Content classification method

Patent metadata

Field	Value
Publication number	US-12387146-B2
Application number	US-201917292783-A
Country	US
Kind code	B2
Filing date	Nov 6, 2019
Priority date	Nov 15, 2018
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

A novel content classification method is provided. A content classification method using machine learning for a learning model and a classifier fabrication method are provided. In Step 1, a data set containing a plurality of contents is acquired. Learning labels are attached to m contents, and the learning labels are not attached to the remaining contents. In Step 2, a first learning model is created by machine learning using the m contents. In Step 3, judgment labels are attached to the plurality of contents using the first learning model and are displayed on a GUI. In Step 4, new learning labels are attached to k contents in the plurality of contents. In Step 5, a second learning model is created by the machine learning using the k contents. In Step 6, judgment labels are attached to the plurality of contents using the second learning model and are displayed on the GUI.

First claim

The invention claimed is:

1. A content classification method of a computer device, comprising the steps of:
acquiring a data set comprising a plurality of contents including m contents to which a learning label is attached and n contents to which the learning label is not attached;
creating a first learning model by machine learning using the m contents;
attaching a judgment label to the plurality of contents using the first learning model and displaying the judgment label in a graphical user interface;
attaching a learning label to q contents in the n contents;
creating a second learning model by the machine learning using the (q+m) contents to which the learning label is attached;
attaching a judgment label to the plurality of contents using the second learning model and displaying the judgment label in the graphical user interface;
calculating a first score for estimating the judgment label;
promoting label attachment when the first score of a record is greater than or equal to 0.5 and less than 0.65; and
changing, based at least in part on the first score, a display order of the judgement label in the graphical user interface,
wherein m, n, and q each represent a natural number.

2. The content classification method according to claim 1 , wherein the plurality of contents include text.

3. The content classification method according to claim 1 , further comprising a step of clustering using unsupervised learning on the data set including the plurality of contents.

4. The content classification method according to claim 1 , wherein the plurality of contents include text in a patent document.

5. The content classification method according to claim 1 , wherein the judgment label and the learning label are two classes.

6. A content classification method of a computer device, comprising the steps of:
acquiring a data set comprising a plurality of contents including m contents to which a learning label is attached and n contents to which the learning label is not attached;
creating a first learning model by machine learning using the m contents;
attaching a judgment label to the plurality of contents using the first learning model and displaying the judgment label in a graphical user interface;
attaching a learning label to k contents in the plurality of contents;
creating a second learning model by the machine learning using the k contents to which the learning label is attached;
attaching a judgment label to the plurality of contents using the second learning model and displaying the judgment label in the graphical user interface;
calculating a first score for estimating the judgment label;
promoting label attachment when the first score of a record is greater than or equal to 0.5 and less than 0.65; and
changing, based at least in part on the first score, a display order of the judgement label in the graphical user interface,
wherein m and k each represent a natural number.

7. The content classification method according to claim 6 , wherein the plurality of contents include text.

8. The content classification method according to claim 6 , further comprising a step of clustering using unsupervised learning on the data set including the plurality of contents.

9. The content classification method according to claim 6 , wherein the plurality of contents include text in a patent document.

10. The content classification method according to claim 6 , wherein the judgment label and the learning label are two classes.

11. A content classification method of a computer device, comprising the steps of:
acquiring a data set comprising a plurality of contents including m contents to which a learning label is attached and n contents to which the learning label is not attached;
calculating a first score for estimating a judgment label of the plurality of contents using the m contents;
displaying a list of labels determined based on the first score and attached to the plurality of contents in a graphical user interface;
attaching a learning label to k contents in the plurality of contents included in the list;
creating a learning model by machine learning using the k contents to which the learning label is attached;
calculating a second score for estimating the judgment label of the plurality of contents;
displaying the list of the judgment labels determined based on the second score and attached to the plurality of contents in the graphical user interface;
promoting label attachment when the first score of a record is greater than or equal to 0.5 and less than 0.65; and
changing, based at least in part on the first score, a display order of the judgement labels in the graphical user interface,
wherein m and k each represent a natural number.

12. The content classification method according to claim 11 , further comprising a step of specifying a specific numerical range in the first score and attaching a learning label to the corresponding content.

13. The content classification method according to claim 11 , wherein the plurality of contents include text.

14. The content classification method according to claim 11 , further comprising a step of clustering using unsupervised learning on the data set including the plurality of contents.

15. The content classification method according to claim 11 , wherein the plurality of contents include text in a patent document.

16. The content classification method according to claim 11 , wherein the judgment label and the learning label are two classes.

Assignees

• Semiconductor Energy Lab

Inventors

• Yamamoto Kunitaka
• Momo Junpei
• Higashi Kazuki
• Fukutome Takahiro

Classifications

• G06F16/9038

  Presentation of query results · CPC title

• G06F16/906

  Clustering; Classification · CPC title

• G06N20/20 Primary

  Ensemble learning · CPC title

• G06N20/00 Primary

  Machine learning · CPC title