Statement Generation Module for Diverse Word Insertion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current input recommendation systems in search and input method applications are limited in their ability to assist users by only completing input statements with prefix-based suggestions, lacking diversity in word insertion methods and requiring manual user intervention.
Innovation Solution
A method and device that determine target positions in input statements using a pre-trained position estimation module and a bidirectional Trie tree or neural network model to suggest candidate words for insertion, allowing for diverse word insertion options and automatic completion of statements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If prefix-based completion is used, then input assistance is provided, but word insertion diversity is limited
Solution Approach 1:
The patent segments the input statement into multiple components (prefix, middle, suffix) and identifies multiple target positions where words can be inserted. Instead of only completing from prefix, the system divides the statement structure to enable insertions at beginning, middle, and end positions, thereby increasing word insertion diversity while managing complexity through structured segmentation.
Solution Approach 2:
The patent transitions from one-dimensional prefix-based completion to multi-dimensional insertion by considering multiple positions (before first word, between words, after last word) and multiple insertion sources (prefix statements, suffix statements, middle statements). This dimensional expansion provides diverse insertion options without proportionally increasing system complexity.
2Productivity
If manual cursor movement is required, then incomplete content can be supplemented, but user time is consumed
Solution Approach 1:
The system performs self-service by automatically identifying target positions and generating candidate words for insertion without requiring manual cursor movement. The system autonomously analyzes the input statement structure, determines where insertions are needed, and provides completion suggestions, thereby eliminating time-consuming manual operations while maintaining high input efficiency.
Solution Approach 2:
The system performs preliminary actions by pre-identifying target positions and pre-generating candidate words before the user needs them. By analyzing the input statement structure in advance and preparing insertion options, the system eliminates the need for manual cursor movement and provides immediate completion suggestions, reducing user time investment.
3Measurement precision
If position estimation module is used, then accurate target positions are identified, but computational complexity increases
Solution Approach 1:
The position estimation module uses parameter changes by analyzing various linguistic parameters (word boundaries, statement structure, semantic context) to determine target positions. The module transforms the input statement into structured parameters and uses these to identify insertion points with high accuracy, managing complexity through parameter-based analysis rather than complex algorithms.
Data Source
AI summary
A method and a device for generating a statement are provided. An embodiment includes obtaining an input statement by a user over a terminal; determining at least one target position in the input statement; according to a target position in the at least one target position, determining a statement to be inserted from the input statement; based on the statement to be inserted, determining at least one candidate word to be inserted in the target position; inserting a candidate word in the at least one candidate word into the target position to obtain a candidate statement; and sending the candidate statement to the terminal of the user for display. The embodiment can make candidate statements displayed on the terminal of the user more diversified to assist the user to select an expected statement from candidate statements, thereby saving time of the user spending on manually inserting words.