Method for image product recommendation

Patent metadata

Field	Value
Publication number	US-2023360103-A1
Application number	US-202318221287-A
Country	US
Kind code	A1
Filing date	Jul 12, 2023
Priority date	Dec 31, 2015
Publication date	Nov 9, 2023
Grant date	—

Abstract

Embodiments of the present disclosure a method for determining product relevancy including extracting metadata from an image file of a digital image collection, the metadata being indicative of at least one feature of the image file. The method includes creating an input profile corresponding to the metadata extracted from the image files of the digital image collection. The method includes comparing the input profile to a product profile, the product profile having one or more rules corresponding to a consumer product, wherein the rules are indicative of the requirements of the product. The method includes determining a match score, the match score indicative of a relevancy of the product profile to the input profile such that a high relevancy correlates to a consumer product that is suited to the input profile and a low relevancy correlates to the consumer product that is not suited to the input profile.

First claim

1 . A method for creating a consumer photo product recommendation, comprising:
receiving, at an image processing unit, one or more digital image and/or video files from a user; extracting recorded and derived metadata from the digital image and/or video files to produce image profiles; utilizing user inputs to form at least a portion of the image profile; analyzing the user's social media, appointment calendars, or the like to determine upcoming events and/or cultural considerations; identifying elements and factors to be used in evaluating the digital images and/or video files to suggest products that would be pleasing and/or not offensive to different cultures; correlating product profiles to the recorded and derived metadata extracted from the digital image and/or video files, information from the user's social media accounts, cultural considerations, and user inputs using rules comprising Boolean statements; and using a weighing system to determine whether to add points or to subtract points to determine consumer products associated with the product profiles that are the most relevant to the digital image and/or video files.

2 . The method of claim 1 wherein the recorded metadata comprises time and date metadata and location metadata.

3 . The method of claim 2 wherein the time and data metadata and location metadata are used to derive event-based metadata.

4 . The method of claim 1 wherein the derived metadata comprises an analysis of pixels of the one or more digital images.

5 . The method of claim 4 wherein the pixel analysis generates face-based metadata or content-based metadata.

6 . The method of claim 1 further comprising:
normalizing the weighing system prior to correlating the product profiles.

7 . The method of claim 1 further comprising:
arranging the one or more digital images into one or more relational databases of the image profiles correlated to an input profile.

8 . The method of claim 1 wherein the weighing system determines that points are not added or subtracted when determining which product profiles are most relevant to the image files.

9 . The method of claim 1 further comprising:
determining a match score from the weighing system wherein the match score represents the relevance of the product profile to the digital image and/or video files.

10 . The method of claim 9 further comprising:
comparing the match score to a threshold match score to determine relevant product profiles when the match score is greater than the threshold match score.

11 . The method of claim 1 wherein the determination of whether to add points or to subtract points varies an amount of points to be added or subtracted based on an importance of the rule to the product profile.

12 . The method of claim 1 wherein the rules weigh features comprising content-based features, time-based features, face-based features, or event-based features.

13 . The method of claim 1 wherein the consumer products comprise a card, a coffee cup, a photo book, or a slide show.

14 . The method of claim 1 wherein the weighing system evaluates cultural considerations from the user inputs for determining product profiles.

15 . The method of claim 1 wherein the one or more digital image and/or video files are received from the social media being analyzed.

16 . The method of claim 1 wherein the rules including Boolean statements are evaluated sequentially for each of the product profiles.

17 . The method of claim 1 wherein certain metadata features are more strongly weighted than other metadata features.

18 . The method of claim 1 wherein user generated tags received from social media are used to determine event-based metadata.

19 . The method of claim 1 wherein an amount of one or more digital image and/or video files is used for determining product profiles.

20 . The method of claim 1 wherein the Boolean statements return values of TRUE or FALSE for each rule.

Assignees

• Kodak Alaris Inc

Inventors

• Louis Alexander
• Das Madirakshi

Classifications

• G06V2201/10

  Recognition assisted with metadata · CPC title

• G06V20/35

  Categorising the entire scene, e.g. birthday party or wedding scene · CPC title

• G06Q30/0631 Primary

  Recommending goods or services · CPC title

• G06Q30/0627

  by specifying product or service characteristics, e.g. product dimensions · CPC title

• G06F16/583

  using metadata automatically derived from the content · CPC title