Input Method Using Language Model for Fast Shorthand Entry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing input methods, such as prefix matching strategies, require users to accurately memorize the front part of English words, leading to challenges in rapid input and low efficiency, especially when multiple page turns are necessary to find the correct word among numerous candidates.
Innovation Solution
An input method that uses a language model to receive an input string with a fast input intent, acquiring word and phrase candidates by determining complete words or phrases based on shorthand information, and presenting them to the user, thereby improving flexibility and reducing keystrokes needed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If prefix matching strategy is used, then input speed is improved for users who memorize prefixes, but input efficiency deteriorates for users who cannot memorize prefixes and require multiple page turns
Solution Approach 1:
The patent introduces a language model as an intermediary between the input prefix and the candidate words. Instead of directly matching prefixes with dictionary words (which requires user memory), the language model processes the prefix and generates contextually relevant candidates, thereby mediating the interaction and reducing the cognitive burden on users.
Solution Approach 2:
The patent changes the parameter of candidate selection from pure prefix matching to probability-based ranking using language models. This transforms the selection criterion from structural matching (prefix equality) to semantic relevance (language model probability), allowing users to receive more accurate candidates without needing to memorize prefixes.
2Adaptability or versatility
If prefix matching returns multiple candidates, then comprehensive word selection is improved, but operation complexity increases due to multiple page turns
Solution Approach 1:
The patent implements feedback mechanisms where the language model continuously refines candidate rankings based on contextual information. The system provides feedback to users through ranked candidate lists, and users can provide feedback through selection behavior, which further improves the system's ability to predict user intent and reduce the number of pages needed.
Solution Approach 2:
The patent performs preliminary action by pre-calculating and ranking candidate words using language models before user interaction. This preliminary processing ensures that the most relevant candidates are already positioned at the top of the list, eliminating the need for users to perform multiple page turns to find the correct word.
3Ease of manufacture
If traditional input methods are used, then simple implementation is maintained, but input efficiency deteriorates due to memory requirements and page turning
Solution Approach 1:
The patent replaces the mechanical prefix matching system with a language model-based system. Instead of relying on simple string matching algorithms, the system uses probabilistic language models to generate and rank candidates, substituting mechanical operations with intelligent processing that improves input efficiency without significantly complicating implementation.
Data Source
AI summary
An input method, an input device, and an apparatus for input are provided in the embodiments of the present application. The method specifically includes: receiving an input string having a fast input intent, wherein the fast input intent is used to indicate, according to a shorthand information of a word or a phrase corresponding to the input string, the word or the phrase; obtaining word candidates and/or phrase candidates corresponding to the input string according to a language model, wherein the word candidates and the phrase candidates are respectively complete words and complete phrases corresponding to the input string; presenting word candidates and/or phrase candidates to a user. The embodiments of the present application can not only improve the flexibility and application range of the fast input, but also improve the quality of word candidates and/or phrase candidates, thereby improving input efficiency.