Abstract: Methods, systems and computer program products are provided for prefetching information and/or (pre)allocating computing resources based on predicting classification labels with temporal data. A trained temporal classification model forecasts events (e.g., too numerous for individual modeling) by predicting classification labels indicating whether events will occur, or a number of occurrences of the events, during each of a plurality of future time intervals. Time-series datasets, indicating whether events occurred, or a number of occurrences of the events, during each of a plurality of past time intervals, are transformed into temporal classification datasets. Classifications may be based, at least in part, on extracted features, such as data seasonality, temporal representation, statistical and/or real-time features. Classification labels are used to determine whether to take one or more actions, such as, for example, prefetching information or (pre)allocating a computing resource.

Abstract: Methods, systems and computer program products are provided for prefetching based on historical use and real-time signals. Forecast models may be configured to forecast whether to prefetch information (e.g. keys responsive to queries) for future time intervals based on historical use and internal or external signals that may influence forecasts, such as prevailing conditions. Historical use of keys may be analyzed for patterns and trends with multiple seasonalities per category and/or per key. Time series data and forecasts may be indexed by cache categories and time intervals. Forecast models may be trainable, optimizable, configurable and/or auto-correcting on a per-category and/or a per-key basis. Forecast precision indicators, confidence indicators and configurable thresholds may be used to optimize performance. Operations may be distributed among multiple servers. Tasks may be time-distributed by offsets. Cached information may be assigned a time to live (TTL) independent of other cached information.

Abstract: Methods, systems and computer program products are provided for prefetching information and/or (pre)allocating computing resources based on predicting classification labels with temporal data. A trained temporal classification model forecasts events (e.g., too numerous for individual modeling) by predicting classification labels indicating whether events will occur, or a number of occurrences of the events, during each of a plurality of future time intervals. Time-series datasets, indicating whether events occurred, or a number of occurrences of the events, during each of a plurality of past time intervals, are transformed into temporal classification datasets. Classifications may be based, at least in part, on extracted features, such as data seasonality, temporal representation, statistical and/or real-time features. Classification labels are used to determine whether to take one or more actions, such as, for example, prefetching information or (pre)allocating a computing resource.

Abstract: Methods, systems and computer program products are provided for prefetching based on historical use and real-time signals. Forecast models may be configured to forecast whether to prefetch information (e.g. keys responsive to queries) for future time intervals based on historical use and internal or external signals that may influence forecasts, such as prevailing conditions. Historical use of keys may be analyzed for patterns and trends with multiple seasonalities per category and/or per key. Time series data and forecasts may be indexed by cache categories and time intervals. Forecast models may be trainable, optimizable, configurable and/or auto-correcting on a per-category and/or a per-key basis. Forecast precision indicators, confidence indicators and configurable thresholds may be used to optimize performance. Operations may be distributed among multiple servers. Tasks may be time-distributed by offsets. Cached information may be assigned a time to live (TTL) independent of other cached information.

Abstract: Technologies are described for generating geographically-driven group communications involve maintaining location information for multiple user devices, data defining geographic regions, and rules that identify a geographical region to which the rules applies and a communication and payload to be sent. When an update in the location information, geographical regions or rules is detected, an evaluation is performed to determine whether a user client device is located in the geographical region identified for the rule. If so, the communication and payload defined in the rule are sent to the user client devices for a group of users located in the geographical region for the rule. In some examples, the rule defines a group characteristic condition and the communication and payload are sent to the user client devices for users that satisfy the group characteristic condition.

Abstract: Technologies are described for generating geographically-driven group communications involve maintaining location information for multiple user devices, data defining geographic regions, and rules that identify a geographical region to which the rules applies and a communication and payload to be sent. When an update in the location information, geographical regions or rules is detected, an evaluation is performed to determine whether a user client device is located in the geographical region identified for the rule. If so, the communication and payload defined in the rule are sent to the user client devices for a group of users located in the geographical region for the rule. In some examples, the rule defines a group characteristic condition and the communication and payload are sent to the user client devices for users that satisfy the group characteristic condition.

Abstract: In some embodiments, a first computing system receives, at an application running on a platform of the first computer system, a communication for an object from a second computer system. The application determines that a geofence is associated with the object. The geofence is set by the second computer system and the application restricts access to the object until a requirement associated with the geofence is met. The application configures a location service of the platform to monitor a location of the first computer system using the information for the geofence. A notification is received from the location service when the location of the first computer system meets a requirement of the geofence. Then, the application performs an action for the object when the first computer system meets the requirement of the geofence.

Abstract: Location data and image data are captured at a location. The location data may include GPS coordinates and the image data may include images or videos taken at the location. The image data is processed to identify anchor points associated with the location. The location data and the anchor points are provided to a cloud service that uses the location data and image data to create a map of locations and anchor points. A user can associate a virtual object with one or more anchor points associated with a location. At a later time, when the same or different user visits the location, the virtual object may be displayed to the user in an AR application at anchor points that match the one or more anchor points associated with the location.