Systems and methods for sharing content

Abstract

Systems, methods, and non-transitory computer-readable media can provide an interface in which a content feed of a user is presented, the content feed including at least one first post that was authored by the user and that includes a first content item, wherein the interface is presented on a display screen of a computing device. A determination is made that the user has selected an option to update the first post to include one or more additional content items. A set of content items is provided for selection through the interface. The first post is updated to include at least one content item that was selected by the user.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 determining, by a computing system, a first post published in a feed;   determining, by the computing system, a second post to be merged with the first post into a single post based on similarity of subject matter associated with the first post and the second post; and   causing, by the computing system, the first post and the second post to be merged into the single post.   
     
     
         2 . The method of  claim 1 , wherein the similarity of subject matter associated with the first post and the second post is determined based on at least one of geographical locations or timestamps associated with the first post and the second post. 
     
     
         3 . The method of  claim 1 , wherein the subject matter associated with the first post and the second post is determined by a machine learning model trained to determine a probability a content item contains selected subject matter. 
     
     
         4 . The method of  claim 3 , wherein the machine learning model is trained based on a training set of content items correlated with a content class, wherein the correlation of the training set of content items with the content class is determined based on contextual cues associated with the training set of content items, and wherein the machine learning model is trained to generate a visual pattern template associated with the content class. 
     
     
         5 . The method of  claim 3 , wherein the machine learning model generates sets of content features that correspond to the subject matter associated with the first post and the second post and probabilities the content features are in the first post and the second post, and wherein the similarity of the subject matter associated with the first post and the second post is based on an overlap in the sets of content features. 
     
     
         6 . The method of  claim 1 , further comprising:
 providing, by the computing system, a request for a user confirmation to merge the first post and the second post into the single post; and   causing, by the computing system, the single post to be published in response to the user confirmation.   
     
     
         7 . The method of  claim 1 , further comprising:
 providing, by the computing system, a first option to revert the single post into the first post and the second post;   causing, by the computing system, the single post to be separated into the first post and the second post based on the first option;   providing, by the computing system, a second option to publish the first post or the second post in a new post; and   causing, by the computing system, the first post or the second post to be published as the new post based on the second option.   
     
     
         8 . The method of  claim 1 , further comprising:
 providing, by the computing system, an interface to update the single post with a content item selected by a user; and   causing, by the computing system, the content item to be merged into the single post with the first post and the second post.   
     
     
         9 . The method of  claim 1 , further comprising:
 providing, by the computing system, the single post in a message to a user.   
     
     
         10 . The method of  claim 1 , further comprising:
 providing, by the computing system, an indication in an interface that the single post is in the process of being published.   
     
     
         11 . A system comprising:
 at least one processor; and   a memory storing instructions that, when executed by the at least one processor, cause the system to perform operations comprising:
 determining a first post published in a feed; 
 determining a second post to be merged with the first post into a single post based on similarity of subject matter associated with the first post and the second post; and 
 causing the first post and the second post to be merged into the single post. 
   
     
     
         12 . The system of  claim 11 , wherein the similarity of subject matter associated with the first post and the second post is determined based on at least one of geographical locations or timestamps associated with the first post and the second post. 
     
     
         13 . The system of  claim 11 , wherein the subject matter associated with the first post and the second post is determined by a machine learning model trained to determine a probability a content item contains selected subject matter. 
     
     
         14 . The system of  claim 13 , wherein the machine learning model is trained based on a training set of content items correlated with a content class, wherein the correlation of the training set of content items with the content class is determined based on contextual cues associated with the training set of content items, and wherein the machine learning model is trained to generate a visual pattern template associated with the content class. 
     
     
         15 . The system of  claim 13 , wherein the machine learning model generates sets of content features that correspond to the subject matter associated with the first post and the second post and probabilities the content features are in the first post and the second post, and wherein the similarity of the subject matter associated with the first post and the second post is based on an overlap in the sets of content features. 
     
     
         16 . A non-transitory computer-readable storage medium including instructions that, when executed by at least on processor of a computing system, cause the computing system to perform operations comprising:
 determining a first post published in a feed;   determining a second post to be merged with the first post into a single post based on similarity of subject matter associated with the first post and the second post; and   causing the first post and the second post to be merged into the single post.   
     
     
         17 . The non-transitory computer-readable storage medium of  claim 16 , wherein the similarity of subject matter associated with the first post and the second post is determined based on at least one of geographical locations or timestamps associated with the first post and the second post. 
     
     
         18 . The non-transitory computer-readable storage medium of  claim 16 , wherein the subject matter associated with the first post and the second post is determined by a machine learning model trained to determine a probability a content item contains selected subject matter. 
     
     
         19 . The non-transitory computer-readable storage medium of  claim 18 , wherein the machine learning model is trained based on a training set of content items correlated with a content class, wherein the correlation of the training set of content items with the content class is determined based on contextual cues associated with the training set of content items, and wherein the machine learning model is trained to generate a visual pattern template associated with the content class. 
     
     
         20 . The non-transitory computer-readable storage medium of  claim 16 , wherein the machine learning model generates sets of content features that correspond to the subject matter associated with the first post and the second post and probabilities the content features are in the first post and the second post, and wherein the similarity of the subject matter associated with the first post and the second post is based on an overlap in the sets of content features.