Detecting and improving content relevancy in large content management systems

Patent metadata

Field	Value
Publication number	US-11734586-B2
Application number	US-201916600606-A
Country	US
Kind code	B2
Filing date	Oct 14, 2019
Priority date	Oct 14, 2019
Publication date	Aug 22, 2023
Grant date	Aug 22, 2023

Abstract

A method, a computer system, and a computer program product for managing content relevancy is provided. Embodiments of the present invention may include collecting and analyzing a plurality of data, wherein the plurality of data includes document data, document access data and user data. Embodiments of the present invention may include retrieving topic model content based on the plurality of data. Embodiments of the present invention may include building a machine learning (ML) model to determine one or more topics contained in the topic model content. Embodiments of the present invention may include generating a heatmap based on the user data. Embodiments of the present invention may include building a content relevancy model (CRM) based on the ML model and the heatmap. Embodiments of the present invention may include determining an action state for the document data. Embodiments of the present invention may include storing the CRM.

First claim

What is claimed is:

1. A method for managing content relevancy, the method comprising:
collecting a plurality of data, wherein the plurality of data includes document data, document access data and user data;
analyzing the plurality of data;
retrieving topic model content based on the plurality of data;
building a machine learning (ML) model to determine one or more topics contained in the topic model content;
generating a heatmap based on the user data;
building a content relevancy model (CRM) based on the ML model and the heatmap;
determining an action state for the document data using the CRM, wherein the action state is based on a logistic regression value probability threshold range from stay as-is, promote and reshare, update and refresh, and retire at least a portion of the document data, wherein the document data is published digital content; and
storing the CRM.

2. The method of claim 1 , wherein the document data includes information relating to a document content, a document topic, a document domain or a document subject matter, wherein the document access data includes information relating to when, by whom, how often or for what purpose a document is accessed.

3. The method of claim 1 , wherein the topic model content includes analytics engine data and crowdsourced data.

4. The method of claim 1 , wherein the ML model determines a plurality of topics contained in the document data and the document access data.

5. The method of claim 1 , wherein the heatmap is generated based on a plurality of content read by the user, wherein the plurality of content read by a user is captured with a front facing camera.

6. The method of claim 1 , wherein the action state is updating metadata of a document.

7. A computer system for managing content relevancy, comprising:
one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage media, and program instructions stored on at least one of the one or more computer-readable tangible storage media for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, wherein the computer system is capable of performing a method comprising:
collecting a plurality of data, wherein the plurality of data includes document data, document access data and user data;
analyzing the plurality of data;
retrieving topic model content based on the plurality of data;
building a machine learning (ML) model to determine one or more topics contained in the topic model content;
generating a heatmap based on the user data;
building a content relevancy model (CRM) based on the ML model and the heatmap;
determining an action state for the document data using the CRM, wherein the action state is based on a logistic regression value probability threshold range from stay as-is, promote and reshare, update and refresh, and retire at least a portion of the document data, wherein the document data is published digital content; and
storing the CRM.

8. The computer system of claim 7 , wherein the document data includes information relating to a document content, a document topic, a document domain or a document subject matter, wherein the document access data includes information relating to when, by whom, how often or for what purpose a document is accessed.

9. The computer system of claim 7 , wherein the topic model content includes analytics engine data and crowdsourced data.

10. The computer system of claim 7 , wherein the ML model determines a plurality of topics contained in the document data and the document access data.

11. The computer system of claim 7 , wherein the heatmap is generated based on a plurality of content read by the user, wherein the plurality of content read by a user is captured with a front facing camera.

12. The computer system of claim 7 , wherein the action state is updating metadata of a document.

13. A computer program product for managing content relevancy, comprising:
one or more computer-readable tangible storage media and program instructions stored on at least one of the one or more computer-readable tangible storage media, the program instructions executable by a processor to cause the processor to perform a method comprising:
collecting a plurality of data, wherein the plurality of data includes document data, document access data and user data;
analyzing the plurality of data;
retrieving topic model content based on the plurality of data;
building a machine learning (ML) model to determine one or more topics contained in the topic model content;
generating a heatmap based on the user data;
building a content relevancy model (CRM) based on the ML model and the heatmap;
determining an action state for the document data using the CRM, wherein the action state is based on a logistic regression value probability threshold range from stay as-is, promote and reshare, update and refresh, and retire at least a portion of the document data, wherein the document data is published digital content; and
storing the CRM.

14. The computer program product of claim 13 , wherein the document data includes information relating to a document content, a document topic, a document domain or a document subject matter, wherein the document access data includes the information relating to when, by whom, how often or for what purpose a document is accessed.

15. The computer program product of claim 13 , wherein the topic model content includes analytics engine data and crowdsourced data.

16. The computer program product of claim 13 , wherein the ML model determines a plurality of topics contained in the document data and the document access data.

17. The computer program product of claim 13 , wherein the heatmap is generated based on a plurality of content read by the user, wherein the plurality of content read by a user is captured with a front facing camera.

Assignees

• IBM

Inventors

• Hewitt Trudy L
• Anders Kelley
• Atkin Steven Edward
• Dunne Jonathan D

Classifications

• G06N5/04 Primary

  Inference or reasoning models · CPC title

• G06F16/93

  Document management systems · CPC title

• G06N20/00

  Machine learning · CPC title

• G06F16/35 Primary

  Clustering; Classification · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title