Method for quickly inputting words based on incomplete identification

An incomplete and word-based technology, applied in the input/output process of data processing, character and pattern recognition, special data processing applications, etc., can solve problems such as low input efficiency, increased interaction time, and less popularity, so as to reduce writing The number of times, the effect of improving efficiency

Inactive Publication Date: 2011-10-19
上海驿创信息技术有限公司
View PDF2 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The first method is the current mainstream technology. Its disadvantage is that each character must be completely written, and the user confirms the recognition result before writing the next character. Compared with other input methods such as Pinyin, the input efficiency is very low.
[0004] Method 2 is an improvement on Method 1, allowing users to write multiple words or entire sentences at one time, which relatively reduces the number of interactions between the user and the machine. If the recognition is wrong, the interaction time will be greatly increased, so it is not very popular at present
[0005] Method 3 is an improvement to Method 1. It allows the user to continue writing the second word without waiting for the recognition result after writing the first word, thereby reducing the number of interactions between the user and the machine. The disadvantage is that each word must be complete After writing, the user's writing time has not been reduced, but the writing strength has been increased, and once the recognition is wrong, the interaction time will be greatly increased. It is a new technology that has just been launched.
[0006] Due to the defects of the current concept and method of online handwriting recognition, the efficiency of handwriting recognition input is very low, especially on touch screens such as mobile phones and tablet computers, most of which do not have a stylus. Handwriting recognition input method with low writing intensity

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for quickly inputting words based on incomplete identification
  • Method for quickly inputting words based on incomplete identification
  • Method for quickly inputting words based on incomplete identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] 1. Incomplete recognition of single characters

[0039] (1) Enter this input method.

[0040] (2) The incomplete recognition calculation of a single character is based on the combination of the template and the matching value of the derived template and the statistical value. The calculation formula is as follows: P=r1*P1+r2*P2 ​​(wherein P is the incomplete recognition probability of a single character, P1 is the handwriting of handwritten input and the matching value of the template and the derived template library, P2 is the characteristic statistical value, r1, r2 are weights coefficient). Taking "she" as an example to describe the concept of template and derived template, figure 1 It is the template of the word "she", figure 2 , image 3 , Figure 4 It is a derived template of the word "she".

[0041] (3) Write fonts in the user writing area.

[0042] (4) if Figure 5 As shown, the candidate words are predicted according to the recognition probability and ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

As intelligent mobile phones are popular and tablet computers prevail, touch screens are used more and more widely, and more and more attention is paid to the application of the on-line handwriting identification technology. The traditional handwriting identification is mainly a single-word identification technology, while the invention discloses an on-line handwriting indemnification method which provides a quick handwriting identification function for word input. By utilizing the method provided by the invention to input words, a system can automatically identify the words required to be input by means of a single stoke or a plurality of strokes instead of a complete word spelling, thereby greatly improving the efficiency of on-line handwriting identification entering.

Description

technical field [0001] The invention relates to a word recognition and input method in the online handwriting recognition technology. Background technique [0002] At present, there are mainly three methods for online handwriting recognition input method, one is single (whole) word recognition technology, the other is whole sentence recognition input technology, and the third is superposition input technology. [0003] The first method is the current mainstream technology. Its disadvantage is that each character must be completely written, and the user confirms the recognition result before writing the next character. Compared with other input methods such as pinyin, the input efficiency is very low. [0004] Method 2 is an improvement on Method 1, allowing users to write multiple words or entire sentences at one time, which relatively reduces the number of interactions between the user and the machine. If the recognition is wrong, the interaction time will be greatly incre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F3/048G06F17/30G06K9/62G06F3/023G06F3/0482
Inventor 周红全
Owner 上海驿创信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products