International Business Machines Corporation

Louis F Roehrs

Michael J Bordash

Gilbert Barron

Anurag Srivastava

Zachary Paul Slayton

Lisa Seacat DeLuca

In embodiments, a ground truth table is used to help determine the relevance of a set of search results from a search query. The ground truth table comprises numerous items, along with a corresponding relevancy ranking for each item. Based on the user interaction with the set of search results, the ground truth table is modified, such that subsequent search queries provide improved results over time. The user interactions can include a click-through action, in which case a user clicked on (or otherwise selected) a search result entry. The user interactions can include a purchase action, wish list addition action, favorite list addition action, and/or a share action, among others. Based on the user interactions, the ranking of an entry in the ground truth table is adjusted. Then, subsequent searches that use the modified ground truth table can provide improved search results.

Modification of ground truth tables based on real-time user interaction

Disclosed aspects include geo-fence management using a cluster analysis technique. A set of dynamic user data is received from a set of users. The cluster analysis technique may be used to process the set of dynamic user data. Accordingly, a geo-fence opportunity event is detected using the cluster analysis technique. Based on a selection criterion with respect to the geo-fence opportunity event, it is determined to provide an opportunity for a subset of the set of users. In response to making the determination, the opportunity can be provided for/to the subset of the set of users.

Geo-fence management using a cluster analysis technique

Disclosed aspects include geo-fence management using a cluster analysis technique. A set of dynamic user data is received from a set of users. The set of dynamic user data may have identification information which identifies one or more users, location information which indicates location for one or more users, and context information which indicates application context for one or more users. The cluster analysis technique may be used to process the set of dynamic user data. Accordingly, a geo-fence opportunity event is detected using the cluster analysis technique. Based on a selection criterion with respect to the geo-fence opportunity event, it is determined to provide an opportunity for a subset of the set of users. In response to making the determination, the opportunity can be provided for/to the subset of the set of users (e.g., sending a notification to the subset of the set of users).

Growing community of inventors

Mountain View, CA, United States of America

Louis F Roehrs