Dynamic Phrase Expansion for Language Input
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Entering Chinese text using Pinyin can be slow and inefficient, as users need to input corresponding Pinyin text and select desired Chinese words or phrases from conversion engine outputs, often requiring additional input and time to find the correct candidate.
Innovation Solution
Systems and processes for dynamic phrase expansion of language input, where user input is received, converted into candidate words, and expanded candidate phrases are generated and ranked based on likelihood scores, allowing for predicted words and improved selection efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If users input Pinyin text and select from conversion engine outputs, then Chinese text can be entered, but the input process becomes slow and inefficient
Solution Approach 1:
The system performs preliminary action by proactively generating and presenting expanded candidate phrases before the user completes their input. Instead of waiting for the user to type the full Pinyin sequence and then search through candidates, the system anticipates potential phrases and makes them available for selection in advance, significantly reducing the time users spend searching for the correct candidate.
Solution Approach 2:
The system implements self-service by automatically expanding the candidate list based on the user's partial input without requiring additional user effort. The conversion engine autonomously generates expanded phrases from the input Pinyin, ranks them by likelihood, and presents them for selection, eliminating the need for users to manually search or refine their queries.
2Measurement precision
If the conversion engine provides basic candidate words, then conversion between symbolic systems is achieved, but the desired candidate is often not the first presented requiring additional input
Solution Approach 1:
The system uses feedback mechanisms by analyzing user selection patterns and input behavior to continuously improve candidate ranking. The conversion engine learns from user interactions with the candidate list, adjusting the likelihood scores and ordering of expanded phrases to better match user preferences and contextual expectations, thereby increasing the probability that the desired candidate appears first.
Solution Approach 2:
The system applies parameter changes by dynamically adjusting the weighting and scoring parameters of candidate phrases based on contextual factors. The conversion engine modifies likelihood scores according to phrase frequency, contextual relevance, and user behavior patterns, transforming the static candidate list into a dynamically optimized selection that adapts to changing user needs and contextual cues.
Data Source
AI summary
The present disclosure generally relates to dynamic phrase expansion for language input. In one example process, a user input comprising text of a first symbolic system is received. The process determines, based on the text, a plurality of sets of one or more candidate words of a second symbolic system. The process determines, based on at least a portion of the plurality of sets of one or more candidate words, a plurality of expanded candidate phrases. Each expanded candidate phrase comprises at least one word of a respective set of one or more candidate words of the plurality of sets of one or more candidate words and one or more predicted words based on the at least one word of the respective set of one or more candidate words. One or more expanded candidate phrases of the plurality of expanded candidate phrases are displayed for user selection.