Handwriting text summarization

Patent metadata

Field	Value
Publication number	US-12050878-B2
Application number	US-202217581730-A
Country	US
Kind code	B2
Filing date	Jan 21, 2022
Priority date	Feb 19, 2021
Publication date	Jul 30, 2024
Grant date	Jul 30, 2024

Abstract

The present disclosure relates to a computer-implemented method for handwriting-to-text-summarization, comprising obtaining, via a user interface of a system, a handwriting input representing a handwriting of a user of the system for handwriting-to-text-summarization, recognizing a text in the handwriting input, extracting at least one dynamic feature of the handwriting from the handwriting input, generating a text summary of the text, wherein generating the text summary is based on the text and on the at least one dynamic feature of the handwriting. The present disclosure also relates to a system for handwriting-to-text-summarization, comprising a user interface comprising a capturing subsystem configured to capture a handwriting of a user of the system, and wherein the system is configured to run the method for handwriting-to-text-summarization.

First claim

The invention claimed is:

1. A computer-implemented method for handwriting-to-text-summarization, comprising:
obtaining, via a user interface of a system, a handwriting input representing a handwriting of a user of the system for the handwriting-to-text-summarization;
recognizing a text in the handwriting input;
extracting at least one dynamic feature of the handwriting from the handwriting input;
generating a text summary of the text, wherein generating the text summary is based on the text and on the at least one dynamic feature of the handwriting;
applying the text summary to a collation algorithm configured for comparing the text summary to one or more further text summaries corresponding to one or more further users of one or more further systems for the handwriting-to-text-summarization; and
sampling a collated text summary based on information about the user and on information about the one or more further users, thereby modifying the text summary.

2. The computer-implemented method of claim 1 , wherein the at least one dynamic feature comprises an average writing pressure, an average stroke length, an average stroke duration, or a combination thereof, and wherein averaging is over the text or portions thereof.

3. The computer-implemented method of claim 2 , wherein extracting the at least one dynamic feature of the handwriting from the handwriting input comprises applying the handwriting input to a handwriting dynamics algorithm configured to extract the at least one dynamic feature from the handwriting input.

4. The computer-implemented method of claim 3 , wherein the handwriting dynamics algorithm is further configured to compute one or more of the average writing pressure, the average stroke length, the average stroke duration, or a combination thereof, wherein the averaging is over the text or portions thereof, thereby producing the at least one dynamic feature for the text or for each portion thereof.

5. The computer-implemented method of claim 1 , wherein the handwriting input comprises a first set of data representing the text.

6. The computer-implemented method of claim 5 , wherein recognizing the text in the handwriting input comprises applying the handwriting input to a text pre-processing algorithm configured to recognize the text represented by the handwriting input.

7. The computer-implemented method of claim 6 , wherein the text pre-processing algorithm is further configured to segment the text into one or more portions.

8. The computer-implemented method of claim 7 , wherein generating the text summary of the text based on the text and on the at least one dynamic feature of the handwriting comprises applying the text and the at least one dynamic feature to a text summarization algorithm configured to generate the text summary of the text.

9. The computer-implemented method of claim 8 , wherein the text summarization algorithm comprises applying the one or more portions of the text to an importance classifier configured to classify each portion of the text in terms of at least two classes indicating different levels of importance.

10. The computer-implemented method of claim 6 , wherein the text pre-processing algorithm comprises or is a machine-learning algorithm pre-trained for handwriting-to-text recognition and/or text segmentation.

11. The computer-implemented method of claim 6 , wherein the text pre-processing algorithm is configured to segment the first set of data into individual character vectors and apply a pre-determined vector-to-character mapping to output the text.

12. The computer-implemented method of claim 1 , wherein the handwriting input comprises a second set of data representing properties of the handwriting that indicate information about the user as the handwriting progresses.

13. The computer-implemented method of claim 1 , further comprising:
applying the text summary to a style transfer algorithm configured to modify the text summary so as to reflect the information about the user.

14. The computer-implemented method of claim 1 , further comprising:
applying the text summary to a font modification algorithm configured to change the font of at least one portion of the text summary based on the information about the user.

15. The computer-implemented method of claim 1 , wherein the handwriting input comprises a first set of data representing the text.

16. A system for handwriting-to-text-summarization, comprising a user interface comprising a capturing subsystem configured to capture a handwriting of a user of the system, wherein the system is configured for:
obtaining, via the user interface of the system, a handwriting input representing the handwriting of the user of the system for the handwriting-to-text-summarization;
recognizing a text in the handwriting input;
extracting at least one dynamic feature of the handwriting from the handwriting input;
generating a text summary of the text, wherein generating the text summary is based on the text and on the at least one dynamic feature of the handwriting;
applying the text summary to a collation algorithm configured for comparing the text summary to one or more further text summaries corresponding to one or more further users of one or more further systems for the handwriting-to-text-summarization; and
sampling a collated text summary based on information about the user and on information about the one or more further users, thereby modifying the text summary.

17. The system of claim 16 , further comprising:
a communication interface to couple to one or more systems for the handwriting-to-text-summarization.

18. The system of claim 16 , wherein the at least one dynamic feature comprises an average writing pressure, an average stroke length, an average stroke duration, or a combination thereof, and wherein averaging is over the text or portions thereof.

19. A method for handwriting-to-text-summarization, comprising:
obtaining, via a user interface of a system, a handwriting input representing a handwriting of a user of the system for the handwriting-to-text-summarization;
recognizing a text in the handwriting input, wherein the text is semantically and/or linguistically interpretable with respect to at least one communication language;
extracting at least one dynamic feature of the handwriting from the handwriting input, wherein the handwriting input comprises a first set of data representing the text;
generating a text summary of the text, wherein generating the text summary is based on the text and on the at least one dynamic feature of the handwriting;
applying the text summary to a collation algorithm configured for comparing the text summary to one or more further text summaries corresponding to one or more further users of one or more further systems for the handwriting-to-text-summarization; and
sampling a collated text summary based on information about the user and on information about the one or more further users, thereby modifying the text summary.

20. The method of claim 19 , wherein the at least one dynamic feature comprises an average writing pressure, an average stroke length, an average stroke duration, or a combination thereof, and wherein averaging is over the text or portions thereof.

Assignees

• SOCIéTé BIC

Inventors

• Duffy David

Classifications

• G06V30/2268

  using stroke segmentation · CPC title

• G06F16/345

  Summarisation for human users · CPC title

• G06V30/32

  Digital ink · CPC title

• G06F40/279

  Recognition of textual entities · CPC title

• G06F40/40 Primary

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title