Intelligent reading support

Patent metadata

Field	Value
Publication number	US-11561964-B2
Application number	US-201916601438-A
Country	US
Kind code	B2
Filing date	Oct 14, 2019
Priority date	Oct 14, 2019
Publication date	Jan 24, 2023
Grant date	Jan 24, 2023

Abstract

Embodiments for providing data content consumption support by a processor. Data from one or more data sources may be captured and received by one or more data capturing devices while a user is consuming the data on the one or more data sources. A domain knowledge may be automatically updated with the data. A response may be provided to one or more queries based upon information accessed from the knowledge domain.

First claim

The invention claimed is:

1. A method, by a processor, for providing data content consumption support in a computing environment, comprising:
receiving data from one or more data sources captured by one or more data capturing devices while a user is consuming the data on the one or more data sources;
executing machine learning logic to generate a content model using the data;
automatically updating a knowledge domain with the data; and
providing a response to one or more queries, directed to one or more specific questions regarding content of the data, based upon information accessed from the knowledge domain and an output of the content model.

2. The method of claim 1 , further including:
capturing the one or more queries from the user via an audio capturing or display device, an image capturing or display device, an Internet of Things (“IoT”) device or sensor, a graphical user interface (“GUI”), an electronic stylus, or a combination thereof; or
providing the response via the audio capturing or display device, the image capturing or display device, the IoT device or sensor, the GUI, the electronic stylus, or a combination thereof.

3. The method of claim 1 , further including extracting the data from one or more data sources while the user is consuming the data, wherein the extracted data includes image data, audio data, media data, contextual data, relational data pertaining to current amount of consumed content or historically consumed content, or a combination thereof.

4. The method of claim 1 , further including analyzing the data to identify a current amount of consumed data, the one or more queries relating to selected portions of the consumed data or historically consumed content, or a combination thereof.

5. The method of claim 1 , further including:
enhancing existing data in the domain knowledge with the data; or
suggesting one or more revisions or editions to the data captured from the one or more data sources; or
resetting the domain knowledge upon commencement of consuming alternative data from one or more alternative data sources.

6. The method of claim 1 , further including searching and identifying, in a knowledge graph, one or more concepts, semantic references or definitions, keywords, or one or more relationships between one or more entities from the data according to the one or more queries, wherein the one or more concepts, the semantic references or definitions, the keywords, and the one or more entities are nodes within the knowledge graph representing the domain knowledge.

7. The method of claim 1 , further including implementing executing the machine learning logic to:
perform a natural language processing (“NLP”) operation upon the data;
convert image data, audio data, or a combination thereof to textual data;
determine one or more concepts, semantic references or definitions, keywords, or one or more relationships between one or more entities;
determine a selected amount of consumed data or non-consumed data to be included in the response to the one or more queries;
restrict an alternative selected amount of the consumed data or the non-consumed data from being included in the response to the one or more queries; or
learn one or more concepts, semantic references or definitions, keywords, or one or more relationships between one or more entities from the data.

8. A system for providing data content consumption support in a computing environment, comprising:
one or more computers with executable instructions that when executed cause the system to:
receive data from one or more data sources captured by one or more data capturing devices while a user is consuming the data on the one or more data sources;
execute machine learning logic to generate a content model using the data;
automatically update a knowledge domain with the data; and
provide a response to one or more queries, directed to one or more specific questions regarding content of the data, based upon information accessed from the knowledge domain and an output of the content model.

9. The system of claim 8 , wherein the executable instructions:
capture the one or more queries from the user via an audio capturing or display device, an image capturing or display device, an Internet of Things (“IoT”) device or sensor, a graphical user interface (“GUI”), an electronic stylus, or a combination thereof; or
provide the response via the audio capturing or display device, the image capturing or display device, the IoT device or sensor, the GUI, the electronic stylus, or a combination thereof.

10. The system of claim 8 , wherein the executable instructions extract the data from one or more data sources while the user is consuming the data, wherein the extracted data includes image data, audio data, media data, contextual data, relational data pertaining to current amount of consumed content or historically consumed content, or a combination thereof.

11. The system of claim 8 , wherein the executable instructions analyze the data to identify a current amount of consumed data, the one or more queries relating to selected portions of the consumed data or historically consumed content, or a combination thereof.

12. The system of claim 8 , wherein the executable instructions:
enhance existing data in the domain knowledge with the data; or
suggest one or more revisions or editions to the data captured from the one or more data sources; or
reset the domain knowledge upon commencement of consuming alternative data from one or more alternative data sources.

13. The system of claim 8 , wherein the executable instructions search and identify, in a knowledge graph, one or more concepts, semantic references or definitions, keywords, or one or more relationships between one or more entities from the data according to the one or more queries, wherein the one or more concepts, the semantic references or definitions, the keywords, and the one or more entities are nodes within the knowledge graph representing the domain knowledge.

14. The system of claim 8 , wherein the executable instructions execute the machine learning logic to:
perform a natural language processing (“NLP”) operation upon the data;
convert image data, audio data, or a combination thereof to textual data;
determine one or more concepts, semantic references or definitions, keywords, or one or more relationships between one or more entities;
determine a selected amount of consumed data or non-consumed data to be included in the response to the one or more queries;
restrict an alternative selected amount of the consumed data or the non-consumed data from being included in the response to the one or more queries; or
learns one or more concepts, semantic references or definitions, keywords, or one or more relationships between one or more entities from the data.

15. A computer program product for, by a processor, providing data content consumption support in a computing environment, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:
an executable portion that receives data from one or more data sources captured by one or more data capturing devices while a user is consuming the data on the one or more data sources;
an executable portion that executes machine learning logic to generate a content model using the data;
an executable portion that automatically updates a knowledge domain with the data; and
an executable portion that provides a response to one or more queries, directed to one or more

Assignees

• IBM

Inventors

• Botea Adi
• Buesser Beat
• Chen Bei
• Kishimoto Akihiro

Classifications

• G06N5/022 Primary

  Knowledge engineering; Knowledge acquisition · CPC title

• G06F16/248

  Presentation of query results · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G06N20/00

  Machine learning · CPC title

• G10L2015/088

  Word spotting · CPC title