Query formulation via task continuum

Abstract

Architecture that comprises a mediation component which identifies engaged applications and, gathers and actively monitors information from the engaged applications (e.g., text displayed directly to the user, text embedded in photos, fingerprint of songs, etc.) to infer the working context of a user. The inferred context can then be handed over to one of the applications, such as a browser (in a form which does not cross the privacy barrier) to provide improved ranking for the suggested queries through the preferred search provider. Since the context is inferred into concepts, no PII (personally-identifiable information) is communicated without user consent--only very high-level contextual concepts are provided to the search engines.

Description

Background technique [0001] The efficiency of task completion is measured by how much time it takes users to complete their tasks. A major contributor to task completion is query formulation. The less time it takes for a user to type a query, find the results, and then refine subsequent queries to find the desired results, the better. One such extreme case is the intelligent personal voice recognition assistant, in which the user no longer needs to type a query on a small touch keyboard, but just speak it. However, speech is not always the preferred way to enter text for various reasons (eg, privacy). [0002] People use multiple desktop applications to accomplish a single task. For example, if a user is researching a "dancing" topic for school, the user will use a first application to write things down, and use a second application (such as a browser) to search for different styles of dance. However, in existing systems, the two applications are completely unrelated to ea...

AI Technical Summary

Problems solved by technology

However, since the applications are usually not associated and not mediated in any way by the operating system (OS), the computing system is not aware of the user's overall goals

Images