Pseudo-morpheme Word Recommendation Reducing Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for providing recommended words struggle with accurately predicting user intentions due to large data storage requirements and inefficiencies in recommending words based on character inputs.
Innovation Solution
A device and method that recommend words in units of pseudo-morphemes, which are smaller than extended words, and then provide extended words based on selected pseudo-morphemes, reducing data storage needs and improving recommendation accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If recommended words are provided in units of extended words, then the recommendation coverage is comprehensive, but the data storage amount becomes large and recommendation accuracy decreases
Solution Approach 1:
The patent segments extended words into smaller pseudo-morpheme units. Instead of storing and processing complete extended words, the system breaks them down into pseudo-morphemes (e.g., breaking down 'hello_world' into 'hello' and 'world'). This segmentation reduces the overall data storage requirement while maintaining the ability to reconstruct and recommend complete words through combination of these smaller units.
2Measurement precision
If recommended words are provided in units of extended words, then all possible words can be covered, but it becomes difficult to accurately predict user intention
Solution Approach 1:
By segmenting extended words into pseudo-morphemes, the system can more easily analyze and match user input patterns. The segmented units allow for more granular comparison with user input, improving the ability to predict user intention while reducing the complexity of processing large extended word structures.
Solution Approach 2:
The patent applies local quality by treating different parts of extended words (pseudo-morphemes) with different processing characteristics. Each pseudo-morpheme can be independently analyzed and matched against user input, allowing the system to focus computational resources on the most relevant segments for predicting user intention.
3Productivity
If large amounts of extended word data are stored, then the database can provide comprehensive recommendations, but the system efficiency decreases
Solution Approach 1:
Segmenting extended words into pseudo-morphemes significantly reduces the database size. Instead of storing numerous complete extended words, the system stores smaller pseudo-morpheme units that can be recombined. This reduces memory usage and speeds up data retrieval, directly improving system efficiency while maintaining comprehensive recommendation capability.
Data Source
AI summary
A device and method for providing recommended words for at least one input character are provided. The method includes: receiving an input for inputting at least character and recommending one or more extended words including the at least one character by applying the input at least one character to an artificial intelligence (AI) model. An input that selects one of the recommended word is received, and whether a space is located next to the selected extended word is predicted. The selected extended word and the space on a character input window is displayed based on the predicting that the space is located next to the selected extended word, and at least one word to be located next to the space is recommended.