Abstract: A computer-implemented system and method for distributed activity detection is provided. Contextual data collected for a user performing an activity is processed on a mobile computing device. The mobile computing device extracts features from the contextual data and compares the features with a set of models. Each model represents an activity. A confidence score is assigned to each model based on the comparison with the features and the mobile computing device transmits the features to a server when the confidence scores for the models are low. The server trains a new model using the features and sends the new model to the mobile computing device.

Abstract: A computer-implemented system and method for distributed activity detection is provided. Contextual data collected for a user performing an activity is processed on a mobile computing device. The mobile computing device extracts features from the contextual data and compares the features with a set of models. Each model represents an activity. A confidence score is assigned to each model based on the comparison with the features and the mobile computing device transmits the features to a server when the confidence scores for the models are low. The server trains a new model using the features and sends the new model to the mobile computing device.

Abstract: A computer-implemented system and method for predicting activity outcome is provided. A set of outcome models is maintained. Contextual data of a user is collected via one or more computing devices associated with the user. An activity being performed by the user is determined based on the contextual data. The activity is compared to a set of outcome models. A predication is made that the activity will not be successfully completed by the user without assistance based on the comparison. The user is provided with one or more tasks for completion of the activity.

Abstract: An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.

Abstract: A computer-implemented system and method for distributed activity detection is provided. Contextual data collected for a user performing an activity is processed on a mobile computing device. The mobile computing device extracts features from the contextual data and compares the features with a set of models. Each model represents an activity. A confidence score is assigned to each model based on the comparison with the features and the mobile computing device transmits the features to a server when the confidence scores for the models are low. The server trains a new model using the features and sends the new model to the mobile computing device.

Abstract: A computer-implemented system and method for predicting activity outcome based on user attention is provided. Sensor data is collected for a user, and an activity performed by a user is identified based on the sensor data. Features of the user are collected while performing the activity and a subject of focus of the user is determined based on the collected features. An outcome of the activity performed by the user is predicted based on the features and the determined subject of focus.

Abstract: A computer-implemented system and method for providing contextually relevant task recommendations to qualified users is provided. Contextual data for a user is collected via one more sensors associated with the user. An activity being performed by the user is determined based on the contextual data. The activity is compared with a profile of the user and a determination that the user is qualified to perform the activity is verified. The activity is monitored. At least one recommendation for performance of a step is identified during the activity and transmitted to at least one recipient including the user or another user.

Abstract: An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.

Abstract: An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.

Abstract: A computer-implemented system and method for providing contextually relevant task recommendations to qualified users is provided. Sensor data is collected for a user. The user's location is determined and subsequently, an activity of the user is determined based on the sensor data and the location. Two or more recommendable items are scored based on the activity and one or more of the recommendable items with the highest scores are selected. Finally, one or more recipients qualified to perform each of the recommendable items are identified.

Abstract: An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.

Abstract: An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.

Abstract: An exercise feedback system receives exercise data captured by client devices of users performing musculoskeletal exercises. The exercise feedback system may provide captured images to a client device of a physical trainer (PT) who remotely provides feedback on the users' exercise performances, for example, by labeling images as indicative of proper or improper musculoskeletal form. A PT may track multiple users using a central feed, which includes content displayed in an order based on ranking of users by a model. Additionally, the exercise feedback system may provide an augmented reality (AR) environment. For instance, an AR graphic indicating a target musculoskeletal form for an exercise is overlaid on a video feed displayed by a client device. Responsive to detecting that a user's form is aligned to the AR graphic, the exercise feedback system may notify the user and trigger the start of the exercise.

Abstract: Apparatuses and methods for location-based visualization of geo-reference content are provided. Apparatus may include logic for causing a display of a map having at least one tag displayed therewith, and logic for causing the display of a set of content objects in response to selection of the tag, the set of content objects associated with the tag and the geographical location of the map. The content objects may be displayed in a viewing window adjacent the map and selectable by a user. The content objects may be filtered by a user, e.g., indicating that a content object is incorrectly tagged or geo-referenced. The apparatus may dynamically update the content based on user interaction. The set of tags and content objects displayed may vary based on a particular zoom level and associated tags may be displayed in response to selection of a tag and/or a content object.

Abstract: A computer-implemented system and method for providing contextually relevant servicing is provided. A request for servicing is received via a call center and assigned to a user. A context of the user is tracked via sensors that are associated with the user. An activity performed by the user during the servicing is determined based on the context, and one or more recommendations relevant to the identified activity are provided to the user.

Abstract: A computer-implemented system and method for predicting activity outcome based on user attention is provided. Sensor data is collected for a user, and an activity performed by a user is identified based on the sensor data. Features of the user are collected while performing the activity and a subject of focus of the user is determined based on the collected features. An outcome of the activity performed by the user is predicted based on the features and the determined subject of focus.

Abstract: A computer-implemented system and method for distributed activity detection is provided. Contextual data collected for a user performing an activity is processed on a mobile computing device. The mobile computing device extracts features from the contextual data and compares the features with a set of models. Each model represents an activity. A confidence score is assigned to each model based on the comparison with the features and the mobile computing device transmits the features to a server when the confidence scores for the models are low. The server trains a new model using the features and sends the new model to the mobile computing device.

Abstract: A computer-implemented system and method for providing contextually relevant task recommendations to qualified users is provided. Sensor data is collected for a user. The user's location is determined and subsequently, an activity of the user is determined based on the sensor data and the location. Two or more recommendable items are scored based on the activity and one or more of the recommendable items with the highest scores are selected. Finally, one or more recipients qualified to perform each of the recommendable items are identified.

Abstract: A computer-implemented system and method for providing selective contextual exposure within social network situations is provided. Contextual information is generated for users. A plurality of social relationships is defined between the users and each social relationship is formed between one user and one of the remaining users. A set of graph production rules is applied to the user contextual information for each social relationship between the user and the one of the remaining users. The user contextual information is transformed based on the graph production rules. The transformed user contextual information is copied to the contextual information of the remaining user.

Abstract: A centralized location system includes a location update application programming interface (API) to receive varying types of location inputs for a user from at least one location-providing application. A memory stores a location of the user and the location inputs, wherein the location update API periodically updates in the memory the location inputs when location updates are received from the at least one location-providing application. A location export API, upon request from a location-based service application, processes the location inputs to estimate a location of the user, which location estimate replaces the stored location in memory and is sent to the location-based service application. A user interface enables the user to specify a location granularity for at least one of the at least one location-providing application and the location-based service application.