeddings;
categorizing and tagging the obtained media files based on complexity, length, or target audience of the obtained media files;
generating a summary of each of the obtained media files based on the extracted key information;
determining relationships between the obtained media files based on the extracted key information and the embeddings;
determining a chronological order of the obtained media files to be reviewed by a user, based on the generated summary, the extracted key information, and the determined relationships;
generating a graph displaying the determined chronological order;
receiving feedback from a user; and
updating the determined chronological order and graph, based on the received feedback.
17 . The computer-implemented method of claim 16 , further comprising applying text preprocessing, image resizing, or audio noise reduction to improve accuracy and reliability of the extracted features.
18 . The computer-implemented method of claim 16 , wherein utilizing a large language model to extract key information further comprises analyzing each media file to identify summarizations, entities, or topics.
19 . The computer-implemented method of claim 16 , further comprising categorizing and tagging the obtained media files by assigning metadata-based labels.
20 . A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
receive input from a user pertaining to a subject of interest;
obtain media files pertaining to the subject of interest;
populate a knowledge base with the obtained media files;
determine a type of media for each of the obtained media files;
extract relevant features and metadata from each of the obtained media files, based on the determined media type of the each of the obtained media files, wherein extracting the relevant features and metadata comprises utilizing media-type-specific feature extraction pipelines including extracting bag-of-words representations or sentiment analysis for text documents, performing object detection or classification for image files, or performing speech recognition or audio classification for audio files;
utilize a large language model to extract key information from the obtained media files, and to generate embeddings representing content of the obtained media files;
store the embeddings in a vector database configured to enable comparison of the obtained media files based on the embeddings;
categorize and tag the obtained media files based on complexity, length, or target audience of the obtained media files;
summarize each of the obtained media files based on the extracted key information;
determine relationships between the obtained media files based on the extracted key information and the embeddings;
determine a chronological order of the obtained media files to be reviewed by a user, based on the generated summary, the extracted key information, and the determined relationships;
generate a graph displaying the determined chronological order;
receive feedback from a user; and
update the determined chronological order and graph, based on the received feedback.