Providing recommendations based on user intent and user-generated post-purchase content

Patent metadata

Field	Value
Publication number	US-2018218430-A1
Application number	US-201715421211-A
Country	US
Kind code	A1
Filing date	Jan 31, 2017
Priority date	Jan 31, 2017
Publication date	Aug 2, 2018
Grant date	—

Abstract

A method including sending to a first user an input form comprising an input element for an intent weight for each of a plurality of features. The plurality of features can represent purchasing criteria that are common to each item in a category of items. The method also can include receiving from the first user the intent weights for the plurality of features. Each of the intent weights can represent a level of importance of a different feature of the plurality of features to the first user. The method additionally can include selecting one or more first items from among a plurality of items in the category of items based at least in part on: (a) the intent weights for the plurality of features for the first user, and (b) sentiment data comprising a sentiment score for each feature for each of the plurality of items. The sentiment scores for the plurality of features for each of the plurality of items can be derived from user-generated post-purchase content about the plurality of items. The method further can include displaying the one or more first items to the first user in real-time after receiving the intent weights. Other embodiments of related systems and methods are disclosed.

First claim

What is claimed is:

1 . A system comprising:
one or more processors; and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:
sending to a first user an input form comprising an input element for an intent weight for each of a plurality of features, the plurality of features representing purchasing criteria that are common to each item in a category of items;
receiving from the first user the intent weights for the plurality of features, each of the intent weights representing a level of importance of a different feature of the plurality of features to the first user;
selecting one or more first items from among a plurality of items in the category of items based at least in part on: (a) the intent weights for the plurality of features for the first user, and (b) sentiment data comprising a sentiment score for each feature for each of the plurality of items, the sentiment scores for the plurality of features for each of the plurality of items being derived from user-generated post-purchase content about the plurality of items; and
displaying the one or more first items to the first user in real-time after receiving the intent weights.

2 . The system of claim 1 , wherein the computing instructions are further configured to perform:
updating a weighting vector for the first user based on the intent weights for the plurality of features received from the first user, the weighting vector tracking the intent weights corresponding to each feature of a plurality of features for the first user.

3 . The system of claim 2 , wherein selecting the one or more first items comprises:
generating, for each item of the plurality of items, an item boosting signal for the first user based on a dot product of the weighting vector and a score vector representing the sentiment scores for the plurality of features for the item.

4 . The system of claim 3 , wherein selecting the one or more first items further comprises:
generating updated ranking scores for each item in the plurality of items based on the item boosting signal for the item for the first user.

5 . The system of claim 4 , wherein:
the one or more first items are selected based on the updated ranking scores for each item in the plurality of items.

6 . The system of claim 1 , wherein the computing instructions are further configured to perform:
before selecting the one or more first items, applying de-biasing rules to normalize the sentiment scores for the features for the plurality of items.

7 . The system of claim 1 , wherein:
each of the input elements in the input form comprise a slider.

8 . The system of claim 1 , wherein the computing instructions are further configured to perform:
receiving from the first user an update to the intent weights for the plurality of features.

9 . The system of claim 8 , wherein the computing instructions are further configured to perform:
selecting one or more second items from among a plurality of items based at least in part on: (a) the update to the intent weights for the plurality of features for the first user, and (b) the sentiment data.

10 . The system of claim 9 , wherein the computing instructions are further configured to perform:
displaying the one or more second items to the first user in real-time after receiving the update to the intent weights.

11 . A method being implemented via execution of computing instructions configured to run at one or more processors and configured to be stored at non-transitory computer-readable media, the method comprising:
sending to a first user an input form comprising an input element for an intent weight for each of a plurality of features, the plurality of features representing purchasing criteria that are common to each item in a category of items; receiving from the first user the intent weights for the plurality of features, each of the intent weights representing a level of importance of a different feature of the plurality of features to the first user; selecting one or more first items from among a plurality of items in the category of items based at least in part on: (a) the intent weights for the plurality of features for the first user, and (b) sentiment data comprising a sentiment score for each feature for each of the plurality of items, the sentiment scores for the plurality of features for each of the plurality of items being derived from user-generated post-purchase content about the plurality of items; and displaying the one or more first items to the first user in real-time after receiving the intent weights.

12 . The method of claim 11 , further comprising:
updating a weighting vector for the first user based on the intent weights for the plurality of features received from the first user, the weighting vector tracking the intent weights corresponding to each feature of a plurality of features for the first user.

13 . The method of claim 12 , wherein selecting the one or more first items comprises:
generating, for each item of the plurality of items, an item boosting signal for the first user based on a dot product of the weighting vector and a score vector representing the sentiment scores for the plurality of features for the item.

14 . The method of claim 13 , wherein selecting the one or more first items further comprises:
generating updated ranking scores for each item in the plurality of items based on the item boosting signal for the item for the first user.

15 . The method of claim 14 , wherein:
the one or more first items are selected based on the updated ranking scores for each item in the plurality of items.

16 . The method of claim 11 , further comprising:
before selecting the one or more first items, applying de-biasing rules to normalize the sentiment scores for the features for the plurality of items.

17 . The method of claim 11 , wherein:
each of the input elements in the input form comprise a slider.

18 . The method of claim 11 , further comprising:
receiving from the first user an update to the intent weights for the plurality of features.

19 . The method of claim 18 , further comprising:
selecting one or more second items from among a plurality of items based at least in part on: (a) the update to the intent weights for the plurality of features for the first user, and (b) the sentiment data.

20 . The method of claim 19 , further comprising:
displaying the one or more second items to the first user in real-time after receiving the update to the intent weights.

Assignees

• Wal Mart Stores Inc

Inventors

• Prendki Jennifer Laetitia

Classifications

• G06Q30/0623

  by investigating goods or services · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06Q30/0641

  utilising user interfaces specially adapted for shopping · CPC title