Product recommendations based on analysis of social experiences

• US 9,697,537 B2
• Filed: 09/19/2016
• Issued: 07/04/2017
• Est. Priority Date: 05/29/2015
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Hamilton, II, Rick A., Balasubramanian, Swaminathan, Boss, Gregory J., Bell, Mark
• Primary Examiner(s): CHEN, ALAN S
• Application Number:
  US15/268,821
• Publication Number:
  US 20160379295A1
• Time in Patent Office: 288 Days
• Field of Search: None
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0261 based on user location
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method for recommending products. The method may include receiving an identification element associated with an image or a visual code captured by a user. The method may include identifying a first item associated with the identification element, whereby the first item is a product or a service. The method may include identifying at least one of a tag and a keyword associated with the first item. The method may include identifying social media interactions within a social media network that reference at least one of the first item, the tag, and the keyword, whereby the social media network is associated with the user. The method may further include identifying a second item referenced in the social media interactions, whereby the second item is a product or a service. The method may also include determining a score for the second item based on an algorithm.

Claims

1. A computer system to make a recommendation to a user for at least one of a product or a service, wherein a social media feed associated with the user is utilized to make the recommendation, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising;

receiving, by a processor, an identification element associated with an image captured by a user, wherein the image is a photographic picture or a video, and wherein the received identification element is captured by the user using a smart device;

identifying a first item based on the received identification element, wherein the first item is at least one of one of a first product or a first service associated with the received identification element, and wherein a current location of the user is considered when identifying the first item; and

wherein the current location of the user is identified using a global positioning system on the smart device, and wherein the first product has a plurality of first product attributes; and

wherein the plurality of first product attributes include at least one of a first product name, a first product feature, and a first product brand; and

wherein the first service has a plurality of first service attributes; and

wherein the plurality of first service attributes include at least one of a first service name, a first service feature, and a first service provider, and wherein, identifying the first item is based on the received identification element further comprises;

determining the received identification element is an image;

analyzing the received identification element using image recognition technology;

identifying a plurality of shapes within the analyzed identification element;

applying a weight to each of the identified plurality of shapes; and

determining the first item based on a highest weighted shape within the identified plurality of shapes, wherein the weight assigned to the identified plurality of shapes is based on at least one of a proximity of each of the identified plurality of shapes to an image center, a shape area relative to an image area, and a total count of a plurality of duplicate shapes;

identifying at least one of a tag or a keyword associated with the first item, wherein the tag and the keyword include at least one of the first product name, the first product feature, the first product brand, the first service name, the first service feature, or the first service provider;

identifying a plurality of social media interactions on a social media feed within a social media network that references at least one of the identified first item, the identified tag, or the identified keyword, wherein the social media feed is associated with the user, and wherein the social media feed used to identify the plurality of social media interactions is preconfigured by the user; and

wherein the social media feed includes at least one of a plurality of user posted videos, a plurality of user posted images, and a plurality of user generated text;

identifying at least one second item referenced in at least one interaction within the plurality of social media interactions, wherein the at least one second item is a second product or a second service; and

determining a relevancy score for each at least one identified second item based on a normalized scoring algorithm, wherein the normalized scoring algorithm determines the relevancy score for each at least one identified second item based on a frequency each at least one identified second item appears in each of plurality of social media interactions.