Abstract: A device in an automated environment can detect patterns in the user's interactions with accessories in the automated environment and can provide feedback to the user based on the patterns. Examples include: suggesting automation of particular actions based on the patterns; suggesting actions that conform to the pattern when the user performs part of the pattern; or suggesting changes to a pattern to conform to a preferred pattern. A state of the group of accessory devices can be changed together based on the pattern of accessory state changes for the group of accessory devices.

Abstract: Techniques are provided for contacting emergency response services when certain conditions are met. In some instances, it may be determined, by a wearable device, whether a user has responded to a first user interface prompt displayed in response to detection of a physical event associated with the user. In accordance with a determination that the user has not responded to the first user interface prompt after expiration of a first time period, certain actions may be performed. For example, a countdown timer may begin to run for a second timer period. During the second period, an audio alert and a haptic alert may be output by the wearable device. In accordance with a determination that the user has not responded to a second user interface prompt prior to expiration of the second time period, a communication channel request may be transmitted to an emergency response service by the wearable device.

Abstract: Methods, systems, and computer program products for determining transit routes through crowd-sourcing, for determining an estimated time of arrival (ETA) of a vehicle of the transit route at a given location, and for providing predictive reminders to a user for catching a vehicle of the transit route. A server receives signal source information about wireless signal sources detected by user devices, including information about a first wireless signal source detected by some devices. The server determines that the first wireless signal source is moving. The server determines that the first wireless signal source is associated with a public transit route upon determining that the signal source information satisfies one or more selection criteria. The server stores information associating the first wireless signal source with the public transit route as transit movement data corresponding to the public transit route.

Abstract: An automated environment can include an accessory device that operates according to an automation rule, to take a prescribed action when a triggering condition occurs. A controller device for the automated environment can determine a user's regular routine and can detect when the user is deviating from the regular routine. The controller device can communicate with accessory devices in the automated environment to modify their behavior relative to the automation rules.

Abstract: Methods, systems, and computer program products for determining transit routes through crowd-sourcing, for determining an estimated time of arrival (ETA) of a vehicle of the transit route at a given location, and for providing predictive reminders to a user for catching a vehicle of the transit route. A server receives signal source information about wireless signal sources detected by user devices, including information about a first wireless signal source detected by some devices. The server determines that the first wireless signal source is moving. The server determines that the first wireless signal source is associated with a public transit route upon determining that the signal source information satisfies one or more selection criteria. The server stores information associating the first wireless signal source with the public transit route as transit movement data corresponding to the public transit route.

Abstract: Techniques are provided for contacting emergency response services when certain conditions are met. In some instances, it may be determined, by a wearable device, whether a user has responded to a first user interface prompt displayed in response to detection of a physical event associated with the user. In accordance with a determination that the user has not responded to the first user interface prompt after expiration of a first time period, certain actions may be performed. For example, a countdown timer may begin to run for a second timer period. During the second period, an audio alert and a haptic alert may be output by the wearable device. In accordance with a determination that the user has not responded to a second user interface prompt prior to expiration of the second time period, a communication channel request may be transmitted to an emergency response service by the wearable device.

Abstract: Techniques are provided for implementing audio looping techniques. In some instances, it may be determined, by a wearable device, whether a user has responded to a user interface prompt displayed in response to detection of a physical event associated with the user. Additionally, the wearable device may transmit a communication channel request to an emergency response service in accordance with a determination that the user has not responded to the user interface prompt after expiration of a time period. Further, the wearable device may transmit an audio message to the emergency response service at least in response to the emergency response service accepting the communication channel request.

Abstract: A device in an automated environment can detect patterns in the user's interactions with accessories in the automated environment and can provide feedback to the user based on the patterns. Examples include: suggesting automation of particular actions based on the patterns; suggesting actions that conform to the pattern when the user performs part of the pattern; or suggesting changes to a pattern to conform to a preferred pattern. A state of the group of accessory devices can be changed together based on the pattern of accessory state changes for the group of accessory devices.

Abstract: A device in an automated environment can detect patterns in the user's interactions with accessories in the automated environment and can provide feedback to the user based on the patterns. Examples include: suggesting automation of particular actions based on the patterns; suggesting actions that conform to the pattern when the user performs part of the pattern; or suggesting changes to a pattern to conform to a preferred pattern.

Abstract: Techniques are provided for implementing audio looping techniques. In some instances, it may be determined, by a wearable device, whether a user has responded to a user interface prompt displayed in response to detection of a physical event associated with the user. Additionally, the wearable device may transmit a communication channel request to an emergency response service in accordance with a determination that the user has not responded to the user interface prompt after expiration of a time period. Further, the wearable device may transmit an audio message to the emergency response service at least in response to the emergency response service accepting the communication channel request.

Abstract: An automated environment can include an accessory device that operates according to an automation rule, to take a prescribed action when a triggering condition occurs. A controller device for the automated environment can determine a user's regular routine and can detect when the user is deviating from the regular routine. The controller device can communicate with accessory devices in the automated environment to modify their behavior relative to the automation rules.

Abstract: Behavior information can be aggregated across multiple automated environments (e.g., across homes in a neighborhood). The automated environments can provide information about detected environment-level behavior patterns to a server. The server can aggregate the patterns across environments in a defined neighborhood and can provide neighborhood-level information back to the participating automated environments. The neighborhood-level information can be used to drive decisions and behavioral changes in individual automated environments.

Abstract: An automated environment can include an accessory device that operates according to an automation rule, to take a prescribed action when a triggering condition occurs. A controller device for the automated environment can determine a user's regular routine and can detect when the user is deviating from the regular routine. The controller device can communicate with accessory devices in the automated environment to modify their behavior relative to the automation rules.

Abstract: In general, in one aspect, a method includes receiving, on a mobile device, an indication that an application executing on the mobile device has entered a background state, determining, based on data received from a location system of the mobile device, that the mobile device has remained within a geographic area during a time interval, the geographic area being defined by a radius determined according to an application type of the application, and disabling at least a portion of the location system of the mobile device.

Abstract: An automated environment can include an accessory device that operates according to an automation rule, to take a prescribed action when a triggering condition occurs. A controller device for the automated environment can determine a user's regular routine and can detect when the user is deviating from the regular routine. The controller device can communicate with accessory devices in the automated environment to modify their behavior relative to the automation rules.

Abstract: An automated environment can monitor its resource consumption at the environment level and detect anomalies. Resource consumption can be monitored using a sparse set of sensors that provide information about the total resource consumption of the automated environment. The sensor data can be analyzed together with information about a behavioral routine of users in the automated environment to define a baseline resource consumption pattern. Once a baseline resource consumption pattern is established, anomalies in resource consumption can be detected and reported to users.

Abstract: Automated behaviors in an environment can be implemented based on aggregation of individual user routines. For example, mobile devices used by users in the environment can provide information about the users' behavior patterns to a coordinator device that can be located in the environment. The coordinator device can analyze the information to detect an aggregate pattern that involves multiple mobile devices and/or multiple users. Based on a detected aggregate patterns, the coordinator can identify behaviors to automate.

Abstract: Methods, systems, and computer program products for determining transit routes through crowd-sourcing, for determining an estimated time of arrival (ETA) of a vehicle of the transit route at a given location, and for providing predictive reminders to a user for catching a vehicle of the transit route. A server receives signal source information about wireless signal sources detected by user devices, including information about a first wireless signal source detected by some devices. The server determines that the first wireless signal source is moving. The server determines that the first wireless signal source is associated with a public transit route upon determining that the signal source information satisfies one or more selection criteria. The server stores information associating the first wireless signal source with the public transit route as transit movement data corresponding to the public transit route.

Abstract: In some implementations, a method includes receiving, from a server, location data identifying locations of access points and mobile access points. A mobile device may determine an identifier of an access point within a communication range. The identifier is compared with the location data to identify parameters for the access point. The access point is determined to be a mobile access point based on the identified parameters included in the location data. In response to identifying the mobile access point, operating parameters executed by the mobile device are updated.

Abstract: Systems, methods and computer program products are disclosed for machine learning to determine preferential device behavior. In some implementations, a server receives inputs, including attributes from a client device, crowd-sourced data from a number of other devices and a priori knowledge. The server includes a concept engine that applies machine-learning process to the inputs. The output of the machine learning process is transported to the client device. At the client device, a client engine associates attributes observed at the device to the machine learning output to determine a user profile. Applications may access the user profile to determine preferential device behavior, such as provide targeted information to the user or take action on the device that is personalized to the user of the device.