Abstract: In some implementations, a user device (or resident device) can notify the user of anomalous accessory states. For example, the user device can determine which accessory states and contexts represent normal accessory states in the respective contexts. Similarly to scene suggestions, the user device can analyze historical accessory state data and context data to determine an accessory state pattern that indicates a normal state of an accessory for a given context. The user device can compare the current state and/or context of an accessory to historical accessory state data to determine when the current state of the accessory is abnormal for the current context. If the current accessory state is abnormal for the current context, the user device can present a notification to the user informing the user of the anomalous accessory state.

Abstract: In some implementations, a user device can automatically generate scene suggestions and/or trigger suggestions. For example, a scene can be a collection of accessories and corresponding accessory states. When the scene is invoked, the user device can cause the accessories associated with the scene to assume the corresponding accessory states. The user device can automatically determine the accessories and/or corresponding accessory states for a scene based on historical patterns of use represented in historical accessory state data. The user device can automatically determine triggers for automatically invoking scenes based on historical patterns of use. For example, the user device can analyze historical context (e.g., location, time, accessory state, etc.) data associated with accessory state transitions to determine triggers for automatically invoking a scene. The user device can present suggest scenes and/or triggers to the user of the user device.

Abstract: In some implementations, a user device can automatically generate scene suggestions and/or trigger suggestions. For example, a scene can be a collection of accessories and corresponding accessory states. When the scene is invoked, the user device can cause the accessories associated with the scene to assume the corresponding accessory states. The user device can automatically determine the accessories and/or corresponding accessory states for a scene based on historical patterns of use represented in historical accessory state data. The user device can automatically determine triggers for automatically invoking scenes based on historical patterns of use. For example, the user device can analyze historical context (e.g., location, time, accessory state, etc.) data associated with accessory state transitions to determine triggers for automatically invoking a scene. The user device can present suggest scenes and/or triggers to the user of the user device.

Abstract: In some implementations, a resident device can automatically generate scene suggestions and/or trigger suggestions based on historical data aggregated from multiple user devices. For example, a resident device can be a user device that is (e.g., mostly) kept in the home environment. Therefore, the resident device is able to collect accessory state and/or context data when another user device may not be connected to the accessories in the home environment. Moreover, the resident device can collect and/or aggregate accessory state data, context data, and user device state data from across multiple user devices. The resident device can automatically determine the accessories and/or corresponding accessory states for a scene and/or scene triggers based on historical patterns of use represented in the aggregated historical accessory state data. The user device can present suggest scenes and/or triggers to the user of the user device.

Abstract: In some implementations, a user device (or resident device) can notify the user of anomalous accessory states. For example, the user device can determine which accessory states and contexts represent normal accessory states in the respective contexts. Similarly to scene suggestions, the user device can analyze historical accessory state data and context data to determine an accessory state pattern that indicates a normal state of an accessory for a given context. The user device can compare the current state and/or context of an accessory to historical accessory state data to determine when the current state of the accessory is abnormal for the current context. If the current accessory state is abnormal for the current context, the user device can present a notification to the user informing the user of the anomalous accessory state.

Abstract: In some implementations, a resident device can automatically generate scene suggestions and/or trigger suggestions based on historical data aggregated from multiple user devices. For example, a resident device can be a user device that is (e.g., mostly) kept in the home environment. Therefore, the resident device is able to collect accessory state and/or context data when another user device may not be connected to the accessories in the home environment. Moreover, the resident device can collect and/or aggregate accessory state data, context data, and user device state data from across multiple user devices. The resident device can automatically determine the accessories and/or corresponding accessory states for a scene and/or scene triggers based on historical patterns of use represented in the aggregated historical accessory state data. The user device can present suggest scenes and/or triggers to the user of the user device.

Abstract: In some implementations, a user device can automatically generate scene suggestions and/or trigger suggestions. For example, a scene can be a collection of accessories and corresponding accessory states. When the scene is invoked, the user device can cause the accessories associated with the scene to assume the corresponding accessory states. The user device can automatically determine the accessories and/or corresponding accessory states for a scene based on historical patterns of use represented in historical accessory state data. The user device can automatically determine triggers for automatically invoking scenes based on historical patterns of use. For example, the user device can analyze historical context (e.g., location, time, accessory state, etc.) data associated with accessory state transitions to determine triggers for automatically invoking a scene. The user device can present suggest scenes and/or triggers to the user of the user device.

Abstract: A system, method and computer program product automatically present at least one product to at least one client for at least one possible purchase. The system applies a matrix factorization on a binary matrix X representing which clients purchased which products. The system optimizes zero-valued elements in the matrix X that correspond to unknown client-product affinities. The system constructs based on the optimization, a prediction matrix {circumflex over (X)} whose each element value represents a likelihood that a corresponding client purchases a corresponding product. The system identifies at least one client-product pair with the highest value in the matrix {circumflex over (X)}. The system recommends at least one product to at least one client according to the client-product pair with the highest value.