Techniques to leverage machine learning for search engine optimization

Patent metadata

Field	Value
Publication number	US-10489474-B1
Application number	US-201916400004-A
Country	US
Kind code	B1
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	Nov 26, 2019
Grant date	Nov 26, 2019

Abstract

Techniques to leverage machine learning for search engine optimization (SEO). Some techniques are applicable to turnkey e-commerce solutions operating on the Internet as an online platform. These techniques use machine learning to gain insights into patterns/relationships between search terms and items for sale on the online platform. Depending on a relevancy or an accuracy of a search term to a particular item for sale, the online platform inserts the search term into the online platform such that a public search engine crawler increases a search engine result position for the online platform. Other embodiments are described and claimed.

First claim

The invention claimed is:

1. An apparatus, comprising:
a processing circuit; and
logic stored in computer memory and executed on the processing circuit, the logic operative to cause the processing circuit to:
store datasets of platform search data, each dataset comprises a word or word combination corresponding to a natural language search of an online platform and an item selected in association with the natural language search;
build a machine learning model based upon a feature set comprising mapping information between the word or word combination and the selected item;
identify, for a particular item associated with a particular online platform, a set of descriptive words amongst the datasets of the platform search data based upon the machine learning model;
update attribute data in a web document of the particular online platform with the set of descriptive words, wherein the attribute data corresponds to the particular item and the web document comprises a selectable option for the particular item;
process search engine results, for a public search engine search, comprising the set of descriptive words to determine whether there is a change in a ranked position for the particular online platform in the search engine results based on the updated attribute data in the web document; and
update other attribute data of other items in the web document with the set of descriptive words in response to the determined change in the search engine results.

2. The apparatus of claim 1 , comprising logic operative to cause the processing circuit to update the attribute data specifying content, metadata, or both the content and the metadata for the web document.

3. The apparatus of claim 1 , comprising logic operative to cause the processing circuit to update an alternate text (ALT) attribute or a TITLE attribute of an image with the set of descriptive words or to update keywords for a link to the web document.

4. The apparatus of claim 1 , comprising logic operative to cause the processing circuit to identify another set of descriptive words to update the web document of the particular online platform.

5. The apparatus of claim 1 , comprising logic operative to cause the processing circuit to determine that the set of descriptive words comprises an undervalued advertisement for the public search engine.

6. The apparatus of claim 1 , comprising logic operative to cause the processing circuit to increase or decrease a frequency of the set of descriptive words in the particular online platform.

7. The apparatus of claim 1 , comprising logic operative to cause the processing circuit to identify an alternative word phrase to use instead of the set of descriptive words.

8. A computer-implemented method executed on a processing circuit, the computer-implemented method comprising:
storing datasets of platform search data, each dataset comprises a set of words corresponding to a natural language search of an online platform, and an item selected in association with the natural language search;
building a machine learning model based upon a feature set comprising mapping information between the set of words and the selected item;
training the machine learning model to identify a set of descriptive words amongst the datasets of the platform search data for a particular item associated with a particular online platform;
updating attribute data in a web document of the particular online platform with the set of descriptive words, wherein the attribute data corresponds to the particular item and the web document comprises a selectable option for the particular item; and
processing search engine results for a public search engine search comprising the set of descriptive words to determine whether there is a change in a ranked position for the particular online platform in the search engine results based on the updated attribute data in the web document; and
updating other attribute data of other items in the web document with the set of descriptive words in response to the determined change in the search engine results.

9. The computer-implemented method of claim 8 , comprising updating an alternate text (ALT) attribute or a TITLE attribute of an image with the set of descriptive words or updating keywords for a link to the web document.

10. The computer-implemented method of claim 8 , comprising identifying another set of descriptive words to update the web document of the particular online platform.

11. The computer-implemented method of claim 8 , comprising determining that the set of descriptive words comprises an undervalued advertisement for the public search engine.

12. The computer-implemented method of claim 8 , comprising increasing or decreasing a frequency of the set of descriptive words in the particular online platform.

13. The computer-implemented method of claim 8 , comprising replacing the set of descriptive words in textual data with another set of descriptive words.

14. The computer-implemented method of claim 8 , comprising identifying an alternative word phrase to use instead of the set of descriptive words.

15. At least one non-transitory computer-readable storage medium comprising instructions that, when executed, cause a system to:
store datasets of platform search data, each dataset comprises a set of words corresponding to a natural language search of an online platform, and an item selected in association with the natural language search;
build a machine learning model based upon a feature set comprising mapping information between the set of words and the selected item;
train the machine learning model to identify a set of descriptive words amongst the datasets of the platform search data for a particular item associated with a particular online platform;
update attribute data in a web document of the particular online platform with the set of descriptive words, wherein the attribute data corresponds to the particular item and the web document comprises a selectable option for the particular item;
process search engine results for a public search engine search directed to the set of descriptive words to determine whether there is a change in an index for the particular online platform based on the updated attribute data in the web document; and
update other attribute data of other items in the web document with the set of descriptive words in response to the determined change in the search engine results.

16. The computer-readable storage medium of claim 15 , comprising instructions that when executed cause the system to update an alternate text (ALT) attribute or a TITLE attribute of an image with the set of descriptive words.

17. The computer-readable storage medium of claim 15 , comprising instructions that when executed cause the system to update keywords for a link to the web document.

18. The computer-readable storage medium of claim 15 , comprising instructions that when executed cause the system to, in response to the change in the index, identify another set of descriptive words to update the web document of the particular online platform.

19. The computer-readable storage medium of claim 15 , comprising instructions that when executed cause the system to determine that the set of descriptive words comprises an undervalued advertisement for the public search engine.

20. The computer-readable storage medium of claim 15 , comprising instructions that when executed cause the system to increase or decrease a frequency of the set of descriptive words in textual data of the particular online p

Assignees

• Capital One Services Llc

Inventors

• Tang Qiaochu
• Wylie Stephen
• Hoover Jason
• Ghamsari Avid
• Price Micah
• Dagley Geoffrey

Classifications

• G06N3/006

  based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO] · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N7/01

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

• G06F16/953 Primary

  Querying, e.g. by the use of web search engines · CPC title

• G06F16/9538 Primary

  Presentation of query results · CPC title