Location-Aware Word Prediction for Mobile Messaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile device text input systems provide generic word predictions that do not account for the specific recipient or location, leading to inefficient and contextually irrelevant suggestions.
Innovation Solution
Implementing a location-aware word prediction system that associates words with recipients and geographic locations, prioritizing predictions based on the identified recipient and device location, and providing context-specific suggestions to the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If generic word prediction is used for all recipients and locations, then the system complexity is low, but the prediction accuracy and relevance deteriorate
Solution Approach 1:
The patent applies local quality by creating recipient-specific and location-specific lexicons that provide different word predictions based on the particular recipient and geographic location. Instead of using a single generic prediction system, the system tailors the lexicon to local contexts (specific recipients and locations), thereby improving prediction accuracy without requiring complete system redesign.
Solution Approach 2:
The patent segments the general lexicon into multiple recipient-specific lexicons and location-specific lexicons. Each lexicon is maintained separately and selected based on the current communication context. This segmentation allows the system to provide accurate predictions for each context while managing complexity through modular organization of lexicons.
2Loss of information
If context-specific word predictions are provided for different recipients and locations, then the prediction relevance improves, but the data storage and processing complexity increases
Solution Approach 1:
The system uses a universal framework that can handle multiple lexicons through a single interface. The prediction system remains multi-functional, capable of switching between different recipient-specific and location-specific lexicons based on context. This universality allows the system to manage multiple data sets without requiring separate processing systems for each lexicon, thereby controlling data storage and processing complexity.
3Adaptability or versatility
If multiple lexicons are maintained for different recipients and locations, then the prediction specificity improves, but the device complexity increases
Solution Approach 1:
The system dynamically selects which lexicon to use based on the current recipient and location context. Rather than managing all lexicons simultaneously in a static structure, the system activates only the relevant lexicon for the current communication context. This dynamic approach improves prediction specificity while reducing the apparent complexity by managing lexicons on-demand rather than all-at-once.
Data Source
AI summary
Word predictions in a message are selected or prioritized based on the recipient of the message and a previous location of use by a user. An input history is created based on messages sent to the recipient from the user at a particular location (e.g., global positioning system coordinates). As the user composes subsequent messages, a current location of the user is determined. Word predictions are performed based on a comparison of the current location to the previous locations, and based on the recipient(s). In further embodiments, location-aware spell-check functionality is provided for the messages.