Two-dimensional symbol for facilitating machine learning of combined meaning of multiple ideograms contained therein

Patent metadata

Field	Value
Publication number	US-10445568-B2
Application number	US-201916374920-A
Country	US
Kind code	B2
Filing date	Apr 4, 2019
Priority date	Aug 3, 2017
Publication date	Oct 15, 2019
Grant date	Oct 15, 2019

Abstract

Two-dimensional symbols with each containing multiple ideograms for facilitating machine learning are disclosed. Two-dimensional symbol comprises a matrix of N×N pixels of data representing a “super-character”. The matrix is divided into M×M sub-matrices with each of the sub-matrices containing (N/M)×(N/M) pixels. N and M are positive integers or whole numbers, and N is preferably a multiple of M. Each of the sub-matrices represents one ideogram defined in an ideogram collection set. “Super-character” represents at least one meaning each formed with a specific combination of a plurality of ideograms. Ideogram collection set includes, but is not limited to, pictograms, logosyllabic characters, Japanese characters, Korean characters, punctuation marks, numerals, special characters. Logosyllabic characters may contain one or more of Chinese characters, Japanese characters, Korean characters. Features of each ideogram can be represented by more than one layer of two-dimensional symbol.

First claim

What is claimed is:

1. A non-transitory storage medium storing instructions for execution by a processor for facilitating machine learning in a Cellular Neural Networks or Cellular Nonlinear Networks (CNN) based computing system using a stored two-dimensional symbol, the two-dimensional symbol comprising: a matrix of N×N pixels of data containing a super-character, the matrix being divided into M×M sub-matrices with each of the sub-matrices containing (N/M)×(N/M) pixels, where N and M are positive integers, and N is a multiple of M; and said each of the sub-matrices representing one ideogram defined in an ideogram collection set, and the super-character representing at least one meaning each formed with a specific combination of a plurality of ideograms; wherein the instructions include learning the meaning of the super-character within the two-dimensional symbol by classifying the two-dimensional symbol via a trained convolutional neural networks model in the CNN based computing system.

2. The non-transitory storage medium of claim 1 , wherein the super-character is extracted out of the matrix in the CNN based computing system using an image processing technique.

3. The non-transitory storage medium of claim 2 , wherein the image processing technique comprises a convolutional neural networks algorithm.

4. The non-transitory storage medium of claim 3 , wherein the CNN based computing system comprises a semi-conductor chip containing digital circuits dedicated for performing the convolutional neural networks algorithm.

5. The non-transitory storage medium of claim 1 , wherein the super-character comprises a minimum of two and a maximum of M×M ideograms.

6. The non-transitory storage medium of claim 1 , wherein the ideogram collection set comprises pictograms, logosyllabic characters, punctuation marks, numerals and special characters defined by humans.

7. The non-transitory storage medium of claim 6 , wherein the pictograms comprise icons.

8. The non-transitory storage medium of claim 6 , wherein the pictograms comprise one or more Latin letters.

9. The non-transitory storage medium of claim 6 , wherein the logosyllabic characters comprise Chinese characters.

10. The non-transitory storage medium of claim 6 , wherein the logosyllabic characters comprise Japanese characters.

11. The non-transitory storage medium of claim 6 , wherein the logosyllabic characters comprise Korean characters.

12. The non-transitory storage medium of claim 6 , wherein the logosyllabic characters comprise Egyptian hierographs.

13. The non-transitory storage medium of claim 6 , wherein the logosyllabic characters comprise Cuneiform scripts.

14. The non-transitory storage medium of claim 1 , wherein each ideogram comprises at least one feature.

15. The non-transitory storage medium of claim 14 , wherein the at least one feature comprises black and white, which is achieved with each of the N×N pixels to contain one-bit of the data.

16. The non-transitory storage medium of claim 14 , wherein the at least one feature comprises grayscale shades, which is achieved each of the N×N pixels to contain more than one-bit of the data.

17. The non-transitory storage medium of claim 14 , wherein the at least one feature comprises different colors, which is achieved with three respective basic color layers of said each ideogram and, with each of the N×N pixels to contain K-bit of the data, where K is a positive integer.

18. The non-transitory storage medium of claim 14 , wherein the at least one feature comprises a dictionary-like definition, which is achieved using three related layers of said each ideogram with the first layer showing logosyllabic Chinese character, the second layer showing Chinese pinyin for pronunciation and the third layer showing a meaning in English.

Assignees

• Gyrfalcon Tech Inc

Inventors

• Yang Lin
• Dong Patrick Z
• Sun Baohua

Classifications

• G06V30/19173

  Classification techniques · CPC title

• G06V10/82

  using neural networks · CPC title

• G06V40/107

  Static hand or arm · CPC title

• G06N3/08 Primary

  Learning methods · CPC title

• G06N3/045

  Combinations of networks · CPC title