REMEDYING DEFECTIVE KNOWLEDGE OF A KNOWLEDGE DATABASE

• US 20200134481A1
• Filed: 10/10/2019
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Grant

• Current Assignee: Entigenlogic LLC
• Original Assignee: Entigenlogic LLC
• Inventors: Williams, Frank John, Lazzara, David Ralph, Wurzel, Donald Joseph, Thompson, Paige Kristen, Sundberg, Stephen Emerson, Reed, Ameeta Vasant, Chen, Stephen, Roberson, Dennis Arlen, MacTavish, Thomas James, Knutson, Karl Olaf, Thomas, Jessy, Corns, II, David Michael, Chu, Andrew, Mazurkiewicz, Theodore, Grube, Gary W.
• Granted Patent: US 11,288,583 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/215 Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
• CPC Class Codes: G06F 16/9035 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/247 Thesauruses; Synonyms
• CPC Class Codes: G06F 40/289 Phrasal analysis, e.g. finite state techniques or chunking
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A method includes detecting a defective entigen group within a knowledge database. The defective entigen group includes entigens and one or more entigen relationships between at least some of the entigens. The defective entigen group represents knowledge of a topic. The method further includes obtaining corrective content for the topic based on the defective entigen group and generating a corrective entigen group based on the corrective content. The method further includes updating the defective entigen group utilizing the corrective entigen group to produce a curated entigen group.

Claims

1. A method for execution by a computing device, the method comprises:

detecting a defective entigen group, wherein a knowledge database includes the defective entigen group, wherein the defective entigen group includes a plurality of entigens and one or more entigen relationships between at least some of the plurality of entigens, wherein the defective entigen group represents knowledge of a topic;

obtaining corrective content for the topic based on the defective entigen group;

generating a corrective entigen group based on the corrective content; and

updating the defective entigen group utilizing the corrective entigen group to produce a curated entigen group.

2. The method of claim 1 further comprises:

storing the curated entigen group in the knowledge database.

3. The method of claim 1, wherein the detecting the defective entigen group comprises one or more of:

determining that a number of entigens of the defective entigen group compares unfavorably to a number of other entigens of another entigen group associated with other knowledge of another topic, wherein the knowledge database further includes the other entigen group;

identifying an incorrect entigen of the defective entigen group; and

identifying an incorrect entigen relationship between first and second entigens of the defective entigen group.

4. The method of claim 1, wherein the obtaining the corrective content for the topic based on the defective entigen group comprises:

identifying a defect of the defective entigen group;

identifying a content aspect based on the defect;

selecting a content source based on the content aspect; and

obtaining the corrective content from the content source based on the content aspect.

5. The method of claim 1, wherein the generating the corrective entigen group based on the corrective content comprises:

identifying a set of identigens for each word of the corrective content to produce a plurality of sets of identigens, wherein a set of identigens of the plurality of sets of identigens represents one or more different meanings of a word of the corrective content; and

identifying one valid identigen of each set of identigens of the plurality of sets of identigens by applying identigen rules to the plurality of sets of identigens to produce the corrective entigen group, wherein the corrective entigen group represents a most likely meaning of the corrective content.

6. The method of claim 1, wherein the updating the defective entigen group utilizing the corrective entigen group to produce the curated entigen group comprises one or more of:

replacing an incorrect entigen of the defective entigen group with a correct entigen of the corrective entigen group;

updating an incorrect entigen relationship between first and second entigens of the defective entigen group with a correct entigen relationship between the first and second entigens of the corrective entigen group; and

augmenting the defective entigen group utilizing the corrective entigen group.

7. A computing device of a computing system, the computing device comprises:

an interface;

a local memory; and

a processing module operably coupled to the interface and the local memory, wherein the processing module functions to;

detect a defective entigen group, wherein a knowledge database includes the defective entigen group, wherein the defective entigen group includes a plurality of entigens and one or more entigen relationships between at least some of the plurality of entigens, wherein the defective entigen group represents knowledge of a topic;

obtain, via the interface, corrective content for the topic based on the defective entigen group;

generate a corrective entigen group based on the corrective content; and

update the defective entigen group utilizing the corrective entigen group to produce a curated entigen group.

8. The computing device of claim 7, wherein the processing module further functions to:

store, via the interface, the curated entigen group in the knowledge database.

9. The computing device of claim 7, wherein the processing module functions to detect the defective entigen group by one or more of:

determining that a number of entigens of the defective entigen group compares unfavorably to a number of other entigens of another entigen group associated with other knowledge of another topic, wherein the knowledge database further includes the other entigen group;

identifying an incorrect entigen of the defective entigen group; and

identifying an incorrect entigen relationship between first and second entigens of the defective entigen group.

10. The computing device of claim 7, wherein the processing module functions to obtain the corrective content for the topic based on the defective entigen group by:

identifying a defect of the defective entigen group;

identifying a content aspect based on the defect;

selecting a content source based on the content aspect; and

obtaining, via the interface, the corrective content from the content source based on the content aspect.

11. The computing device of claim 7, wherein the processing module functions to generate the corrective entigen group based on the corrective content by:

identifying a set of identigens for each word of the corrective content to produce a plurality of sets of identigens, wherein a set of identigens of the plurality of sets of identigens represents one or more different meanings of a word of the corrective content; and

identifying one valid identigen of each set of identigens of the plurality of sets of identigens by applying identigen rules to the plurality of sets of identigens to produce the corrective entigen group, wherein the corrective entigen group represents a most likely meaning of the corrective content.

12. The computing device of claim 7, wherein the processing module functions to update the defective entigen group utilizing the corrective entigen group to produce the curated entigen group by one or more of:

replacing an incorrect entigen of the defective entigen group with a correct entigen of the corrective entigen group;

updating an incorrect entigen relationship between first and second entigens of the defective entigen group with a correct entigen relationship between the first and second entigens of the corrective entigen group; and

augmenting the defective entigen group utilizing the corrective entigen group.

13. A computer readable memory comprises:

a first memory element that stores operational instructions that, when executed by a processing module, causes the processing module to;

detect a defective entigen group, wherein a knowledge database includes the defective entigen group, wherein the defective entigen group includes a plurality of entigens and one or more entigen relationships between at least some of the plurality of entigens, wherein the defective entigen group represents knowledge of a topic;

a second memory element that stores operational instructions that, when executed by the processing module, causes the processing module to;

obtain corrective content for the topic based on the defective entigen group;

a third memory element that stores operational instructions that, when executed by the processing module, causes the processing module to;

generate a corrective entigen group based on the corrective content; and

a fourth memory element that stores operational instructions that, when executed by the processing module, causes the processing module to;

update the defective entigen group utilizing the corrective entigen group to produce a curated entigen group.

14. The computer readable memory of claim 13 further comprises:

a fifth memory element that stores operational instructions that, when executed by the processing module, causes the processing module to;

store the curated entigen group in the knowledge database.

15. The computer readable memory of claim 13, wherein the processing module functions to execute the operational instructions stored by the first memory element to cause the processing module to detect the defective entigen group by one or more of:

determining that a number of entigens of the defective entigen group compares unfavorably to a number of other entigens of another entigen group associated with other knowledge of another topic, wherein the knowledge database further includes the other entigen group;

identifying an incorrect entigen of the defective entigen group; and

identifying an incorrect entigen relationship between first and second entigens of the defective entigen group.

16. The computer readable memory of claim 13, wherein the processing module functions to execute the operational instructions stored by the second memory element to cause the processing module to obtain the corrective content for the topic based on the defective entigen group by:

identifying a defect of the defective entigen group;

identifying a content aspect based on the defect;

selecting a content source based on the content aspect; and

obtaining the corrective content from the content source based on the content aspect.

17. The computer readable memory of claim 13, wherein the processing module functions to execute the operational instructions stored by the third memory element to cause the processing module to generate the corrective entigen group based on the corrective content by:

identifying a set of identigens for each word of the corrective content to produce a plurality of sets of identigens, wherein a set of identigens of the plurality of sets of identigens represents one or more different meanings of a word of the corrective content; and

identifying one valid identigen of each set of identigens of the plurality of sets of identigens by applying identigen rules to the plurality of sets of identigens to produce the corrective entigen group, wherein the corrective entigen group represents a most likely meaning of the corrective content.

18. The computer readable memory of claim 13, wherein the processing module functions to execute the operational instructions stored by the fourth memory element to cause the processing module to update the defective entigen group utilizing the corrective entigen group to produce the curated entigen group by one or more of:

replacing an incorrect entigen of the defective entigen group with a correct entigen of the corrective entigen group;

updating an incorrect entigen relationship between first and second entigens of the defective entigen group with a correct entigen relationship between the first and second entigens of the corrective entigen group; and

augmenting the defective entigen group utilizing the corrective entigen group.