Context-Based Voice Command Architecture for Mobile Content Interaction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for locating and interacting with content across multiple devices are cumbersome, time-consuming, and error-prone, especially on small screen devices like smartphones.
Innovation Solution
A computing device that receives voice command inputs, processes them using a language processing system to identify intent and arguments, and uses contextual information to suggest and perform actions, such as searching and sharing content, through a context-based command architecture.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If users manually browse through files to locate content, then they can find the desired document, but the process becomes time-consuming and cumbersome
Solution Approach 1:
The system performs preliminary actions by automatically gathering contextual information about the user's current situation (location, time, active applications, recent interactions) before the user even initiates a search. This pre-computed context enables rapid content retrieval without manual browsing, resolving the contradiction between accurate content location and time efficiency
Solution Approach 2:
The patent replaces the mechanical manual browsing process with an automated voice-based system. Users speak natural language commands instead of manually navigating file systems, and the system uses speech recognition and context analysis to automatically locate and present relevant content, eliminating the time-consuming manual search process while maintaining accurate content retrieval
2Reliability
If users manually compose email messages with attachments, then they can share documents with others, but the process becomes cumbersome and error-prone
Solution Approach 1:
The system performs self-service by automatically gathering recipient information from contextual sources (calendar events, contact lists, meeting participants) and pre-configuring the email message with the correct document attachments. The user simply needs to review and confirm the auto-generated sharing request, which dramatically reduces errors while maintaining ease of operation
Solution Approach 2:
The patent introduces an intermediary intelligent assistant that mediates between the user's intent to share content and the actual email composition process. This intermediary automatically handles the complex tasks of identifying recipients, selecting the correct document, attaching files, and formatting the message, thereby improving reliability while keeping the user experience simple and error-free
3Adaptability or versatility
If users operate on small screen devices like smartphones, then they have portability, but the operations become more error-prone and difficult
Solution Approach 1:
The patent replaces manual mechanical interactions with the small touchscreen interface (tapping, scrolling, typing) with voice-based commands. Users can issue complex commands like 'find the sales report and email it to the marketing team' through speech, which is then processed by speech recognition and natural language understanding systems. This substitution eliminates the precision problems inherent in small screen interactions while maintaining full functionality on portable devices
Data Source
AI summary
A computing device receives voice command inputs from a user. The device obtains a language processing result based on the voice command input. The result includes an intent and a set of arguments. The device also obtains a variety of different types of contextual information. An action is identified based on the intent, the arguments, and the contextual information, and the device then suggests the action by displaying a user selectable input mechanism that can be actuated by the user to perform the action. The device can automatically perform the action as well.