Text Segmentation Using Character Entry Timing Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current text segmentation algorithms, such as those used for domain name processing and search requests, face challenges in accurately identifying words in strings of characters without spaces, often resulting in incorrect word identification due to reliance on linguistic properties.
Innovation Solution
A method that determines actual word boundaries in strings of characters by analyzing the time between character entries on an input device, combining this data with possible word boundaries from linguistic algorithms, to output accurate words for domain name registration, search requests, and text processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If linguistic-based segmentation algorithms are used to identify words in character strings, then the process can be automated and performed without human intervention, but the accuracy of word identification deteriorates due to linguistic ambiguities
Solution Approach 1:
The patent segments the character string into multiple possible word combinations using linguistic algorithms, then further segments based on character entry timing data. This multi-level segmentation approach allows the system to consider both linguistic validity and user input patterns, resolving the contradiction between automation and accuracy by processing the string in distinct analytical stages.
Solution Approach 2:
The patent changes the parameter basis for segmentation from purely linguistic properties to a combination of linguistic properties and temporal parameters (character entry timing). By introducing timing data as an additional parameter, the system maintains automation while significantly improving word identification accuracy, as the temporal pattern of character entry provides disambiguation information that linguistic algorithms alone cannot provide.
2Adaptability or versatility
If multiple possible word boundaries are identified using linguistic algorithms, then the system can consider various interpretations, but the complexity of determining the correct segmentation increases
Solution Approach 1:
The patent uses character entry timing data as feedback to evaluate and select from multiple possible word boundaries generated by linguistic algorithms. The system compares the timing patterns against each possible segmentation and selects the one that best matches the observed entry rhythm, thereby reducing complexity by providing a clear selection criterion rather than requiring complex analysis of all possibilities.
Solution Approach 2:
The patent introduces character entry timing data as an intermediary element that mediates between the multiple possible linguistic segmentations and the final word identification. This intermediary provides objective temporal evidence that simplifies the selection process, acting as a bridge that resolves the complexity of choosing among multiple valid linguistic interpretations.
3Measurement precision
If character entry timing data is collected and analyzed for each character, then the accuracy of word boundary determination improves, but the amount of data processing and system complexity increases
Solution Approach 1:
The patent extracts only the relevant temporal information (time between character entries) from the raw input data, discarding unnecessary details. This extraction approach maintains high accuracy in word boundary determination while reducing processing complexity by focusing on the single most informative temporal parameter rather than analyzing all possible character properties.
Solution Approach 2:
The patent collects timing data for all character entries (excessive action) but uses only the intervals between consecutive characters (partial action) for the actual segmentation determination. This approach ensures complete data collection for potential edge cases while keeping the core processing simple by focusing on the essential inter-character timing information.
Data Source
AI summary
A method can include receiving a string of characters. The method can include determining one or more possible word boundaries for words in the string of characters based at least partially on a segmentation process. The method can also include determining, for each character in the string of characters, an amount of time between entry of each character on an input device. The method can include determining, based at least partially on the amount of time and the one or more possible word boundaries, one or more actual word boundaries for the words in the string of characters. The method can also include outputting one or more determined words in the string of characters based at least partially on the one or more actual word boundaries.