IP Library › Granted Patent US 10,579,625

Granted Patent B2

US 10,579,625 · App. 15/266,941 · Granted Mar 3, 2020

Personalized review snippet generation and display

Inventors: Hyun Duk Cho (Mountain View, CA); Evren Korpeoglu (Sunnyvale, CA); Venkata Syam Prakash Rapaka (Cupertino, CA); Kannan Achan (Saratoga, CA)

Assignee: WALMART APOLLO, LLC

G06F16/24573 G06F16/24575 G06F16/287 G06Q30/0625

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 10,579,625
App. No.: 15/266,941
Granted: Mar 3, 2020
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of receiving a plurality of user reviews of a product, performing topic modeling of the plurality of user reviews of the product to find a plurality of snippets within the plurality of user reviews each relating to at least one user attribute category of a plurality of user attribute categories, and facilitating a display on a device of a first snippet of the plurality of snippets proximate the product.

Claims (357)

1. A system comprising:

one or more processing modules; and

one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of:

receiving a plurality of user reviews of a product;

performing topic modeling of the plurality of user reviews of the product to find a plurality of snippets within the plurality of user reviews, each snippet of the plurality of snippets relating to at least one user attribute category of a plurality of user attribute categories;

creating a score for each snippet of the plurality of snippets based on:

the topic modeling of the plurality of user reviews of the product; and

a probability of association between the at least one user attribute category and one or more seed words, the one or more seed words describing qualities of the product and having a weight describing an influence of the one or more seed words on the score for each snippet of the plurality of snippets; and

facilitating a display on a user device of a first snippet of the plurality of snippets proximate the product on the display of the user device, the first snippet having a highest score of the scores for the plurality of snippets.

2. The system of claim 1 , wherein the one or more non-transitory storage modules storing the computing instructions are further configured to run on the one or more processing modules and perform acts of:

determining a first user attribute category of the plurality of user attribute categories for a user of the user device; and

selecting the first snippet of the plurality of snippets, wherein:

the first snippet relates to the at least one user attribute category of the plurality of user attribute categories;

the at least one user attribute category of the plurality of user attribute categories corresponds to the first user attribute category determined for the user; and

the first snippet is personalized to the user.

3. The system of claim 2 , wherein determining the first user attribute category comprises determining the first user attribute category based upon a browsing history of the user.

4. The system of claim 2 , wherein determining the first user attribute category comprises determining the first user attribute category based upon a profile information of the user.

5. The system of claim 2 , wherein the one or more non-transitory storage modules storing the computing instructions are further configured to run on the one or more processing modules and perform an act of:

scoring each snippet of the plurality of snippets based upon a probability of association of each snippet of the plurality of snippets with each user attribute category of the plurality of user attribute categories.

6. The system of claim 2 , wherein:

receiving the plurality of user reviews of the product comprises receiving a first plurality of user reviews of a first product and a second plurality of user reviews of a second product;

performing the topic modeling of the plurality of user reviews of the product comprises:

performing the topic modeling of the first plurality of user reviews of the first product to find the first snippet within the first plurality of user reviews relating to the first user attribute category of the plurality of user attribute categories; and

performing topic modeling of the second plurality of user reviews of the second product to find a second snippet within the second plurality of user reviews relating to a second user attribute category of the plurality of user attribute categories, wherein the second user attribute category is different from the first user attribute category;

selecting the first snippet of the plurality of snippets comprises selecting the first snippet of the plurality of snippets relating to the first user attribute category that corresponds to the first user attribute category, as determined for the user;

facilitating the display on the user device of the first snippet of the plurality of snippets proximate the product comprises facilitating the display on the user device of the first snippet of the plurality of snippets proximate the first product on the user device; and

the one or more non-transitory storage modules storing the computing instructions are further configured to run on the one or more processing modules and perform acts of:

determining the second user attribute category of the plurality of user attribute categories for the user is different from the first user attribute category for the user;

selecting the second snippet of the plurality of snippets relating to the second user attribute category that corresponds to the second user attribute category determined for the user; and

facilitating the display on the user device of the second snippet of the plurality of snippets proximate the second product on the user device.

7. The system of claim 2 , wherein:

receiving the plurality of user reviews of the product comprises receiving a first plurality of user reviews of a first product and a second plurality of user reviews of a second product;

performing the topic modeling of the plurality of user reviews of the product comprises:

performing topic modeling of the second plurality of user reviews of the second product to find a second snippet within the second plurality of user reviews relating to the first user attribute category of the plurality of user attribute categories, wherein a second user attribute category is different from the first user attribute category;

the one or more non-transitory storage modules storing the computing instructions are further configured to run on the one or more processing modules and perform acts of:

selecting the second snippet of the plurality of snippets relating to the first user attribute category that corresponds to the first user attribute category determined for the user; and

facilitating the display on the user device of the second snippet of the plurality of snippets proximate the second product on the display of the user device.

8. The system of claim 2 , wherein a probability of the first snippet relating to the at least one user attribute category corresponding to the first user attribute category determined for the user is determined by an equation comprising:

⁡

(

)

∑

∈

⁢

⁡

(

)

⁡

(

)

where:

P is the probability of the first snippet relating to the at least one user attribute category;

RS is the first snippet;

U is the user;

a is the first user attribute category, as determined; and

A is the plurality of user attribute categories.

9. The system of claim 1 , wherein the plurality of user attribute categories comprises value-conscious, quality-conscious, brand-conscious, product popularity, gender, age, and location.

10. The system of claim 1 , wherein facilitating the display on the user device of the first snippet proximate the product comprises facilitating the display on the user device of the first snippet proximate the product displayed in a product carousel.

11. The system of claim 1 , wherein:

receiving the plurality of user reviews of the product comprises receiving a first plurality of user reviews of a first product and a second plurality of user reviews of a second product;

performing the topic modeling of the plurality of user reviews of the product comprises:

performing the topic modeling of the first plurality of user reviews of the first product to find the first snippet within the first plurality of user reviews relating to a first user attribute category of the plurality of user attribute categories; and

the one or more non-transitory storage modules storing the computing instructions are further configured to run on the one or more processing modules and perform acts of:

determining the first user attribute category of the plurality of user attribute categories for a user and the second user attribute category of the plurality of user attribute categories for the user different from the first user attribute category for the user based upon at least one of the user's browsing history and the user's profile information;

selecting the first snippet of the plurality of snippets relating to the first user attribute category of the plurality of user attribute categories that corresponds to the first user attribute category determined for the user, wherein the first snippet is personalized to the user;

selecting the second snippet of the plurality of snippets relating to the second user attribute category of the plurality of user attribute categories that corresponds to the second user attribute category determined for the user;

facilitating the display on the user device of the second snippet of the plurality of snippets relating to the second user attribute category determined for the user proximate the second product on the display of the user device; and

facilitating the display on the user device of the first snippet proximate the product comprises facilitating the display on the user device of the first snippet relating to the first user attribute category determined for the user proximate the first product on the display of the user device;

the plurality of user attribute categories comprises value-conscious, quality-conscious, brand-conscious, product popularity, gender, age, and location;

a probability of the first snippet relating to the first user attribute category corresponding to the determined first user attribute category for the user is determined by a first equation comprising:

⁡

(

)

∑

∈

⁢

⁡

(

)

⁡

(

)

where:

P 1 is the probability of the first snippet relating to the first user attribute category;

RS 1 is the first snippet;

U is the user;

a 1 is the determined first user attribute category for the user; and

A is the plurality of user attribute categories; and

a probability of the second snippet relating to the second user attribute category corresponding to the determined second user attribute category for the user is determined by a second equation comprising:

⁡

(

)

∑

∈

⁢

⁡

(

)

⁡

(

)

where:

P 2 is the probability of the second snippet relating to the second user attribute category;

RS 2 is the second snippet;

U is the user;

a 2 is the determined second user attribute category for the user; and

A is the plurality of user attribute categories.

12. A method, comprising:

receiving a plurality of user reviews of a product;

creating a score for each snippet of the plurality of snippets based on:

the topic modeling of the plurality of user reviews of the product; and

facilitating a display on a user device of a first snippet of the plurality of snippets proximate the product on the display device of the user device, the first snippet having a highest score of the scores for the plurality of snippets.

13. The method of claim 12 , further comprising:

determining a first user attribute category of the plurality of user attribute categories for a user of the user device; and

selecting the first snippet of the plurality of snippets, wherein:

the first snippet relates to the at least one user attribute category of the plurality of user attribute categories;

the at least one user attribute category of the plurality of user attribute categories corresponds to the first user attribute category determined for the user; and

the first snippet is personalized to the user.

14. The method of claim 13 , wherein determining the first user attribute category comprises determining the first user attribute category based upon a browsing history of the user.

15. The method of claim 13 , wherein determining the first user attribute category comprises determining the first user attribute category based upon a profile information of the user.

16. The method of claim 13 , further comprising scoring each snippet of the plurality of snippets based upon a probability of association of each snippet of the plurality of snippets with each user attribute category of the plurality of user attribute categories.

17. The method of claim 13 , wherein:

receiving the plurality of user reviews of the product comprises receiving a first plurality of user reviews of a first product and a second plurality of user reviews of a second product;

performing the topic modeling of the plurality of user reviews of the product comprises:

the method further comprises:

determining the second user attribute category of the plurality of user attribute categories for the user is different from the first user attribute category for the user;

selecting the second snippet of the plurality of snippets relating to the second user attribute category that corresponds to the second user attribute category determined for the user; and

facilitating the display on the user device of the second snippet of the plurality of snippets proximate the second product on the user device.

18. The method of claim 13 , wherein:

receiving the plurality of user reviews of the product comprises receiving a first plurality of user reviews of a first product and a second plurality of user reviews of a second product;

performing the topic modeling of the plurality of user reviews of the product comprises:

the method further comprises:

selecting the second snippet of the plurality of snippets relating to the first user attribute category that corresponds to the first user attribute category determined for the user; and

facilitating the display on the user device of the second snippet of the plurality of snippets proximate the second product on the display of the user device.

19. The method of claim 13 , wherein a probability of the first snippet relating to the at least one user attribute category corresponding to the first user attribute category determined for the user is determined by an equation comprising:

⁡

(

)

∑

∈

⁢

⁡

(

)

⁡

(

)

where:

P is the probability;

RS is the first snippet;

U is the user;

a is the first user attribute category, as determined; and

A is the plurality of user attribute categories.

20. The method of claim 13 , wherein the plurality of user attribute categories comprises value-conscious, quality-conscious, brand-conscious, product popularity, gender, age, and location.

21. The method of claim 12 , wherein facilitating the display on the user device of the first snippet proximate the product comprises facilitating the display on the user device of the first snippet proximate the product displayed in a product carousel.

22. The method of claim 12 , wherein:

receiving the plurality of user reviews of the product comprises receiving a first plurality of user reviews of a first product and a second plurality of user reviews of a second product;

performing the topic modeling of the plurality of user reviews of the product comprises:

the method further comprises:

determining first user attribute category of the plurality of user attribute categories for a user and second user attribute category of the plurality of user attribute categories for the user different from the first user attribute category for the user based upon at least one of the user's browsing history and the user's profile information;

the plurality of user attribute categories comprises value-conscious, quality-conscious, brand-conscious, product popularity, gender, age, and location;

⁡

(

)

∑

∈

⁢

⁡

(

)

⁡

(

)

where:

P 1 is the probability of the first snippet relating to the first user attribute category;

RS 1 is the first snippet;

U is the user;

a 1 is the determined first user attribute category for the user; and

A is the plurality of user attribute categories; and

⁡

(

)

∑

∈

⁢

⁡

(

)

⁡

(

)

where:

P 2 is the probability of the second snippet relating to the second user attribute category;

RS 2 is the second snippet;

U is the user;

a 2 is the determined second user attribute category for the user; and

A is the plurality of user attribute categories.

Assignments (2)

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 2, 2018

From: WAL-MART STORES, INC.

To: WALMART APOLLO, LLC

Reel/Frame 045817/0115 →

ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 16, 2016

From: CHO, HYUN DUK; KORPEOGLU, EVREN; RAPAKA, VENKATA SYAM PRAKASH; ACHAN, KANNAN

To: WAL-MART STORES, INC.

Reel/Frame 039769/0869 →

Continuity (1)

Related Publication 20180075110A1 · Mar 15, 2018