Systems and methods for autonomous creation of personalized, self-updating curricula

A non-transitory computer-readable medium encoded with instructions, that when executed by one or more processors, cause the one or more processors to carry out a process for automatically generating a curriculum, the process comprising:

• training one or more machine learning models using a training data set comprising extracted keywords that are classified from a variety of source databases, wherein output data from the one or more machine learning models is added to the training data set by the one or more machine learning models to train itself and autonomously produce additional outputs,
• wherein the one or more machine learning models and one or more additional machine learning models or algorithms are configured to:
• receive a user input related to a subject matter for learning;
• search one or more databases for keywords of material related to the user input subject matter;
• generate knowledge areas based on the keywords of the material from the search;
• search the one or more databases for content related to the keywords and extract modules that include material related to the user input subject matter in response to the generated knowledge areas;
• compare two or more modules to determine similarity between the two or more modules;
• merge the two or more modules if the similarity exceeds a threshold;
• populate a map with the knowledge areas and the two or more modules if the similarity does not exceed the threshold;
• create semantic vectors that define a relationship between each module and a knowledge area;
• associate, in the map, the modules with one or more knowledge areas based on the defined relationships.

A computer-implemented method for automatically generating a curriculum, the method comprising:

• training one or more machine learning models using a training data set comprising extracted keywords that are classified from a variety of source databases,
• wherein at least one machine learning model is configured to:
• search one or more databases for a plurality of content elements including content related to a module that is associated with a module title corresponding to a user subject matter input, wherein the content is one of:
• educational content, instructional content, training content, or a combination thereof, and wherein at least a portion of the content elements comprise one or both of:
• audio or video such that the at least one machine learning model is configured to transform audio into text;
• wherein one or more algorithms are configured to receive the plurality of content elements as input and to:
• determine similarity between content elements, wherein keywords for the at least a portion of the content elements are analyzed by the one or more algorithms to increase transcription accuracy;
• select content elements as learning objects based on similarity below a threshold;
• populate a map with the modules and the selected learning objects;
• create semantic vectors that define a relationship between each module and the selected learning objects;
• and
• associate the selected learning objects with a corresponding module based on the defined relationships.