Automated content curation and communication

Patent metadata

Field	Value
Publication number	US-11895068-B2
Application number	US-202117372981-A
Country	US
Kind code	B2
Filing date	Jul 12, 2021
Priority date	Jun 30, 2016
Publication date	Feb 6, 2024
Grant date	Feb 6, 2024

Abstract

Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system receives a plurality of content communications from a plurality of client devices, each content communication comprising an associated piece of content and a corresponding metadata. Each content communication is processed to determine associated context values for each piece of content, each associated context value comprising at least one content value generated by machine vision processing of the associated piece of content. A first content collection is automatically generated based on context values, and a set of user accounts are associated with the collection. An identifier associated with the first content collection is published to user devices associated with user accounts. In various additional embodiments, different content values, image processing operations, and content selection operations are used to curate content collections.

First claim

What is claimed is:

1. A method comprising:
receiving, at a server system, a plurality of content communications from a plurality of client devices, each content communication comprising an associated piece of content and a corresponding metadata;
processing, by the server system, each content communication of the plurality of content communications to determine associated context values for each piece of content, the associated context values comprising at least one content value generated by machine vision processing of the associated piece of content, the associated context values further comprising an audio content value selected based on an analysis of audio data from the associated piece of content and an audio quality value determined based at least in part on an analysis to determine an audio noise level for the associated piece of content;
automatically generating at least a first content collection, wherein the first content collection comprises a first plurality of pieces of content from the plurality of content communications, and wherein the first plurality of pieces of content for the first content collection are selected based on the associated context values for each piece of content of the first plurality of pieces of content;
identifying one or more user segments associated with the first content collection; and
publishing an identifier associated with the first content collection to user devices associated with user accounts of the one or more user segments.

2. The method of claim 1 , further comprising:
receiving, at the server system, a content message from a first content source of the plurality of client devices, the content message comprising a first piece of content of the first plurality of pieces of content;
analyzing, by the server system, the content message to determine a set of context values for the first piece of content, the set of context values comprising one or more quality scores and one or more content values associated with the content message, wherein the first piece of content is selected for the first content collection based on at least a first content value of the set of content values;
storing the content message in a database of the server system along with the one or more quality scores and the one or more context values;
analyzing, by the server system, the content message with a plurality of content collections of the database to identify a match between at least one of the one or more context values and a topic associated with at least the first content collection of the plurality of content collections; and
automatically adding, by the server system, the first piece of content to the first content collection based at least in part on the match.

3. The method of claim 2 , further comprising:
receiving, at the server system, one or more content messages from each content source of the plurality of content sources, each content message comprising media content; and
analyzing, by the server system, each of the one or more content messages from each content source to determine corresponding one or more quality scores and one or more content values for each content message.

4. The method of claim 3 , further comprising:
storing the one or more content messages from each content source in the database of the server system along with the one or more quality scores and the one or more content values;
analyzing, by the server system, the database to identify one or more content values shared by a first set of content messages in the database;
automatically generating the first content collection based on identifying the one or more content values shared by the first set of content messages; and
automatically transmitting, by the server system, a notification associated with the first content collection in response to generation of the first content collection.

5. The method of claim 4 , wherein analyzing, by the server system, each of the one or more content messages, comprises:
processing each content messages of the one or more content message to identify one or more objects in the content message;
associating one or more keywords with each content message based on the one or more objects in the content message; and
storing each content message in the database with the one or more keywords.

6. The method of claim 5 , wherein the one or more content values comprise the one or more keywords, and
wherein the match between the at least one of the one or more content values and the topic associated with at least the first content collection of the one or more content collections is based on an association between at least a portion of the one or more keywords and the topic.

7. The method of claim 6 , wherein the context values further comprise a time, a location, a user account associated with the content message.

8. The method of claim 2 , further comprising:
processing image content of a content message, received from at least one of the plurality of client devices, to determine an interestingness value for the image content using a predefined set of metrics, the interestingness value corresponding to predicted user interest in the content message,
wherein the interestingness value is generated using a neural network having been trained with set of content messages identified as interesting within the server system; and
deleting the content message from the database based on a deletion trigger associated with the content message,
wherein the interestingness value is further generated based on rating inputs received at a curation tool integrated with the server system to provide operator selected training sets for the neural network, and
wherein the content message as received at the server system is associated with the deletion trigger.

9. The method of claim 8 , wherein the interestingness value is further generated based on feedback training data comprising feedback messages from users rating selected content messages of the training set of content messages based on previous content collections communicated to the users.

10. The method of claim 1 , further comprising:
generating a first visibility area for the first content collection based on associated content generation locations for the first plurality of pieces of content,
wherein publishing the identifier associated with the first content collection to the user devices associated with the user accounts of the one or more user segments comprises communicating the identifier to client devices within the first visibility area.

11. The method of claim 1 , wherein selection of the first plurality of pieces of content are based on context values for a local content geolocation area, a content time period, one or more content quality metrics, and one or more content categories.

12. A system comprising:
a processor; and
a memory storing instructions that, when executed by the processor, configure the processor to perform operations comprising:
receiving a plurality of content communications from a plurality of client devices, each content communication comprising an associated piece of content and a corresponding metadata;
processing each content communication of the plurality of content communications to determine associated context values for each piece of content, the associated context values comprising at least one content value generated by machine vision processing of the associated piece of content, the associated context values further comprising an audio content value selected based on an analysis of audio data from the associated piece of content and an audio quality value determined based at least in part on an analysis to determine an aud

Assignees

• Snap Inc

Inventors

• Yang Jianchao
• Zhu Yuke
• Xu Ning
• Tang Kevin Dechau
• Li Jia

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• H04L51/10 Primary

  Multimedia information · CPC title