Abstract: A system and method for identifying and labeling locations frequented by a user of a device, where the system and method track geographic positions and environmental or contextual factors as the user moves about, and identify locations of interest to the user via a clustering procedure. As the device collects contextual data, the system and method label each identified location to create a location model. This model allows the device to label new locations as they arise. The model may be periodically updated by separately processing geographic position data gathered after the model was created to determine if the cluster locations and labels remain accurate.

Abstract: A method intercepts correlation instructions related to a plurality of meta-content elements associated with a primary content. The primary content or the meta-content elements may have associated privacy rules. At least one meta-content element of the group is selected as having privacy protected information specified in the privacy rules. A set of meta-content items, of meta-content element, are determined that are subject to a correlation restriction based on evaluation of the privacy rules with respect to each meta-content item contained in the meta-content element, and the privacy rules for the set of meta-content items are enforced.

Abstract: A method for automatic recognition of human activity is provided and includes the steps of decomposing human activity into a plurality of fundamental component attributes needed to perform an activity and defining ontologies of fundamental component attributes from the plurality of the fundamental component attributes identified during the decomposing step for each of a plurality of different targeted activities. The method also includes the steps of converting a data stream captured during a performance of an activity performed by a human into a sequence of fundamental component attributes and classifying the performed activity as one of the plurality of different targeted activities based on a closest match of the sequence of fundamental component attributes obtained during the converting step to at least a part of one of the ontologies of fundamental component attributes defined during the defining step. A system for performing the method is also disclosed.

Abstract: A system and method for identifying and labeling locations frequented by a user of a mobile communication device track geographic positions and environmental or contextual factors as the user moves about, and identify locations of interest to the user via a clustering procedure. As the device collects contextual data, the system and method label each identified location to create a location model. This model allows the device to label new locations as they arise. The model may be periodically updated by separately processing geographic position data gathered after the model was created to determine if the cluster locations and labels remain accurate.

Abstract: User-preference datapoints are collected. At least some of these datapoints are associated with user-preference information about an item (e.g., a movie), and some of these datapoints are associated with user-preference information about an attribute (e.g., a movie genre or an actor). A profile of the user is created based, at least in part, on these datapoints. When a new datapoint is collected, the new datapoint is assigned a user-preference “score.” If, for example, the new datapoint does not come with an explicit user-preference rating, then the score is based on related item and attribute datapoints already in the profile. Depending upon the relationship of the new datapoint to the already existing datapoints, a confidence value is assigned to the user-preference score. The profile is then updated with the new datapoint along with its assigned score and confidence rating. The user profile can be used in performing any number of actions.

Abstract: Disclosed are techniques (300, 500, 600) and apparatuses (102, 700) for drawing an inference using multiple sensors. These techniques and apparatuses enable a computing device to choose (302) a set of sensors that are capable of providing information for an inference, invoke (304) the chosen set of sensors to provide the information, receive (306) the information from at least a subset of the chosen sensors, and draw (308), based on the received information, the inference. In some cases, the set of sensors are chosen such that time or resources of the computing device can be conserved.

Abstract: Disclosed are a system and method for constructing and using a predictive model to generate a prediction signal, also referred to as a classification signal when the signal indicates one of a plurality of distinct classes. In various embodiments, the disclosed technique reduces a size of a predictive Support Vector Model by extracting certain values beforehand and storing only weighting values. The technique does not sacrifice generalization performance but does significantly reduce the model size and accelerate prediction performance. The described system applies to most kernel functions, whether linear or nonlinear.

Abstract: Systems, methods, and devices for determining contexts and determining associated demographic profiles using information received from multiple demographic sensor enabled electronic devices, are disclosed. Contexts can be defined by a description of spatial and/or temporal components. Such contexts can be arbitrarily defined using semantically meaningful and absolute descriptions of time and location. Demographic sensor data is associated with or includes context data that describes the circumstances under which the data was determined. The demographic sensor data can include demographic sensor readings that are implicit indications of a demographic for the context. The sensor data can also include user reported data with explicit descriptions of a demographic for the context. The demographic sensor data can be filtered by context data according a selected context.

Abstract: In a hierarchical profile, each node represents at least one feature of behavioral data collected about an entity profiled, with the topmost node selected as the “statistically most informative” feature of the data. A profile can cover numerous domains and be predictively very powerful in each domain. A number of observations can be “aggregated” together into a single datapoint. In use, the structure of the profile is compared against current information associated with the entity to produce a recommendation or prediction. If the profile represents at least some data aggregation, then new observations are folded into the profile based on statistical weights of the aggregations. Because of the way the profile is created and updated, its hierarchical structure maps the collected observations. Therefore, as new observations are incorporated, if the new observations change the profile's structure significantly, then it can be hypothesized that something “interesting” has happened to the entity.

Abstract: A disclosed content rights management system defines a content usage policy via a conditional rule set contained in metadata. The conditional rule set is correlated to at least one second content. An access control manager determines, dynamically, access rights conferrable to a user device or a server, based on the content usage policy and user history parameters. The embodiments may confer limited access rights for a first activity by a user device, or by a server, with respect to the protected content and the second content, and block a second activity with respect to the protected content and the second content, in response to determining that the request for the second content, in conjunction with the user history parameters, does not comply with the conditional rule set for the second activity.

Abstract: Disclosed are a system and method for constructing and using a predictive model to generate a prediction signal, also referred to as a classification signal when the signal indicates one of a plurality of distinct classes. In various embodiments, the disclosed technique reduces a size of a predictive Support Vector Model by extracting certain values beforehand and storing only weighting values. The technique does not sacrifice generalization performance but does significantly reduce the model size and accelerate prediction performance. The described system applies to most kernel functions, whether linear or nonlinear.

Abstract: In a hierarchical profile, each node represents at least one feature of behavioral data collected about an entity profiled, with the topmost node selected as the “statistically most informative” feature of the data. A profile can cover numerous domains and be predictively very powerful in each domain. A number of observations can be “aggregated” together into a single datapoint. In use, the structure of the profile is compared against current information associated with the entity to produce a recommendation or prediction. If the profile represents at least some data aggregation, then new observations are folded into the profile based on statistical weights of the aggregations. Because of the way the profile is created and updated, its hierarchical structure maps the collected observations. Therefore, as new observations are incorporated, if the new observations change the profile's structure significantly, then it can be hypothesized that something “interesting” has happened to the entity.

Abstract: Generating a sequential semantic representation and a resulting content item sequence or presentation is disclosed. A set of nodes and paths among the nodes are determined. Each node includes a corresponding a set of criteria. The paths define a relationship among the plurality of nodes. Transitional operators that define additional criteria for the nodes, are associated with the paths. Content items that include characteristics that are determined to match the corresponding set of criteria for at least one of the nodes are retrieved.

Abstract: Systems, methods, and devices for determining contexts and determining associated health profiles using information received from multiple health sensor enabled electronic devices, are disclosed. Contexts can be defined by a description of spatial and/or temporal components. Such contexts can be arbitrarily defined using semantically meaningful and absolute descriptions of time and location. Health sensor data is associated with or includes context data that describes the circumstances under which the data was determined. The health sensor data can include health sensor readings that are implicit indications of health for the context. The sensor data can also include user reported data with explicit descriptions of health for the context. The health sensor data can be filtered by context data according a selected context. The filtered sensor data can then be analyzed to determine a health profile for the context that can be output to one or more users or entities.

Abstract: Systems, methods, and devices for determining contexts and determining associated demographic profiles using information received from multiple demographic sensor enabled electronic devices, are disclosed. Contexts can be defined by a description of spatial and/or temporal components. Such contexts can be arbitrarily defined using semantically meaningful and absolute descriptions of time and location. Demographic sensor data is associated with or includes context data that describes the circumstances under which the data was determined. The demographic sensor data can include demographic sensor readings that are implicit indications of a demographic for the context. The sensor data can also include user reported data with explicit descriptions of a demographic for the context. The demographic sensor data can be filtered by context data according a selected context.

Abstract: Systems, methods, and devices for determining contexts and determining associated emotion profiles using information received from multiple emotion sensor enabled electronic devices, are disclosed. Contexts can be defined by a description of spatial and/or temporal components. Such contexts can be arbitrarily defined using semantically meaningful and absolute descriptions of times and locations. Emotion sensor data is associated with or includes context data that describes the circumstances under which the data was determined. The emotion sensor data can include emotion sensor readings that are implicit indications of an emotion for the context. The sensor data can also include user reported data with explicit descriptors of an emotion for the context. The emotion sensor data can be filtered by context data according a selected context. The filtered sensor data can then be analyzed to determine an emotion profile for the context that can be output to one or more users or entities.

Abstract: User-preference datapoints are collected. At least some of these datapoints are associated with user-preference information about an item (e.g., a movie), and some of these datapoints are associated with user-preference information about an attribute (e.g., a movie genre or an actor). A profile of the user is created based, at least in part, on these datapoints. When a new datapoint is collected, the new datapoint is assigned a user-preference “score.” If, for example, the new datapoint does not come with an explicit user-preference rating, then the score is based on related item and attribute datapoints already in the profile. Depending upon the relationship of the new datapoint to the already existing datapoints, a confidence value is assigned to the user-preference score. The profile is then updated with the new datapoint along with its assigned score and confidence rating. The user profile can be used in performing any number of actions.

Abstract: The present disclosure teaches techniques for aggregating observations across multiple sensor-data streams and for presenting the results to users in meaningful ways. Available data are analyzed using a variety of statistical techniques. Significant correlations are presented to users to help them to identify any underlying informative patterns. The presented results help people gain insight into their habits as those habits affect their health and wellness. Users can then make informed decisions about their health, wellness, and environment.

Abstract: Generating a sequential semantic representation and a resulting content item sequence or presentation is disclosed. A set of nodes and paths among the nodes are determined. Each node includes a corresponding a set of criteria. The paths define a relationship among the plurality of nodes. Transitional operators that define additional criteria for the nodes, are associated with the paths. Content items that include characteristics that are determined to match the corresponding set of criteria for at least one of the nodes are retrieved.

Abstract: The power of analytical modeling is added to existing methods for specifying policies. Generally speaking, humans use their knowledge and experience to draft policies at a relatively high level. These policies then incorporate analytical models which provide the intelligence on how to most effectively apply the high-level policy to a particular situation. When a policy is invoked, the analytical model provides up-to-date intelligence at a level of completeness and refinement not possible with previous techniques. As a result, fewer policies need to be drafted, and those few need to be updated less frequently than in previous schemes. Rather than updating the policy itself, the analytical model is automatically updated whenever new data are fed into it. As the analytical model incorporates new observational data, it grows more powerful and thus automatically increases the effectiveness of the high-level policy.