Method and apparatus for determining user context
First Claim
Patent Images
1. A method comprising:
- receiving, by a processor, a user input at a device for specifying a context;
causing, by one or more sensors, recording of context information associated with the device, the user of the device, or a combination thereof, wherein the recorded context information includes sensory information of the device and user interaction information with one or more services associated with the device;
updating, by the processor, a context information training database with the recorded context information;
associating, by the processor, the recorded context information with the context;
causing, at least in part, monitoring of unlabeled context information associated with the device, the user of the device, or a combination thereof;
comparing the unlabeled context information against the recorded context information;
causing, at least in part, recognition of the context associated with the unlabeled context information based, at least in part, on the comparison;
generating a context model based, at least in part, on the recorded context information;
generating a behavior model, independent of the context model, based at least in part, on the recorded context information,wherein the associating of the recorded context information with the context comprises at least in part associating the context model with the context, andwherein the recognition of the context in the unlabeled context information is based, at least in part, on the context model.
3 Assignments
0 Petitions
Accused Products
Abstract
An approach is provided for training a device to associate user, object or device context information with a user defined context. The context information platform receives recorded context information from a device. The associated recorded context information is then associated with the context to enable training of a context model associated with the context.
-
Citations
18 Claims
-
1. A method comprising:
-
receiving, by a processor, a user input at a device for specifying a context; causing, by one or more sensors, recording of context information associated with the device, the user of the device, or a combination thereof, wherein the recorded context information includes sensory information of the device and user interaction information with one or more services associated with the device; updating, by the processor, a context information training database with the recorded context information; associating, by the processor, the recorded context information with the context; causing, at least in part, monitoring of unlabeled context information associated with the device, the user of the device, or a combination thereof; comparing the unlabeled context information against the recorded context information; causing, at least in part, recognition of the context associated with the unlabeled context information based, at least in part, on the comparison; generating a context model based, at least in part, on the recorded context information; generating a behavior model, independent of the context model, based at least in part, on the recorded context information, wherein the associating of the recorded context information with the context comprises at least in part associating the context model with the context, and wherein the recognition of the context in the unlabeled context information is based, at least in part, on the context model. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. An apparatus comprising:
-
at least one processor; and at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following; receive, by the processor, a user input at a device for specifying a context; cause, by one or more sensors, recording of context information associated with the device, the user of the device, or a combination thereof, wherein the recorded context information includes sensory information of the device and user interaction information with one or more services associated with the device; update, by the processor, a context information training database with the recorded context information; associate, by the processor, the recorded context information with the context; cause, at least in part, monitoring of unlabeled context information associated with the device, the user of the device, or a combination thereof; compare the unlabeled context information against the recorded context information; causing, at least in part, recognition of the context associated with the unlabeled context information based, at least in part, on the comparison; generate a context model based, at least in part, on the recorded context information; and generate a behavior model, independent of the context model, based, at least in part, on the recorded context information, wherein the associating of the recorded context information with the context comprises at least in part associating the context model with the context, and wherein the recognition of the context in the unlabeled context information is based, at least in part, on the context model. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A non-transitory computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the following steps:
-
receiving, by the one or more processors, a user input at a device for specifying a context; causing, by one or more sensors, recording of context information associated with the device, the user of the device, or a combination thereof, wherein the recorded context information includes sensory information of the device and user interaction information with one or more services associated with the device; updating, by the one or more processors, a context information training database with the recorded context information; associating, by the one or more processors, the recorded context information with the context; causing, at least in part, monitoring of unlabeled context information associated with the device, the user of the device, or a combination thereof; comparing the unlabeled context information against the recorded context information; causing, at least in part, recognition of the context associated with the unlabeled context information based, at least in part, on the comparison; generating a context model based at least in part, on the recorded context information; and generating a behavior model, independent of the context model, based at least in part, on the recorded context information. - View Dependent Claims (16, 17, 18)
-
Specification