Optimization-based visual context management

Abstract

Improved visual context management techniques are disclosed. By way of example, a technique for updating an existing visual display to incorporate new information comprises obtaining new information requested by a subsequent user query, and dynamically deriving one or more visual transformations for updating at least a portion of the existing display to incorporate the new information, wherein the transformation derivation is modeled as an optimization operation which attempts to balance visual context management constraints and to achieve a desired presentation of intended information.

Description

FIELD IF THE INVENTION [0001] The present invention generally relates to information-seeking systems and, more particularly, to optimization-based techniques for visual context management in such information-seeking systems. BACKGROUND OF THE INVENTION [0002] In human-computer interactions, a computer system needs to dynamically update its visual output presentation when the user asks for a new set of data. The present invention focuses on visual context management, a process that dynamically determines how to incorporate newly requested information into an existing visual context so that users can comprehend all relevant information as a coherent whole. Here, the phrase “visual context” refers to a visual scene that a user perceives when issuing a query. Such a process is often subject to diverse constraints (e.g., ensuring semantic continuity and minimizing visual clutter) and unanticipated information introduced during a human-computer conversation. For example, the introduction ...

AI Technical Summary

Benefits of technology

[0010] Advantageously, to incrementally present diverse, unanticipated information introduced during a human-computer conversation, principles of the invention model visual context management as an optimization problem. One main objective is to find a set of optimal visual transformations that maximize the satisfaction of all relevant constraints (e.g., ensuring semantic continuity and minimizing visual clutter). As a result, principles of the invention are capable of deriving a set of near optimal visual transformations by simultaneously balancing a comprehensive set of constraints. Such techniques are easily extensible, since they preferably use feature-based metrics to uniformly model all visual context management constraints.

Problems solved by technology

Such a process is often subject to diverse constraints (e.g., ensuring semantic continuity and minimizing visual clutter) and unanticipated information introduced during a human-computer conversation.

Without integrating new information into an existing scene, a user may have difficulty in comparing and combining information.

Since it is very difficult to predict how a human-computer conversation would unfold, it is impractical to plan all possible visual context transformations a priori.

However, these approaches normally handle one constraint at a time and do not consider how the constraints themselves may affect one another.

As a result, the visual context management result obtained from such existing approaches may not be desirable.

Images