Presentation of product recommendations based on social informatics

• US 9,230,278 B2
• Filed: 03/07/2014
• Issued: 01/05/2016
• Est. Priority Date: 10/03/2013
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cook, Kelly L., Do, Lydia M., Min, Eileen, Woods, Eric
• Primary Examiner(s): Allen, William
• Assistant Examiner(s): O'SULLIVAN, KATHERINE L
• Application Number:
  US14/200,363
• Publication Number:
  US 20150100454A1
• Time in Patent Office: 669 Days
• Field of Search: 705 261- 272
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/0619 Neutral agent
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method, system, and/or computer program product presents product recommendations based on input derived from a user'"'"'s social network. A description of a product selected for purchase by a user is received. A social networking site is searched for information relevant to a characterization the product. The relevant information is characterized according to a social relationship between the user and an other member of the social networking site, a product family of the product, and a product expertise of the other member about the product. Characterized information about the product is then presented to the user.

Claims

1. A method for presenting product recommendations and purchasing products, the method comprising:

defining, by one or more processors, a circle of friends, wherein the circle of friends is defined for a particular purpose of recommending a particular type of product;

further defining, by one or more processors, the circle of friends based on a rich site summary (RSS) feed, wherein members of the circle of friends are all subscribers to the RSS feed;

blocking, by one or more processors, access to a purchasing history of the members of the circle of friends, wherein the members of the circle of friends are prevented from accessing a database of historical purchases made by other members of the circle of friends, and wherein computing logic uses the past purchasing history of the members of the circle of friends when defining the circle of friends to be used for recommending the particular type of product;

pulling, by one or more processors, content from a friends database describing the circle of friends to build a product recommendation dataset;

categorizing, by one or more processors, the content according to types of products;

visually representing to a user, by one or more processors and on a first graphical user interface, each product from the types of products in a product circle;

weighting, by one or more processors, each category of the types of products based on information in the friends database that describes which friend from the circle of friends recommended said each product, how recently said each product was purchased, a strength of a social connection of a person who recommends said each product to the user, and an expertise of the person who recommends said each product to the user;

receiving, by one or more processors, a user selection on the first graphical user interface of a product from the product recommendation dataset, wherein a representation of the product is presented on the first graphical user interface, wherein the user selection is performed by the user dragging an image of the product into a selection box on the first graphical user interface, and wherein said dragging causes a detailed description of the product to be displayed on the first graphical user interface;

correlating, by one or more processors, metatags associated with the image of the product with a category of the product from the product recommendation dataset;

correlating, by one or more processors, the category of the product with a database containing entries of friend descriptors, wherein the friend descriptors describe persons having experience in purchasing products from the category of the product;

receiving, by one or more processors, an activation of the selection box, wherein activating the selection box depicts and associates each product from the product recommendation dataset with one or more members of the circle of friends on a second graphical user interface;

receiving, by one or more processors, a description of the product selected for purchase by the user;

searching, by one or more processors, a social networking site for information relevant to a characterization of the product;

characterizing, by one or more processors, the information according to a social relationship between the user and another member of the social networking site, a product family of the product, and a product expertise of the other member about the product;

presenting, by one or more processors and on the second graphical user interface, information about each member of the circle of friends according to which product said each member recommends, wherein said information is depicted on the second graphical user interface with a visual link between the image of the product and each member of the circle of friends who recommends a particular product;

presenting, by one or more processors, the characterized information about the product to the user on the second graphical user interface; and

receiving, by one or more processors, a user selection action from the user from the second graphical user interface, wherein the user selection action causes the product to be purchased by;

automatically directing the user to an online retail service;

adding the product to an on-line shopping cart; and

automatically selecting a purchase option for the user to purchase the product.

2. The method of claim 1, wherein the product is at least one of a merchandise and a service.

3. The method of claim 1, wherein the presenting, by one or more processors, of the characterized information about the product is on a social graph.

4. The method of claim 1, wherein the product is from a group of multiple products in a same category, and wherein the method further comprises:

weighting, by one or more processors, each product recommendation for each of the multiple products to generate weighted product recommendations; and

aggregating, by one or more processors, the weighted product recommendations for each of the multiple products to generate an aggregated weighted recommendation for each of the multiple products.

5. The method of claim 4, wherein presenting characterized information about the product to the user further comprises:

identifying, by one or more processors, a highest weighted product that has a highest aggregated weighted recommendation relative to other products in the same category; and

presenting, by one or more processors the highest weighted product and the highest weighted product recommendation to the user.