Using classifications from text to determine instances of graphical element types to include in a template layout for digital media output

Patent metadata

Field	Value
Publication number	US-11200366-B2
Application number	US-201916716410-A
Country	US
Kind code	B2
Filing date	Dec 16, 2019
Priority date	Dec 16, 2019
Publication date	Dec 14, 2021
Grant date	Dec 14, 2021

Abstract

Provided are a computer program product, system, and method for using classifications from text to determine instances of graphical element types to include in a template layout for digital media output. Text is processed to determine classifications. The determined classifications of the text are inputted to a machine learning module to output instances for graphical element types. The outputted instances of the graphical element types are rendered in a user interface for a user to select. User selection is received of one of the instances rendered in the user interface for each of the graphical element types. The text with the user selected instances for the graphical element types are rendered in a template layout. The template layout including the text rendered with the user selected instances for the graphical element types is rendered in an output layout of digital media.

First claim

What is claimed is:

1. A computer program product for determining styling and appearance to render text in digital media, the computer program product comprising a computer readable storage medium having computer readable program code embodied therein that executes to perform operations, the operations comprising:
processing attributes of text, with at least one machine learning classifier, to determine classifications of the text;
inputting the determined classifications of the text to a machine learning module to output graphical element types;
rendering, in a user interface, the outputted graphical element types for a user to select;
receiving, by a layout generator, user selection of one of the graphical element types rendered in the user interface;
rendering, by the layout generator, in a template layout, the text with the user selected graphical element type; and
generating, in an output layout of digital media, the template layout including the text rendered with the user selected graphical element type.

2. The computer program product of claim 1 , wherein the user selected graphical element type comprises a selected typeface in which to render the text, wherein the text is rendered in the template layout according to the selected typeface in which to render the text.

3. The computer program product of claim 1 ,
wherein the graphical element types are members of a set of graphical element types comprising: typefaces in which to display the text; color composition in which to render elements in the template layout; images; icons; and a visual representation of numerical data included in the text, and
wherein the classifications are members of a set of classifications comprising: sentiments, concepts, entities, tones, categories, keywords, and semantic roles.

4. The computer program product of claim 1 , wherein the classifications comprise sentiments, concepts, and entities, wherein the processing the attributes of the text further comprises:
providing the text to a tone analyzer machine learning module to determine sentiments of the text;
providing the text to a natural language classifier to determine concepts for the text; and
providing the text to a natural language processing machine learning module to determine entities in the text.

5. The computer program product of claim 1 , wherein the operations further comprise:
receiving user modification to a placement of the text and selected graphical element types rendered in the template layout to produce a modified template layout including the text and the user selected graphical element types, wherein the template layout comprises the modified template layout.

6. The computer program product of claim 5 , wherein the operations further comprise:
inputting the modified template layout including the text and the user selected graphical element types and the determined classifications of the text to a verification machine learning module; and
outputting, by the verification machine learning module whether the modified template layout and content therein is appropriate for the determined classifications with a confidence level exceeding a threshold confidence level, wherein the modified template layout is generated in response to determining that the confidence level exceeds the threshold confidence level.

7. The computer program product of claim 1 , wherein a confidence level is provided with each of the outputted graphical element types, wherein the operations further comprise:
determining a predetermined number of outputted graphical element types having highest confidence levels of the outputted graphical element types, wherein the rendered outputted graphical element types comprise the predetermined number of outputted graphical element types.

8. The computer program product of claim 1 , wherein the operations further comprise:
providing training sets, wherein each training set provides as input a classification and as output a corresponding graphical element type with a confidence level, wherein the training sets comprise preselected design choices of graphical element types to use for different possible classifications of text with a confidence level indicating an appropriateness of the corresponding graphical element type for the input classification; and
for each of the training sets, training the machine learning module to output the corresponding graphical element type for the input classification with the confidence level provided in the training set.

9. The computer program product of claim 1 , wherein the operations further comprising:
training the machine learning module to output the user selected graphical element types with higher degrees of confidence than confidence levels of the user selected graphical element types; and
training the machine learning module to output the graphical element types rendered in the user interface that were not selected by the user with lower degrees of confidence than confidence levels of the graphical element types selected by the user.

10. The computer program product of claim 1 , wherein the operations further comprise:
using metadata describing the outputted graphical element types to search a datastore to access the graphical element types matching the metadata, wherein the outputted graphical element types rendered in the user interface for the user to select comprises the graphical element types accessed from the datastore.

11. A system for determining styling and appearance to render text in digital media, comprising:
a processor;
a machine learning module; and
a computer readable storage medium having computer readable program code embodied therein that executes to perform operations, the operations comprising:
processing attributes of text, with at least one machine learning classifier, to determine classifications of the text;
inputting the determined classifications of the text to the machine learning module to output graphical element types;
rendering, in a user interface, the outputted graphical element types for a user to select;
receiving, by a layout generator, user selection of one of the of the graphical element types rendered in the user interface;
rendering, by the layout generator, in a template layout the text with the user selected graphical element type; and
generating, in an output layout of digital media, the template layout including the text rendered with the user selected graphical element type.

12. The system of claim 11 ,
wherein the graphical element types are members of a set of graphical element types comprising: typefaces in which to display the text; color composition in which to render elements in the template layout; images; icons; and a visual representation of numerical data included in the text, and
wherein the classifications are members of a set of classifications comprising: sentiments, concepts, entities, tones, categories, keywords, and semantic roles.

13. The system of claim 11 , wherein the operations further comprise:
receiving user modification to a placement of the text and selected graphical element types rendered in the template layout to produce a modified template layout including the text and the user selected graphical element types, wherein the template layout comprises the modified template layout.

14. The system of claim 11 , wherein a confidence level is provided with each of the outputted graphical element types, wherein the operations further comprise:
determining a predetermined number of outputted graphical element types having highest confidence levels of the outputted graphical element types, wherein the rendered outputted

Assignees

• IBM

Inventors

• Co Hau
• Lam Joseph

Classifications

• G06F3/04817

  using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title

• G06F8/38

  for implementing user interfaces · CPC title

• G06F8/36 Primary

  Software reuse · CPC title

• G06F9/451

  Execution arrangements for user interfaces · CPC title

• G06N20/00

  Machine learning · CPC title