Generating structured data for rich experiences from unstructured data streams

A system comprising:

• a processor;
• and
• memory, the memory including instruction which when executed by the processor, causes the processor to:
• obtain a plurality of information items from a plurality of data sources, each information item including unstructured content;
• provide the information item to a trained machine learning model, wherein the model is trained with training data that includes information items and corresponding labeled entities for a plurality of historical entities;
• receive a formatted request, wherein the formatted request is associated with one or more labeled entities associated with trained machine learning model;
• identify, by the trained machine learning model, multiple entities from the unstructured content based on the formatted request associated with the one or more labeled entities;
• and
• store each identified entity of the identified multiple entities as structured content responsive to the formatted request when a number of matching identified entities for each identified entity of the identified multiple entities exceeds a threshold.

A system for training a machine learning model, the system comprising:

• a processor;
• and
• memory, the memory including instruction which when executed by the processor, causes the processor to:
• receive a request from a requesting entity to train a machine learning model to extract relevant information from unstructured content;
• identify a plurality of keywords from a plurality of information items including unstructured content;
• associate a formatted request for one or more entities with the plurality of keywords;
• train the machine learning model with the plurality of keywords and the formatted request;
• and
• provide the trained model to the requesting entity.