Matching and ranking content items

Patent metadata

Field	Value
Publication number	US-11245966-B2
Application number	US-202017107592-A
Country	US
Kind code	B2
Filing date	Nov 30, 2020
Priority date	Apr 17, 2017
Publication date	Feb 8, 2022
Grant date	Feb 8, 2022

Abstract

The present disclosure is directed to a networking system that provides a user experience in which users of the networking system can interact with user-generated digital content items to select and receive information about one or more products. In particular, the systems and methods involve identifying products shown within user-generated digital content items and associating the user-generated digital content items with the identified products. In addition, where a user selects a product shown within a digital content item, the systems and methods involve selectively identifying other user-generated digital content items for the user based on a coefficient between the user and the other user-generated digital content items. Moreover, the systems and methods involve tracking user-interactions with respect to digital content items and generating and providing a creation insight including an identification of one or more products predicted to engage users of the networking system.

First claim

The invention claimed is:

1. A method comprising:
identifying a plurality of social networking posts comprising user-generated digital content items depicting products;
determining confidence scores for the plurality of social networking posts indicating likelihoods that the depicted products correspond to a social networking merchant;
based on determining confidence scores indicating a set of products corresponding to the social networking merchant, determining population engagement scores for the set of products indicating respective predictions of engagement by a user population with products within the set of products; and
providing, based on the population engagement scores and for display on a merchant device associated with the social networking merchant, an insight interface comprising a collection of user-generated digital content items depicting one or more products from the set of products.

2. The method of claim 1 , wherein determining the confidence scores indicating the set of products corresponding to the social networking merchant comprises:
comparing visual characteristics of products within the user-generated digital content items with visual characteristics of products within a catalog associated with the social networking merchant;
determining the confidence scores for the products based on comparing the visual characteristics; and
selecting products with confidence scores that satisfy a threshold confidence to include within the set of products corresponding to the social networking merchant.

3. The method of claim 1 , wherein determining the confidence scores indicating the set of products corresponding to the social networking merchant comprises:
comparing tags associated with products within the user-generated digital content items and tags associated with products within a catalog associated with the social networking merchant;
determining the confidence scores for the products based on comparing the tags; and
selecting products with confidence scores that satisfy a threshold confidence to include within the set of products corresponding to the social networking merchant.

4. The method of claim 1 , wherein determining the population engagement scores comprises:
identifying the user population by determining a demographic of social networking users that defines the user population; and
determining predictions of users within the user population engaging with respective products within the set of products.

5. The method of claim 1 , wherein determining the population engagement scores comprises:
determining a history of user interactions for the user population that indicates previous user interactions with respect to one or more products within the set of products; and
assigning higher population engagement scores for products with more previous user interactions than for products with fewer previous user interactions.

6. The method of claim 1 , wherein providing the insight interface comprises:
ranking the collection of user-generated content items according to respective population engagement scores; and
providing the collection of user-generated digital content items for display within the insight interface in order according to the ranking.

7. The method of claim 1 , wherein providing the insight interface comprises:
determining, based on the population engagement scores for the set of products, population engagement scores for different combinations of products within the set of products corresponding to the social networking merchant; and
identifying a combination of products to include within the insight interface based on the population engagement scores for the different combinations of products.

8. A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computing system to:
identify a plurality of social networking posts comprising user-generated digital content items depicting products;
determine confidence scores for the plurality of social networking posts indicating likelihoods that the depicted products correspond to a social networking merchant;
based on determining confidence scores indicating a set of products corresponding to the social networking merchant, determine population engagement scores for the set of products indicating respective predictions of engagement by a user population with products within the set of products; and
provide, based on the population engagement scores and for display on a merchant device associated with the social networking merchant, an insight interface comprising a collection of user-generated digital content items depicting one or more products from the set of products.

9. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing system to determine the confidence scores indicating the set of products corresponding to the social networking merchant by:
comparing visual characteristics of products within the user-generated digital content items with visual characteristics of products within a catalog associated with the social networking merchant;
determining the confidence scores for the products based on comparing the visual characteristics; and
selecting products with confidence scores that satisfy a threshold confidence to include within the set of products corresponding to the social networking merchant.

10. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing system to determine the confidence scores indicating the set of products corresponding to the social networking merchant by:
comparing tags associated with products within the user-generated digital content items and tags associated with products within a catalog associated with the social networking merchant;
determining the confidence scores for the products based on comparing the tags; and
selecting products with confidence scores that satisfy a threshold confidence to include within the set of products corresponding to the social networking merchant.

11. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing system to determine the population engagement scores by:
identifying the user population by determining a demographic of social networking users that defines the user population; and
determining predictions of users within the user population engaging with respective products within the set of products.

12. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing system to determine the population engagement scores by:
determining a history of user interactions for the user population that indicates previous user interactions with respect to one or more products within the set of products; and
assigning higher population engagement scores for products with more previous user interactions than for products with fewer previous user interactions.

13. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing system to provide the insight interface by:
ranking the collection of user-generated content items according to respective population engagement scores; and
providing the collection of user-generated digital content items for display within the in

Assignees

• Facebook Inc

Inventors

• Saxena Sanchan Sahai
• Markov Sergey
• Wang Fei
• Wu Yi-Wei
• Salvana Ed Ignatius Tanghal
• Schurman William Taube
• Ahres Youssef

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q30/0277

  Online advertisement · CPC title

• H04N21/4532

  involving end-user characteristics, e.g. viewer profile, preferences (monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18) · CPC title

• G06Q30/0241

  Advertisements · CPC title

• H04N21/47815 Primary

  Electronic shopping (payment schemes, payment architectures or payment protocols for electronic shopping systems G06Q20/12) · CPC title