Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A technology for writing mistakes and Chinese, applied in the field of data analysis, can solve the problems of low recognition accuracy and can not reflect the writing accuracy well, and achieve the effect of high recognition success rate
Pending Publication Date: 2020-08-07
北京纽诺智康科技有限公司
View PDF0 Cites 3 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
Due to the complexity of writing Chinese characters and the diversity of each person's writing, simply comparing with the standard template cannot reflect the accuracy of writing well, and the accuracy of recognition is low, which needs to be improved
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0027] A method for identifying Chinese writing errors, comprising the following steps:
[0028] S1. Establish a standardized grid, and establish a standard character database with the grid as a reference. The standard character database includes the gridded point data of each character, that is, the point coordinates of each stroke of each character.
[0029] S2. Practitioners need to use a magnetic induction digital board to carry out writing exercises. Fixed grids are arranged on the digital board, so as to determine the corresponding coordinate range of each grid on the electromagnetic digital board. The coordinate vector of each grid and The coordinate vectors of the standardized grid correspond (the two can be equal or proportional).
[0030] S3. During the writing process, the practitioner fills in the text into the squares of the digital board, and the electromagnetic digital board collects the written strokes, and uploads the collected stroke data to the writing recog...
Embodiment 2
[0044] refer to figure 2 , a system for identifying Chinese writing errors, comprising a computer 1 and a magnetic induction digital tablet 2 communicatively connected with it, a fixed square grid array 3 is arranged on the writing surface of the digital tablet 2, and the computer 1 is loaded with writing Identify software platforms.
[0045] In order to remind the practitioner when writing errors occur, in the present embodiment, a vibration motor is housed in the digital board, and a controller for controlling the vibration motor is housed in the digital board.
[0046] refer to image 3 , the controller adopts single-chip microcomputer and amplifying circuit, among which the single-chip microcomputer adopts AT89C51 chip U1, and the amplifying circuit includes NPN type transistor Q1 and PNP type transistor Q2, the 40th pin of U1 is connected to the power supply VCC, and the 18th pin of U1 There is a crystal oscillator X1 connected between pin 19, capacitor C1 is connected...
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
Login to view more
Abstract
The invention discloses a method for identifying Chinese writing errors. The method comprises the following steps: S1, establishing standard gridding point data of characters; s2, setting grids on a digital panel for practicing writing, and determining a coordinate range corresponding to each grid; s3, during writing, filling the grids of the digital panel with characters, and uploading the acquired stroke data to a writing recognition platform by the electromagnetic digital panel; s4, separating each stroke data area by the writing identification platform, and carrying out point taking processing to obtain coordinate sampling data of strokes in each grid; s5, dividing strokes of the characters according to the coordinate sampling data of the strokes; and S6, after the grids of the strokesare divided, sending the writing data of each character into the model, and performing comparative analysis on the writing data of the character and the point data of each character in the standard character database by utilizing an LSTM algorithm. According to the method, strokes of each character written by a practicer are independently recognized, the recognition success rate is extremely high, and various errors of Chinese writing can be recognized.
Description
technical field [0001] The invention relates to the technical field of data analysis, more specifically, it relates to a method for identifying Chinese writing errors. Background technique [0002] In recent years, in order to improve Chinese learners' writing and memorizing of Chinese characters, some auxiliary writing devices have appeared on the market, such as writing templates, writing recognition devices (such as digital tablets), and the like. The writing module pre-presses a groove with a character shape, and the writer can draw beautiful characters along the groove with a pen. However, using the writing module to practice writing requires a lot of repeated practice, which is time-consuming and labor-intensive. It is not conducive to the practitioner's formation. One's own writing style; the written characters of the practitioner can be recognized by the writing recognition device, and errors can be pointed out when there are writing errors. [0003] However, the ex...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.
Login to view more 
Login to view more