Associative relationship based recommendations

Patent metadata

Field	Value
Publication number	US-9569419-B1
Application number	US-201313950072-A
Country	US
Kind code	B1
Filing date	Jul 24, 2013
Priority date	Jul 24, 2013
Publication date	Feb 14, 2017
Grant date	Feb 14, 2017

Abstract

The systems and/or processes described herein may establish a controlled and limited vocabulary that may serve as explicit associative relationships. The explicit associative relationships may define the nature of relationships between items and/or categories of items. In response to determining that a user has interacted with or selected an item via a website, an application, etc., associated with a service provider, explicit associative relationships associated with the selected item may be parsed in order to identify additional items related to the selected item. The additional related items may then be dynamically recommended to the user via the website, the application, etc., associated with the service provider.

First claim

What is claimed is:

1. A system comprising:
one or more processors;
memory;
a classification module maintained in the memory and executable by the one or more processors to maintain a taxonomy for a catalog of products;
an explicit associative relationships module maintained in the memory and executable by the one or more processors to determine a plurality of explicit associative relationships, wherein the plurality of explicit associative relationships include words or phrases that define a plurality of different types of relationships between products included in the catalog of products, the plurality of different types of relationships including at least one of:
an optional accessory relationship that indicates that a first product is both suggested for use with a second product and not necessary for to using the second product,
a necessary accessory relationship that indicates that the first product is necessary for using the second product, or
a consumable accessory relationship that indicates that the first product is consumed during use of the first product in conjunction with the second product;

a relationships assignment module maintained in the memory and executable by the one or more processors to assign the plurality of explicit associative relationships to one or more pairings of the products;
a relationships parsing module maintained in the memory and executable by the one or more processors to:
determine that a user has selected the second product; and
parse the explicit associative relationships assigned to the second product to identify that the first product is related to the second product; and
an item recommendation module maintained in the memory and executable by the one or more processors to recommend the first product to the user and to explain a nature of at least one of the optional accessory relationship, the necessary accessory relationship, or the consumable accessory relationship assigned to the second product with respect to the first product.

2. The system as recited in claim 1 , wherein at least some of the plurality of explicit associative relationships indicate a type of the first product and an importance of the first product to using the second product.

3. The system as recited in claim 2 , wherein the importance of the first product to using the second product corresponds to an extent to which the first product is recommended to the user.

4. The system as recited in claim 1 , wherein the relationships parsing module is further executable to determine that the user has navigated to, browsed to, searched for, viewed, clicked on, or purchased the second product or a category of products associated with the second product.

5. The system as recited in claim 1 , wherein one or more related products are presented to the user in different categories based at least partly on the explicit associative relationships between the second product and the one or more related products.

6. A method comprising:
under control of one or more processors:
determining a plurality of explicit associative relationships that include words or phrases that define a plurality of different types of relationships between at least one of (i) items of a catalog of items, or al categories of the items, wherein the plurality of explicit associative relationships are different than a plurality of hierarchical relationships between at least one of the items or the categories of the items, and wherein the plurality of different types of relationships include at least one of:
an optional accessory relationship that indicates that at least one of a first item or a first category of items is both suggested for use with a second item and not necessary for using the second item,
a necessary accessory relationship that indicates that at least one of the first item or the first category of items is necessary for using the second item, or
a consumable accessory relationship that indicates that at least one of the first item or the first category of items is consumed during use in conjunction with the second item; and

assigning the plurality of explicit associative relationships to at least one of the items or the categories of items, the plurality of explicit associative relationships being utilized to recommend, to one or more users, at least one of the first item or the first category of items based on the second item having been selected by a user of the one or more users;
parsing the plurality of explicit associative relationships assigned to the second item to identify that at least one of the first item or the first category of items is related to the second item; and
transmitting, to the user, an explanation of a nature of at least one of the optional accessory relationship, the necessary accessory relationship, or the consumable accessory relationship assigned to the first item or the first category of items with respect to the second item.

7. The method as recited in claim 6 , further comprising:
determining data that corresponds to at least one of transactional data, merchant input, data from a subject matter expert, keyword search data, or category name data; and
assigning the plurality of explicit associative relationships based at least partly on the data.

8. The method as recited in claim 6 , further comprising:
determining which of the items or the categories of items are eligible to be assigned an explicit associative relationship of the plurality of explicit associative relationships; and
assigning the explicit associative relationship between the items or the categories of items that are determined to be eligible.

9. The method as recited in claim 6 , wherein the plurality of explicit associative relationships are determined by one or more algorithms utilizing an automated or partially automated process.

10. The method as recited in claim 6 , further comprising:
determining that the user has selected the second item via a site or an application associated with a service provider;
parsing the explicit associative relationships between the second item and the items to determine that the first item or the first category of items are related to the second item; and
dynamically recommending at least one of the first item or the first category of items to the user via the site or the application.

11. The method as recited in claim 6 , further comprising:
determining that the user has selected a particular category of items of the categories of items via a site or an application associated with a service provider;
parsing the explicit associative relationships between the particular category of items and the categories of items to determine one or more other categories of items that are related to the particular category of items; and
dynamically recommending at least one of the one or more other categories of items to the user via the site or the application.

12. The method as recited in claim 6 , wherein at least one of the first item or the first category of items are recommended to the one or more users via a user interface, a widget, one or more windows, one or more tabs, or one or more pages provided by a site or application associated with a service provider.

13. One or more non-transitory computer-readable media having computer executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
determining that a user has interacted with a first item of a catalog of items;
parsing explicit associative relationships between the first item and at least one type of related items from the catalog of items, the explicit associative relationships

Assignees

• Amazon Tech Inc

Inventors

• Rice Ronald Allen

Classifications

• G06F17/2705 Primary

  Physics · mapped topic

• G06Q30/0603

  Catalogue creation or management · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title