Systems and methods for automated local story generation and curation

Patent metadata

Field	Value
Publication number	US-10592574-B2
Application number	US-201715853609-A
Country	US
Kind code	B2
Filing date	Dec 22, 2017
Priority date	May 5, 2015
Publication date	Mar 17, 2020
Grant date	Mar 17, 2020

Abstract

Systems and methods for automated local story generation and curation are described. In one example embodiment, a server computer receives content from client devices, and processes the content to identify content characteristics. Stories are then generated based on the characteristics of the received content, and the stories are communicated to client devices. In certain embodiments, selection at a client device of an individual piece of content within a story may further be used by the system to provide the client device with a sub-story that includes pieces of content sharing content characteristics with the characteristics of the selected image or video.

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 content captured by an image sensor of a corresponding client of the plurality of client devices, a location associated with the content, and a time associated with the content;
processing, by the server system using machine vision, each content communication from the plurality of content communications to determine a set of content characteristics for the content of each of the plurality of content communications, wherein the set of content characteristics is based at least in part on one or more objects identified in the content using machine vision;
automatically generating at least a first story, wherein the first story 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 story are automatically selected by the server system based on the set of content characteristics for the content of the first plurality of pieces of content from the plurality of content communications;
associating a visibility of the first story with a first visibility area based on trend data from the set of content characteristics; and
automatically communicating the first story to a second plurality of client devices within the first visibility area in response to the associating the visibility of the first story with the first visibility area.

2. The method of claim 1 wherein the set of content characteristics further comprises one or more of:
a local content geolocation area;
a content time period;
one or more content quality metrics; and
one or more content categories.

3. The method of claim 2 further comprising, prior to generating the first story:
determining, by the server system, an baseline content receipt rate for a first set of content characteristics;
determining, by the server system, that a current content receipt rate associated with the first set of content characteristics has deviated from the baseline content receipt rate by more than a threshold amount; and
adjusting a story visibility area for the first story based on the determination that the current content receipt rate for the first set of content characteristics has deviated from the baseline content receipt rate by more than the threshold amount.

4. The method of claim 3 further comprising:
communicating the first story to a first client device based, at least in part, on a location of the first client device within the story visibility area;
receiving, at the server system from the first client device, a selection communication associated with a second piece of content of the first story;
communicating a second story comprising pieces of content sharing at least a portion of a set of content characteristics of the second piece of content; and
communicating the second story to the first client device.

5. The method of claim 4 wherein the second story is generated in response to receipt of the selection communication at the server system.

6. The method of claim 4 wherein the second story is generated and associated with the second piece of content based on content characteristics of the second piece of content prior to receipt of the selection communication.

7. The method of claim 2 wherein the one or more content categories are determined using machine vision processes operating as part of the server system to analyze each received content communication.

8. The method of claim 7 wherein the machine vision processes generate one or more content characteristic values for the content from a content dictionary; and
wherein the one or more content categories are determined using the content characteristic values for the content.

9. The method of claim 1 further comprising:
analyzing a plurality of incoming content messages to determine system trends associated with the first story; and
adjusting the visibility of the first story to a second visibility area.

10. The method of claim 9 wherein first visibility area is a local geographic area, the second visibility area is a regional geographic area comprising a plurality of local geographic areas, and the first visibility area is a first local geographic area of the plurality of local geographic areas within the regional geographic area.

11. The method of claim 9 wherein the second visibility area is a local geographic area, the first visibility area is a regional geographic area comprising a plurality of local geographic areas, and the second visibility area is a first local geographic area of the plurality of local geographic areas within the regional geographic area.

12. The method of claim 1 further comprising:
receiving, from a first client device, a first client device location;
communicating at least two stories to the first client device, wherein the at least two stories comprise the first story, wherein each of the at least two stories is associated with a visibility area, and wherein the visibility area for each of the at least two stories encompasses the first client device location.

13. A non-transitory computer readable medium comprising computer readable instructions that, when executed by one or more processors cause a server system to:
receive a plurality of content communications from a plurality of client devices, each content communication comprising at least one piece of content captured by an image sensor of a corresponding client of the plurality of client devices, a location associated with the at least one piece of content, and a time associated with the at least one piece of content;
process each content communication from the plurality of content communications using, at least in part, machine vision to determine a set of content characteristics for each piece of content, wherein the set of content characteristics is based at least in part on one or more objects identified in the content using machine vision; and
automatically generating at least a first story, wherein the first story 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 story are automatically selected by the one or more processors based on the set of content characteristics for each piece of content of the first plurality of pieces of content;
associate a visibility of the first story with a first visibility area based on trend data from the set of content characteristics; and
automatically communicating the first story to a second plurality of client devices within the first visibility area in response to the association of the visibility of the first story with the first visibility area.

14. The non-transitory computer readable medium of claim 13 wherein the one or more processors further cause the server system to:
analyze a plurality of incoming pieces of content to determine system trends associated with the first story; and
adjust the visibility of the first story to a second visibility area.

15. The non-transitory computer readable medium of claim 14 wherein the set of content characteristics for each piece of content comprises:
a local content geolocation area;
a content time period; and
one or more content categories determined from a machine vision analysis of each piece of content.

16. A server system comprising:
memory; and
one or more processors coupled to the memory and configured to perform operations comprising:
receiving, at the server sys

Assignees

• Snap Inc

Inventors

• Pavlovskaia Maria
• Spiegel Evan

Classifications

• G06F40/10

  Text processing (natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40) · CPC title

• G06F16/40

  of multimedia data, e.g. slideshows comprising image and additional audio data (retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70) · CPC title

• G06F16/489

  using time information · CPC title

• G06F16/29

  Geographical information databases · CPC title

• G06F16/437 Primary

  Administration of user profiles, e.g. generation, initialisation, adaptation, distribution · CPC title