Automated image processing and insight presentation

Patent metadata

Field	Value
Publication number	US-11297027-B1
Application number	US-202016778242-A
Country	US
Kind code	B1
Filing date	Jan 31, 2020
Priority date	Jan 31, 2019
Publication date	Apr 5, 2022
Grant date	Apr 5, 2022

Abstract

Systems, methods, devices, computer readable instruction media, and other embodiments are described for automated image processing and insight presentation. One embodiment involves receiving a plurality of ephemeral content messages from a plurality of client devices, and processing the messages to identify content associated with at least a first content type. A set of analysis data associated with the first content type is then generated from the messages, and portions of the messages associated with the first content type are processed to generate a first content collection. The first content collection and the set of analysis data are then communicated to a client device configured for a display interface comprising the first content collection and a representation of at least a portion of the set of analysis data.

First claim

What is claimed is:

1. A method comprising:
receiving, at a server computer from a plurality of client devices, a plurality of ephemeral content messages;
processing, by one or more processors of the server computer, the plurality of ephemeral content messages to identify a set of ephemeral content messages associated with a first content type;
generating, from the set of ephemeral content messages using the one or more processors, a set of analysis data associated with the first content type;
processing a portion of the set of ephemeral content messages using the one or more processors to generate a first content collection associated with the first content type; and
initiating communication, by the one or more processors, of the first content collection and the set of analysis data configured for a display interface comprising the first content collection and a representation of at least a portion of the set of analysis data on a first client device,
wherein generating the set of analysis data comprises:
machine vision processing of the plurality of ephemeral content messages to identify content type values for at least one image of each message of the plurality of ephemeral content messages,
determining time, location, and source account demographic information for each message of the plurality of ephemeral content messages,
updating a set of metrics associated with corresponding content types associated with the content type values using the time, location, and source account demographic information, and
restricting access to at least the portion of the set of analysis data based on a determination that a number of client accounts associated with the portion of the set of analysis data is less than a threshold number, where the threshold number is associated with a determination that the demographic information is not sufficiently anonymous if the number of client accounts is less than the threshold number.

2. The method of claim 1 , wherein processing the portion of the set of ephemeral content messages to generate the first content collection associated with the first content type comprises analyzing the portion of the set of ephemeral content messages to generate a quality value of for each piece of content of the portion of the set of ephemeral content messages.

3. The method of claim 2 wherein the quality value for each piece of content is based on an audio quality value and one or more image quality values.

4. The method of claim 3 further comprising:
determining that a content timer for a first piece of content of the first content collection has expired; and
removing the first piece of content from the first content collection based on expiration of the content timer for the first piece of content.

5. The method of claim 4 further comprising:
analyzing an updated a set of ephemeral content messages associated with the first content type; and
updating the first content collection using updated content from the updated set of ephemeral content messages, wherein the updated set of ephemeral messages is generated after expiration of the content timer.

6. The method of claim 1 wherein processing the portion of the set of ephemeral content messages to generate the first content collection associated with the first content type comprises presenting content from the plurality of ephemeral content messages associated with the first content type to an administrator via a curation tool; and
generating the first content collection based on input selections received at the curation tool for the content from the plurality of ephemeral content messages.

7. The method of claim 1 , wherein the first content type comprises a brand association for a first brand, and wherein the brand association is identified by a logo image for the first brand or text for the first brand.

8. A computing device comprising:
communication circuitry configured to receive, a plurality of ephemeral content messages;
memory coupled to the communication circuitry and configured to store data associated with the plurality of content messages; and
one or more processors coupled to the memory and configured to perform operations comprising:
processing the plurality of ephemeral content messages to identify a set of ephemeral content messages associated with a first content type;
generating, from the set of ephemeral content messages, a set of analysis data associated with the first content type;
processing a portion of the set of ephemeral content messages to generate a first content collection associated with the first content type; and
initiating communication of the first content collection and the set of analysis data configured for a display interface comprising the first content collection and a representation of at least a portion of the set of analysis data on a first client device,
wherein generating the set of analysis data comprises:
machine vision processing of the plurality of ephemeral content messages to identify content type values for at least one image of each message of the plurality of ephemeral content messages,
determining time, location, and source account demographic information for each message of the plurality of ephemeral content messages,
updating a set of metrics associated with corresponding content types associated with the content type values using the time, location, and source account demographic information, and
restricting access to at least the portion of the set of analysis data based on a determination that a number of client accounts associated with the portion of the set of analysis data is less than a threshold number, where the threshold number is associated with a determination that the demographic information is not sufficiently anonymous if the number of client accounts is less than the threshold number.

9. The computing device of claim 8 , wherein processing the portion of the set of ephemeral content messages to generate the first content collection associated with the first content type comprises analyzing the portion of the set of ephemeral content messages to generate a quality value of for each piece of content of the portion of the set of ephemeral content messages.

10. The computing device of claim 9 wherein the quality value for each piece of content is based on an audio quality value and one or more image quality values.

11. A non-transitory computer readable medium comprising instructions that, when executed by one or more processors of a server computer, cause the server computer to perform operations comprising:
receiving, from a plurality of client devices, a plurality of ephemeral content messages;
processing the plurality of ephemeral content messages to identify a set of ephemeral content messages associated with a first content type;
generating, from the set of ephemeral content messages, a set of analysis data associated with the first content type;
processing a portion of the set of ephemeral content messages to generate a first content collection associated with the first content type; and
initiating communication of the first content collection and the set of analysis data configured for a display interface comprising the first content collection and a representation of at least a portion of the set of analysis data on a first client device,
wherein generating the set of analysis data comprises:
machine vision processing of the plurality of ephemeral content messages to identify content type values for at least one image of each message of the plurality of ephemeral content messages,
determining time, location, and source account demographic information for each message of the plurality of ephemeral content messages,

Assignees

• Snap Inc

Inventors

• Agrawal Harsh
• Huang Xuan
• Kim Jung Hyun
• Li Yuncheng
• Ma Yiwei
• Ning Tao
• Tao Ye

Classifications

• G06V10/993

  Evaluation of the quality of the acquired pattern · CPC title

• G06Q30/0201

  Market modelling; Market analysis; Collecting market data · CPC title

• G06Q30/0241

  Advertisements · CPC title

• H04L51/52

  for supporting social networking services · CPC title

• H04L67/12 Primary

  specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks · CPC title