Semantic Segment Text Selection on Touchscreens
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information processing methods on touch screen devices are cumbersome and time-consuming, as they require multi-step operations for selecting and processing text information, lacking semantic analysis and user intent recognition, which hinders user convenience and efficiency.
Innovation Solution
An information processing method that performs natural language understanding through word segmentation, named entity recognition, and semantic analysis to identify semantic segments, allowing users to select and operate on these segments with a single touch, and automatically determines candidate operations based on user intent, enabling direct execution of intended actions without leaving the current interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If multi-step operations are used for selecting and processing text information, then text processing can be performed, but user convenience deteriorates and operation time increases
Solution Approach 1:
The patent segments text into semantic units (words, phrases, sentences) and associates multiple operations with each segment. When users select a semantic segment, all associated operations are triggered simultaneously, eliminating the need for multi-step manual selection and processing.
Solution Approach 2:
The system performs preliminary analysis to pre-associate multiple potential operations with each semantic segment before user interaction. This pre-computation enables instant operation execution upon selection, avoiding time-consuming sequential processing during actual use.
2Ease of operation
If word segmentation technique is used for keyword selection, then keyword selection is facilitated, but semantic structure analysis is lacking and user intent cannot be automatically recognized
Solution Approach 1:
The patent merges word segmentation with semantic structure analysis and user intent recognition into a unified processing framework. By combining these techniques, the system maintains the simplicity of keyword selection while enriching it with semantic understanding and automatic intent detection capabilities.
Solution Approach 2:
The semantic segment serves multiple functions simultaneously: it acts as a selectable unit for user interaction, a structured semantic entity for analysis, and a basis for automatic intent recognition. This multi-functionality eliminates the need for separate processing steps for each aspect.
3Measurement precision
If manual selection of each word is required for semantic segments, then precise selection is possible, but operation complexity increases and time consumption increases
Solution Approach 1:
The system automatically identifies and groups semantically related words into segments and associates relevant operations with them. This self-organizing capability eliminates the need for users to manually select each word individually, providing both precise semantic selection and operational simplicity simultaneously.
4Adaptability or versatility
If manual exit and re-entry of interfaces is required for further operations, then application switching can be performed, but user convenience deteriorates and operation time increases
Solution Approach 1:
The patent introduces an intermediary layer that bridges the current interface and target applications. Semantic segments and their associated operations act as mediators that enable direct transitions to relevant applications without manual interface navigation, maintaining application versatility while dramatically improving convenience.
Data Source
AI summary
An information processing apparatus has a touch controllable display for displaying information, and an information processing method includes detecting a specific touch controlled operation on information including text displayed on a display, obtaining the text in the information touched by the specific touch controlled operation as a text-of-interest according to the detected specific touch controlled operation, performing a first natural language understanding processing which is based on word segmentation and named entity recognition on the text-of-interest to obtain a result of the word segmentation and a result of the named entity recognition for the text-of-interest, performing a second natural language understanding processing which is based on semantic analysis on the text-of-interest to obtain structured semantics of the text-of-interest in unit of semantic segments, and displaying the text-of-interest on the display in a manner that the semantic segments are marked.