Gesture-keyboard decoding using spatial gesture model and trie

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Gesture-based keyboards on computing devices face limitations in accuracy, speed, and adaptability, and often require a dedicated gesture dictionary that is difficult to integrate with multiple on-device dictionaries.

Innovation Solution

A method that outputs a graphical keyboard on a presence-sensitive display, allowing users to enter text by performing a single gesture that increments the determination of candidate words based on alignment points and cost values, using a spatial gesture model to match the gesture with words in a lexicon trie, thereby improving speed and accuracy without the need for a separate gesture dictionary.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If gesture-based keyboards use a dedicated gesture dictionary, then gesture recognition accuracy is improved, but device complexity and integration difficulty increase

Engineering Contradiction:

Improvegesture recognition accuracyVSAvoidkeyboard system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent merges the gesture recognition system with the existing lexical database by integrating gesture paths directly into the trie structure. Instead of maintaining a separate gesture dictionary, the system combines gesture input processing with word lookup, allowing gesture paths to traverse the existing lexical trie and leverage pre-computed n-gram probabilities for scoring candidate words.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The lexical database is made multi-functional by enabling it to serve both traditional keyboard input and gesture-based input. The same trie structure and n-gram data structures are used for both typing and gesture recognition, eliminating the need for separate dedicated structures and reducing overall system complexity.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If gesture-based keyboards require multiple discrete key selections, then input precision is improved, but input speed decreases

Engineering Contradiction:

Improveinput precisionVSAvoidtext entry speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent segments the gesture path into multiple alignment points that correspond to different keys in the sequence. Each alignment point is evaluated independently against the lexical database, allowing the system to process continuous gesture input as discrete key selections without requiring the user to perform separate actions for each key.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary processing by pre-computing n-gram probabilities and organizing the lexical database in a trie structure before gesture input occurs. This allows rapid evaluation of candidate words during gesture recognition, enabling fast text entry while maintaining precision through comprehensive candidate evaluation.

Inventive Principle:

Principle #10Preliminary action

3Measurement precision

If gesture-based keyboards use separate gesture dictionary, then gesture decoding accuracy is improved, but ease of operation deteriorates due to integration difficulty

Engineering Contradiction:

Improvegesture decoding accuracyVSAvoidsystem integration ease

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

Inventive Principle:

Principle #5Merging (Combining)

4Measurement precision

If gesture-based keyboards process complete gestures before decoding, then decoding accuracy is improved, but response time increases

Engineering Contradiction:

Improvedecoding accuracyVSAvoidresponse time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent enables continuous processing during gesture execution by evaluating candidate words incrementally as the gesture progresses. The system continuously updates candidate word scores based on alignment points traversed so far, providing real-time feedback and enabling rapid response without waiting for complete gesture termination.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS9552080B2Incremental feature-based gesture-keyboard decoding

Publication Date: 2017.01.24 GOOGLE LLC

AI summary

In one example, a method includes outputting, at a presence-sensitive display operatively coupled to a computing device, a graphical keyboard comprising a plurality of keys and receiving an indication of a gesture to select a group of keys of the plurality of keys. The method may further include determining, in response to the indication, a candidate word based at least in part on the group of keys. The method may further include determining a group of alignment points traversed by the gesture and respective cost values for each of at least two keys of the plurality of keys. The method may further include comparing the respective cost values for at least each of at least two keys of the plurality of keys to determine a combination of keys having a combined cost value and outputting the candidate word that is based on the respective cost values.