COMPUTING SYSTEMS AND METHODS FOR IMPROVING CONTENT QUALITY FOR INTERNET WEBPAGES

• US 20190318371A1
• Filed: 06/14/2018
• Published: 10/17/2019
• Est. Priority Date: 04/13/2018
• Status: Active Application

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Inventors: Oruganti, Pavan Kumar, Bantay, Maria Kristian, Stuk, Archimedes
• Application Number:
  US16/009,074
• Publication Number:
  US 20190318371A1
• Time in Patent Office: Days
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: G06F 16/9577 Optimising the visualization of content, e.g. distillation of HTML documents
• CPC Class Codes: G06F 16/958 Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
• CPC Class Codes: G06Q 30/0203 Market surveys; Market polls
• CPC Class Codes: G06Q 30/0641 Shopping interfaces

Abstract

Computing systems and methods for assessing and improving content quality for internet webpages is provided.

Claims

1. A system for improving content quality for internet webpages, the system comprising:

a database storing;

a plurality of items, each item displayable on a webpage; and

a plurality of content attributes for each item;

a processor configured to;

retrieve, from the database, the plurality of items and the plurality of content attributes for the items;

score each content attribute according to a first set of rules;

select a modeling technique from two or more modeling techniques according to a second set of rules;

estimate an order potential for each item using the selected modeling technique;

prioritize the items based on the order potential for each item;

select a specified number of high scoring content attributes associated with a specified number of high priority items; and

compare each content attribute score of the specified number of high scoring content attributes against a benchmark score associated with a corresponding content attribute,

wherein when a content attribute score for an item is less than a benchmark score, transmit a recommendation to fix the content attribute for the item.

2. The system of claim 1, wherein the first set of rules comprises the processor further configured to score each content attribute based on a relevance of the content attribute to a market vehicle.

3. The system of claim 1, wherein the second set of rules comprises the processor further configured to:

retrieve a first specified percentage of items from the plurality of items and running the two or more modeling techniques on the specified percentage of items to train each model for predicting webpage traffic and webpage orders as a function of the items and the content attribute scores;

retrieve a second specified percentage of items from the plurality of items and testing the prediction of webpage traffic and webpage orders for each model against actual webpage traffic and webpage orders; and

select the modeling technique based on a lowest margin of error from the testing results.

4. The system of claim 1, wherein the plurality of items are within a department.

5. The system of claim 1, where the content attributes include at least one of a product description, one or more product images, one or more customer ratings, one or more customer reviews, a product comparison table to similar products, frequently asked questions and answers, an interactive tour of product, one or more product videos, and product specifications.

6. The system of claim 1, further comprising an importance engine configured to determine an importance of each content attribute by department based on an importance of the content attribute scores.

7. The system of claim 1, further comprising a content quality dashboard configured to display the recommendation to fix the content attribute for the item.

8. A method for improving content quality for internet webpages, the method comprising:

storing, in a database, a plurality of items, each item displayable on a webpage;

storing, in a database, a plurality of content attributes for each item;

retrieving, via a processor from the database, the plurality of items and the plurality of content attributes for the items;

scoring, via the processor, each content attribute according to a first set of rules;

selecting, via the processor, a modeling technique from two or more modeling techniques according to a second set of rules;

estimating, via the processor, an order potential for each item using the selected modeling technique;

prioritizing, via the processor, the items based on the order potential for each item;

selecting, via the processor, a specified number of high scoring content attributes associated with a specified number of high priority items; and

comparing, via the processor, each content attribute score of the specified number of high scoring content attributes against a benchmark score associated with a corresponding content attribute,

wherein when a content attribute score for an item is less than a benchmark score, transmitting, via the processor, a recommendation to fix the content attribute for the item.

9. The method of claim 8, wherein the first set of rules comprises scoring, via the processor, each content attribute based on a relevance of the content attribute to a market vehicle.

10. The method of claim 8, wherein the second set of rules comprises:

retrieving, via the processor, a first specified percentage of items from the plurality of items and running the two or more modeling techniques on the specified percentage of items to train each model for predicting webpage traffic and webpage orders as a function of the items and the content attribute scores;

retrieving, via the processor, a second specified percentage of items from the plurality of items and testing the prediction of webpage traffic and webpage orders for each model against actual webpage traffic and webpage orders; and

selecting, via the processor, the modeling technique based on a lowest margin of error from the testing results.

11. The method of claim 8, wherein the plurality of items are within a department.

12. The method of claim 8, where the content attributes include at least one of a product description, one or more product images, one or more customer ratings, one or more customer reviews, a product comparison table to similar products, frequently asked questions and answers, an interactive tour of product, one or more product videos, and product specifications.

13. The method of claim 8, further comprising determining, via an importance engine, an importance of each content attribute by department based on an importance of the content attribute scores.

14. The method of claim 8, further comprising displaying, via a content quality dashboard, the recommendation to fix the content attribute for the item.

15. A non-transitory computer-readable medium storing instructions for improving content quality for internet webpages, the instruction when executed by a processing device cause the processing device to:

retrieve, from a database storing a plurality of items and a plurality of content attributes for each item, the plurality of items and the plurality of content attributes for the items;

score each content attribute according to a first set of rules;

select a modeling technique from two or more modeling techniques according to a second set of rules;

estimate an order potential for each item using the selected modeling technique;

prioritize the items based on the order potential for each item;

select a specified number of high scoring content attributes associated with a specified number of high priority items; and

compare each content attribute score of the specified number of high scoring content attributes against a benchmark score associated with a corresponding content attribute,

wherein when a content attribute score for an item is less than a benchmark score, transmit a recommendation to fix the content attribute for the item.

16. The non-transitory computer-readable medium of claim 15, wherein the first set of rules comprises scoring, via the processor, each content attribute based on a relevance of the content attribute to a market vehicle.

17. The non-transitory computer-readable medium of claim 15, wherein the second set of rules comprises:

retrieving, via the processor, a first specified percentage of items from the plurality of items and running the two or more modeling techniques on the specified percentage of items to train each model for predicting webpage traffic and webpage orders as a function of the items and the content attribute scores;

retrieving, via the processor, a second specified percentage of items from the plurality of items and testing the prediction of webpage traffic and webpage orders for each model against actual webpage traffic and webpage orders; and

selecting, via the processor, the modeling technique based on a lowest margin of error from the testing results.

18. The non-transitory computer-readable medium of claim 15, wherein the plurality of items are within a department.

19. The non-transitory computer-readable medium of claim 15, where the content attributes include at least one of a product description, one or more product images, one or more customer ratings, one or more customer reviews, a product comparison table to similar products, frequently asked questions and answers, an interactive tour of product, one or more product videos, and product specifications.

20. The non-transitory computer-readable medium of claim 15, further comprising instructions that when executed by a processing device cause the processing device to determine, via an importance engine, an importance of each content attribute by department based on an importance of the content attribute scores.

21. The non-transitory computer-readable medium of claim 15, further comprising instructions that when executed by a processing device cause the processing device to display, via a content quality dashboard, the recommendation to fix the content attribute for the item.