Contextual Voice Search Suggestions Using Local Screen Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital assistant systems face delays and limitations in providing contextually relevant voice search suggestions due to reliance on network communication, which can result in high latency and inability to function without a stable internet connection.
Innovation Solution
A system that analyzes screen data on a user device to identify entities and generate suggested queries locally, using optical character recognition and semantic classification, allowing for immediate and context-aware voice search suggestions without the need for network communication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system relies on network communication to provide voice search suggestions, then it can access external search resources and databases, but it experiences high latency and cannot function without stable internet connection
Solution Approach 1:
The patent segments the search system into two parts: a local component that processes screen data and generates suggestions immediately, and a remote component that provides comprehensive search resources when available. This segmentation allows the system to function reliably offline while maintaining access to external resources when connected, resolving the contradiction between reliability and latency.
Solution Approach 2:
The system performs preliminary action by analyzing screen data and generating voice search suggestions locally before network communication is needed. This preliminary local processing eliminates latency for suggestion generation and ensures functionality even when network connection is unavailable, directly addressing the reliability-latency contradiction.
2Productivity
If the system processes screen data locally to generate suggestions, then latency is reduced and offline functionality is enabled, but device complexity increases
Solution Approach 1:
The device performs self-service by locally analyzing its own screen data and generating voice search suggestions without requiring external processing. This self-service approach improves productivity by eliminating network latency while the complexity is managed by leveraging existing device capabilities rather than adding substantial new hardware.
Solution Approach 2:
The patent applies multi-functionality by using the device's existing screen and processor for dual purposes: displaying content and simultaneously analyzing that content for voice search suggestions. This universal use of existing components improves suggestion generation speed without proportionally increasing device complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach reduces latency, enables voice search suggestions even with limited or no network connectivity, and provides contextually relevant queries, enhancing user experience and flexibility across various user interfaces.
Implementation Method 1
recognizing one or more terms displayed on the screen of the computing device using optical character recognition on the screen data
Data Source
AI summary
Methods, systems, and apparatus for receiving user input that invokes digital assistant functionality; obtaining screen data indicating content displayed on a screen of the computing device; determining a classification for an entity referenced in the content indicated by the screen data; determining a suggested request that refers to the entity based on the determined classification; and providing the suggested request in response to receiving the user input that invokes the digital assistant functionality.