Search International and National Patent Collections
Some content of this application is unavailable at the moment.
If this situation persists, please contact us atFeedback&Contact
1. (US20160275194) Query formulation via task continuum
Note: Text based on automatic Optical Character Recognition processes. Please use the PDF version for legal matters

Claims

1. A system, comprising:
one or more processing units; and
one or more memories storing instructions that, when executed by the one or more processing units, cause the system to perform a method comprising:
identifying one or more user-engaged non-operating system (non-OS) applications;
gathering and monitoring content presented by the one or more user-engaged non-OS applications to determine user context, the user context is based on one or more user actions or one or more predicted user actions with the one or more user-engaged non-OS applications;
determining one or more high-level concepts from the determined user context, wherein each of the one or more high-level concepts is based at least on the one or more user actions or the one or more predicted user actions associated with at least one of the one or more user-engaged non-OS applications;
passing the one or more high-level concepts to a browser application for query formulation, the query formulation comprising formulating at least a portion of a query;
based on the query formulation, automatically returning search results relevant to the determined user context; and
causing the search results to be presented in one of the one or more user-engaged non-OS applications.
2. The system of claim 1, wherein the user context is determined at any point in time based on the content gathered at that point in time.
3. The system of claim 1, wherein the browser application receives one or more most recent contextual concepts from an operating system.
4. The system of claim 1, wherein the method further comprises:
tracking the content presented by the one or more user-engaged non-OS applications; and
clustering the presented content to determine the user context.
5. The system of claim 1, wherein the method further comprises transmitting the determined user context to one or more search providers to improve ranking of query suggestions.
6. The system of claim 1, wherein each of the one or more high-level concepts is absent personally identifiable information.
7. The system of claim 1, further comprising a machine learning system configured to generate user persona information to enhance query formulation.
8. A method, comprising:
gathering and monitoring, at a given point in time during completion of a task, information presented by one or more first user-engaged non-operating system (non-OS) applications, where each of the one or more first user-engaged non-OS applications is an application associated with the completion of the task and the information presented by the one or more first user-engaged non-OS applications is based on one or more user actions or one or more predicted user actions with the one or more first user-engaged non-OS applications;
determining user context from the gathered and monitored information;
determining a high-level concept from the determined user context, wherein the high-level concept is associated at least with the one or more user actions being performed at the given point in time or the one or more predicted user actions at the given point in time with or by at least one of the one or more first user-engaged non-OS applications; and
automatically fetching and passing the high-level concept to one or more second user-engaged non-OS applications, wherein at least one of the one or more second user-engaged non-OS applications uses the high-level concept to assist in completing the task.
9. The method of claim 8, further comprising mediating, by an operating system of a computing device, the fetching and the passing of the high-level concept to the one or more second user-engaged non-OS applications.
10. The method of claim 8, wherein determining the high-level concept comprises clustering the gathered information from the one or more first user-engaged non-OS applications to determine the high-level concept.
11. The method of claim 8, further comprising sharing the determined user context across applications and devices.
12. The method of claim 8, further comprising tracking the information presented by the one or more user-engaged non-OS applications and clustering the content to determine the high-level concept.
13. The method of claim 8, further comprising performing the acts of gathering and monitoring the information, determining the user context, determining the high-level concept, and fetching and passing the high-level concept, for multiple concurring tasks performed on one or more computing devices.
14. The method of claim 8, further comprising performing future sub-task prediction to predict a new sub-task to be performed and future sub-tasks likely to be performed.
15. A method, comprising:
gathering and monitoring information associated with one or more user-engaged applications as relates to completion of a task, the information comprising content presented by the one or more user-engaged applications based on one or more user actions or one or more predicted user actions at given points in time;
continually inferring instances of user context from the information at the given points in time;
deriving one or more high-level concepts from the corresponding instances of the user context, wherein each of the one or more high-level concepts are associated at least with the one or more user actions being performed at the given points in time or the one or more predicted user actions at the given points in time;
servicing requests for the one or more high-level concepts from respective user-engaged applications; and
generating additional information via the respective user-engaged applications based on the high-level concepts, wherein the additional information is provided to at least one of the one or more user-engaged applications during completion of the task.
16. The method of claim 15, wherein the additional information comprises search results, that are ranked at the given points in time based on the corresponding inferred instances of user context.
17. The method of claim 16, further comprising:
gathering and monitoring, at the given points in time, information of one or more dormant applications;
inferring instances of user context from the information of the one or more dormant applications; and
sending the instances of user context inferred from the information of the dormant applications and the instances of user context inferred from the information of the one or more user-engaged applications as an array to a browser for ranking of the search results.
18. The method of claim 17, further comprising re-ranking at least one of search suggestions, web results, advertisements, applications, or rewards based on the inferred instances of user context from the information of the one or more dormant applications and the information of the one or more user-engaged applications.
19. The method of claim 15, further comprising performing future sub-task prediction to predict a new sub-task to be performed and future sub-tasks likely to be performed as part of completing the task.