Handheld Text Input Character Segment Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for text input on handheld devices, such as pinyin Chinese input, face challenges in accurately determining the intended Standard Mandarin character when multiple characters correspond to a single pin, leading to difficulty in generating the correct character interpretation.

Innovation Solution

The implementation of a handheld electronic device with a processor and memory that employs a segment learning routine, which converts input sequences into raw inputs, compares them with stored generic and learned segments, and uses algorithms like the Maximum Matching Algorithm to provide a character interpretation, allowing for customization through user interaction and learning from input patterns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If the simple maximum matching algorithm is used to generate character interpretation, then the largest Chinese words are obtained, but the accuracy of matching the intended character is reduced

Engineering Contradiction:

Improveword lengthVSAvoidcharacter interpretation accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent segments the character interpretation process into multiple stages: initial character interpretation using maximum matching algorithm, identification of ambiguous characters, presentation of alternative interpretations, and user feedback collection. This segmentation allows the system to balance between obtaining long words and maintaining accuracy by correcting errors at later stages.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system implements feedback mechanisms where user selections and corrections are captured and used to refine future character interpretations. The feedback loop allows the system to learn from user preferences and improve accuracy over time, resolving the contradiction between speed/length and precision.

Inventive Principle:

Principle #23Feedback

2Adaptability or versatility

If multiple Standard Mandarin characters correspond to a single pin, then more character options are available, but the difficulty in determining the intended character increases

Engineering Contradiction:

Improvecharacter option varietyVSAvoidintended character identification difficulty

Core Design Contradiction:

Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system dynamically adjusts the character interpretation process based on contextual information and user behavior patterns. It transitions from static algorithmic matching to dynamic adaptation by incorporating user feedback, learning common usage patterns, and adjusting probability distributions for character selection based on observed preferences.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The patent changes parameters such as character frequency weights, context relevance scores, and user preference probabilities to optimize character selection. By dynamically adjusting these parameters based on user feedback and contextual analysis, the system resolves the difficulty of identifying the intended character among multiple options.

Inventive Principle:

Principle #35Parameter changes

3Adaptability or versatility

If a Latin keyboard is used for pinyin Chinese input, then text input in Standard Mandarin is enabled, but substantial difficulty exists in determining the specific character to output

Engineering Contradiction:

Improvelanguage input capabilityVSAvoidcharacter selection ease

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The system introduces an intermediary processing layer between the Latin keyboard input and the Standard Mandarin character output. This intermediary layer includes context analysis, probability calculation, and user feedback integration that mediates the mapping process, making it easier for users to obtain the intended character without directly managing the complexity of multiple character options.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system progressively becomes self-adjusting by automatically learning from user selections and corrections. It self-optimizes the character interpretation process by incorporating user feedback into its probability models, reducing the operational difficulty over time as it adapts to individual user preferences and typing patterns.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS9286288B2Method of learning character segments during text input, and associated handheld electronic device

Publication Date: 2016.03.15 MALIKIE INNOVATIONS LTD

AI summary

An improved method of learning character segments during text input enables facilitated text input on an improved handheld electronic device. In response to a series of inputs, segments and other objects are analyzed to generate a proposed character interpretation of the series of inputs. Responsive to detecting a replacement of a character of the character interpretation with another character, a character learning string comprising the another character and a number of additional characters of the character interpretation are stored as a candidate. In response to another series of inputs, another proposed character interpretation is generated. Responsive to detecting another replacement of a character of the another character interpretation with a different character, another character learning string comprising the different character and a number of characters of the another character interpretation are compared with the stored candidate. If a set of characters in the another character learning string match characters in the candidate, the set of characters are stored as a segment.