US Patent 11501736 Systems and methods for context-based optical character recognition

Methods, systems, and apparatus, including computer programs stored on computer-readable media, for displaying contextually relevant information, comprising receiving cursor data comprising a location of a cursor on an electronic display, and determining a screenshot of at least a portion of the electronic display. One or more proximate alphanumeric characters may be determined in at least a portion of the screenshot based on the location of the cursor, and at least one of the proximate alphanumeric characters may be matched with one or more terms from a predetermined list of terms. An information card may be caused to be displayed on the electronic display based on the location of the cursor, the information card corresponding to the one or more terms from the predetermined list of terms.