RECOMMENDATIONS AND TARGETED ADVERTISING BASED UPON DIRECTIONS REQUESTS ACTIVITY AND DATA

• Main Authors: HORVITZ ERIC, KRUMM JOHN CHARLES
• Format: Patent
• Language: English
• Published: 12.01.2012
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; GYROSCOPIC INSTRUMENTS; MEASURING; MEASURING DISTANCES, LEVELS OR BEARINGS; NAVIGATION; PHOTOGRAMMETRY OR VIDEOGRAMMETRY; PHYSICS; SURVEYING; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR; TESTING

Concepts and technologies are described herein for providing recommendations and/or advertisements based upon route query activity. A web server is configured to receive queries from an entity. The queries and contextual data associated therewith can be analyzed, and data relating to the queries can be stored by the web server as route activity logs. Adjacent routes and explicit waypoint routing can be abstracted via address directories and ontologies to higher-level goals and the route activities and goals. Such data can serve as case libraries for the construction via machine learning of models that predict interests and preferences with visits to locations and the sequencing of such visits. Training data can include correlated contextual data such as the time and day, prior route queries, and weather, to learn predictive models. Predictions about context- and destination-centric goals and interests can be harnessed to predict preferences, target advertising about waypoints and alternative destinations of potential interest, or advertisements about location-centric or location-independent products or services, all of which can drive recommendations in the present or at a future time.