A computer implemented method comprising instructions stored on a non-transitory storage medium and run on a hardware processor in a computing device for creating, presenting, sharing, organizing and analyzing knowledge on a subject matter through a plurality of algorithms, the method comprises the steps of:
- collecting a plurality of resources or documents related to a particular topic from a user or content provider and extracting a key information related to the particular topic from the plurality of resources or documents through a Resource Injection and Preprocessing module loaded on the computing device, and wherein a raw text, a plurality of words tagged with position information and a plurality of images in the plurality of resources or documents are extracted along with a metadata about the plurality of words tagged with position information and a plurality of images in a resource or document are extracted along with a metadata about the plurality of resources or documents;
- parsing the resource or document to extract and tag all words in the resource or document through a parsing module loaded on the computing device using an algorithm, and wherein the extracted words are tagged with a position information and a formation information:
- clarifying and tagging the words extracted with the parsing module into parts of speech through a Part-of-Speech (POS) tagging module loaded on the computing device using an algorithm, based on a combination of a rule based on a combination of a rule based algorithm and a stochastic based algorithm;
- automatically generating a knowledge map with a Knowledge engine loaded on the computing device through an algorithm;
- collecting a plurality of user generated knowledge maps created with the extracted words and images through a visual learning interface and data presentation module loaded on the computing device using an algorithm, and wherein the plurality of user generated knowledge maps are audio-visual knowledge maps, and wherein the plurality of user generated knowledge maps comprises a text, an image, a mathematical equation, a drawing, an audio and a video notes/nodes;
- receiving a plurality of knowledge maps created by experts on a subject matter with the visual learning interface and data presentation module using an algorithm;
- combining the automatically generated knowledge map with the plurality of user generated knowledge maps and with the plurality of knowledge maps created by the experts on the subject matter to create a gold standard map for a topic on the subject matter through the visual learning interface and data presentation module using an algorithm;
- and
- assessing an understanding of the user in a subject matter by comparing a user generated knowledge map with the knowledge map created by a teacher or an expert or an automatically generated gold standard map with the visual learning interface and data presentation module using an algorithm;
- wherein the step of collecting the plurality of resources or documents related to the particular topic from the user or content provider and extracting the relevant information comprises:
- acquiring the plurality of resources or documents and placing the acquired documents in a document corpora, and wherein the document corpora is categorized by a subject, a topic and a unit;
- performing a pre-processing operation on the collected resources or documents to determine a type or format of the collected resources or documents, and wherein the pre-processing operation includes a text processing operation, an audio processing operation and a video processing operation;
- and
- extracting a preset information related to the resource or document and wherein the preset information includes topic, file type, file size, author, owner, data created, and data modified;
- and
- wherein the step of parsing the resource or document to extract and tag all words in the resource or document using a parsing module comprises;
- extracting and tagging all words in the resource or document except commonly used words and wherein the commonly used words includes articles, prepositions, conjugation and interjections;
- tagging words with a position information, and wherein the position information includes a paragraph number, a line number, a column number and a row number for text, and wherein the position information includes an actual time offset in minutes or seconds for a video or audio;
- tagging words with a formatting information, and wherein the formatting information includes a font size, a font type, a font style, a section header and a numbered list;
- assigning a document formatting weights for each word in the document based on the formatting information using a plurality of typographical analysis methods;
- calculating an intra-document semantic weight of the key-phrase or word in the document using a plurality of intra-document semantic analysis methods;
- calculating an inter-document semantic weight of the key-phrase or word based on a corpus acquired by analyzing a document corpus;
- combining the inter-document semantic weight and the intra-document semantic weight to create an aggregate semantic weight of the key-phrase or word in the document;
- updating the aggregate semantic weight of the key-phrase or word based on the document formatting weights determined by the typographical analysis;
- and
- collecting and saving the updated aggregate semantic weight for the words in the acquired or collected documents in a database.