IP Library Granted Patent US 11,200,715
Granted Patent B1
US 11,200,715 · App. 17/230,850 · Granted Dec 14, 2021

Automated creation and design of presentation charts

Inventors: Daisuke Takuma (Tokyo, JP); Yoshinori Kabeya (Kawasaki, JP); Emiko Takeuchi (Tokyo, JP)
Assignee: International Business Machines Corporation
G06T11/206G06F40/106G06F40/186G06F40/20G06T11/60
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,200,715
App. No.
17/230,850
Granted
Dec 14, 2021
Kind
B1
Abstract

A method of creating a presentation includes extracting text parts from content, assigning first attributes to the text parts based on the content and design similarities between the text parts, assigning second attributes to the text parts based on processing the text content to extract contextual similarities between the text parts, determining groups of the text parts based on the first and second attributes, determining first links between the text parts of different groups using the display information and adjacencies of the text parts, determining second links of the text parts to object types defined by a graph restriction listing the object types and their parameters, and outputting a presentation by setting the text parts in the presentation corresponding to the parameters of their linked object type in the graph restriction, wherein the text parts of each of the groups are associated with a same one of the object types.

Claims (52)

1. A computer-implemented method of operating a computer system for creation of shaped presentation data comprising:

receiving text content comprising display information;

extracting a plurality of text parts from the text content and the display information;

assigning first attributes to each of the text parts based on the display information and design similarities between the text parts;

assigning second attributes to each of the text parts based on a processing of the text content by word-embedding to extract contextual similarities between the text parts;

determining a plurality of groups of the text parts based on the first attributes and the second attributes;

determining first links between the text parts of different ones of the groups using the display information, adjacency of the text parts in the text content, and adjacency of the groups in the text content;

determining second links of the text parts to a plurality of object types defined by a graph restriction listing the object types and their parameters; and

outputting a presentation by setting the text parts in the presentation corresponding to the parameters of their linked object type in the graph restriction, wherein the text parts of each of the groups are associated with a same one of the object types.

2. The computer-implemented method of claim 1 , wherein the determination of the first links between the text parts of different ones of the groups are based on one or more of the display information, adjacency of the text parts, and adjacency of the groups of text parts.

3. The computer-implemented method of claim 1 , further comprising:

providing a plurality of design templates defining graph restrictions, including the graph restriction; and

determining a correspondence between the text content and each of the design templates based on a number of the second links determined between the text parts and the object types defined by the graph restriction.

4. The computer-implemented method of claim 3 , further comprising issuing an alert upon determining that the correspondence between the text content and any one of the design templates is less than a threshold.

5. The computer-implemented method of claim 3 , further comprising issuing an alert upon determining that the correspondence between the text content and any one of the design templates is greater than a threshold.

6. The computer-implemented method of claim 1 , further comprising verifying the second links using the first attributes and the second attributes.

7. The computer-implemented method of claim 1 , further comprising:

determining at least one item of the text content that is not logically parallel to other items in the text content; and

using the at least one item of the text content to weigh against the determination of the plurality of groups of the text parts based on the first attributes and the second attributes.

8. The computer-implemented method of claim 1 , wherein the graph restriction is configured to insert a page break into the presentation based on a known output object display area of a computing device.

9. The computer-implemented method of claim 1 , wherein the graph restriction is configured to insert a page break into the presentation based on a relevance of output information contents.

10. The computer-implemented method of claim 1 , further comprising:

creating, automatically, the graph restriction based on the display information of the text content;

preparing the graph restriction with an object image, a size, and a position as external parameters;

generating objects of the graph restriction using objects extracted from the display information of the text content; and

determining numerical parameters for each of the objects of the graph restriction that match the display information of the text content.

11. A non-transitory computer readable storage medium comprising computer executable instructions which when executed by a computer cause the computer to perform a method for creation of shaped presentation data comprising:

receiving text content comprising display information;

extracting a plurality of text parts from the text content and the display information;

assigning first attributes to each of the text parts based on the display information and design similarities between the text parts;

assigning second attributes to each of the text parts based on a processing of the text content by word-embedding to extract contextual similarities between the text parts;

determining a plurality of groups of the text parts based on the first attributes and the second attributes;

determining first links between the text parts of different ones of the groups using the display information, adjacency of the text parts in the text content, and adjacency of the groups in the text content;

determining second links of the text parts to a plurality of object types defined by a graph restriction listing the object types and their parameters; and

outputting a presentation by setting the text parts in the presentation corresponding to the parameters of their linked object type in the graph restriction, wherein the text parts of each of the groups are associated with a same one of the object types.

12. The method of claim 11 , wherein the determination of the first links between the text parts of different ones of the groups are based on one or more of the display information, adjacency of the text parts, and adjacency of the groups of text parts.

13. The method of claim 11 , further comprising:

providing a plurality of design templates defining graph restrictions, including the graph restriction; and

determining a correspondence between the text content and each of the design templates based on a number of the second links determined between the text parts and the object types defined by the graph restriction.

14. The method of claim 13 , further comprising issuing an alert upon determining that the correspondence between the text content and any one of the design templates is less than a threshold.

15. The method of claim 13 , further comprising issuing an alert upon determining that the correspondence between the text content and any one of the design templates is greater than a threshold.

16. The method of claim 11 , further comprising verifying the second links using the first attributes and the second attributes.

17. The method of claim 11 , further comprising:

determining at least one item of the text content that is not logically parallel to other items in the text content; and

using the at least one item of the text content to weigh against the determination of the plurality of groups of the text parts based on the first attributes and the second attributes.

18. The method of claim 11 , wherein the graph restriction is configured to insert a page break into the presentation based on a known output object display area of a computing device.

19. The method of claim 11 , wherein the graph restriction is configured to insert a page break into the presentation based on a relevance of output information contents.

20. The method of claim 11 , further comprising:

creating, automatically, the graph restriction based on the display information of the text content;

preparing the graph restriction with an object image, a size, and a position as external parameters;

generating objects of the graph restriction using objects extracted from the display information of the text content; and

determining numerical parameters for each of the objects of the graph restriction that match the display information of the text content.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 14, 2021
From: TAKUMA, DAISUKE; KABEYA, YOSHINORI; TAKEUCHI, EMIKO
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 055921/0819 →
Cited By (6)
US 12,417,338 US 12,462,451 US 12,499,302 US 12,518,080 US 12,626,048 US 12,718,000