NORMALIZING DIGITAL CONTENT ACROSS DATABASES AND GENERATING PERSONALIZED CONTENT RECOMMENDATIONS

摘要

Methods and apparatuses are described for normalizing digital content across databases and generating personalized content recommendations. A server normalizes structured text for each content item to generate unstructured text. The server converts the unstructured text into a multidimensional content item feature set. The server trains a model based upon user profile information, historical content consumption information, historical content recommendation information, and the feature sets. The server receives a request including a vector associated with a user of a client device. The server executes the model using the vector as input to generate interaction prediction scores. The server selects scores above a threshold and identifies content items associated with each score. The server retrieves identified items for display, including converting the normalized text for the items into a format compatible with the client device, receives a response to the displayed digital content items, and updates the model based upon the response.