Predictive service for third party application developers
First Claim
Patent Images
1. A method comprising:
- sending a prediction request to a prediction service to construct a prediction result;
receiving a constructed prediction result and an estimation of accuracy of the prediction result; and
configuring an application to adapt to at least one of user preferences, behavior and habits based upon the prediction result and estimation of accuracy of the prediction result;
wherein the prediction request includes a plurality of uniform profile vectors that are used to protect a user'"'"'s privacy and sensitive personal information, which are created by extracting features from databases of a plurality of user devices, and wherein the profile vectors are computed locally on an electronic device based upon usage and/or context data gathered on the device itself.
2 Assignments
0 Petitions
Accused Products
Abstract
Disclosed is an apparatus, method and computer program device which send a prediction request to a prediction service to construct a prediction result, receives a prediction result and an estimation of accuracy of the prediction result from the prediction service and configures an application to adapt to at least one of user preferences, behavior and habits based upon the prediction result and estimation of accuracy of the prediction result. The prediction service can include an over-the-air server which is coupled to a prediction server or a dedicated API residing on one or more user devices and configured to access a prediction server.
-
Citations
19 Claims
-
1. A method comprising:
-
sending a prediction request to a prediction service to construct a prediction result; receiving a constructed prediction result and an estimation of accuracy of the prediction result; and configuring an application to adapt to at least one of user preferences, behavior and habits based upon the prediction result and estimation of accuracy of the prediction result; wherein the prediction request includes a plurality of uniform profile vectors that are used to protect a user'"'"'s privacy and sensitive personal information, which are created by extracting features from databases of a plurality of user devices, and wherein the profile vectors are computed locally on an electronic device based upon usage and/or context data gathered on the device itself. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. An apparatus comprising a processor and a memory including computer program code, wherein the memory and the computer program code are configured, with the processor, to cause the apparatus to perform at least:
-
sending a prediction request to a prediction service to construct a prediction result; receiving a constructed prediction result and an estimation of accuracy of the prediction result; and configuring an application to adapt to at least one of user preferences, behavior and habits based upon the prediction result and estimation of accuracy of the prediction result; wherein the prediction request includes a plurality of uniform profile vectors that are used to protect a user'"'"'s privacy and sensitive personal information, which are created by extracting features from databases of a plurality of user devices, and wherein the profile vectors are computed locally on an electronic device based upon usage and/or context data gathered on the device itself. - View Dependent Claims (15, 16, 17, 18)
-
-
19. An apparatus comprising a processor and a memory including computer program code, wherein the memory and the computer program code are configured, with the processor, to cause the apparatus to perform at least:
-
receiving one or more prediction requests from one or more third parties; calculating a prediction result based on the received prediction request and an estimation of accuracy of the prediction result; and sending the prediction result and the estimation of accuracy to third party to enable the third party to configure an application to adapt to at least one of user preferences, behavior and habits based upon the prediction result and estimation of accuracy of the prediction result; wherein the prediction request includes a plurality of uniform profile vectors that are used to protect a user'"'"'s privacy and sensitive personal information, which are created by extracting features from databases of a plurality of user devices, and wherein the profile vectors are computed locally on an electronic device based upon usage and/or context data gathered on the device itself.
-
Specification