Back to results
US 12,639,331 B2Granted
Event detection system
AssigneeSnap Inc.
InventorsYupeng Gu, Xiaolin Shi, Jie Luo
Life of this patent
Estimating the term…
Abstract
An event detection system is configured to access a repository that contains a collection of media content. The media content may for example include images, videos, audio clips, and the like, wherein the media content comprises features that include: tags (e.g., hashtags or other similar mechanisms to label and sort content); captions that comprises one or more words or phrases; continuous numerical values; geolocation data (e.g., geo-hash, check-in data, coordinates); as well as temporal data (e.g., timestamps).
Claims15
A system comprising:
- a memory;
- and
- at least one hardware processor coupled to the memory and comprising instructions that causes the system to perform operations comprising:
- accessing a repository that comprises a collection of media content that comprises metadata that comprises geolocation data, temporal data, and content feature data;
- extracting the metadata from the collection of media content;
- generating a graph comprising a first axis representing location values, a second axis representing temporal values, and a third axis representing feature values;
- plotting representations of the media content from among the collection of media content on the graph based on the extracted metadata;
- receiving, from a client device, a user input that specifies a location and time period filter;
- filtering the plotted representations based on the location and time period filter to identify a subset of the media content;
- determining a total number of occurrences of content features within the subset of the media content;
- selecting a content feature from among the content features based on the total number of occurrences representing a most common content feature;
- identifying one or more clusters among the filtered representations based on a clustering parameter that comprises a geographical threshold and a temporal threshold, the one or more clusters comprising groupings of media content having geolocation data and temporal data within the geographical threshold and the temporal threshold of the clustering parameter;
- designating the selected content feature to the one or more clusters;
- and
- causing display of a visualization of the one or more clusters that comprises a table at the client device, the visualization including an indication of the location and the time period specified by the user input, and the designated content feature associated with the selected content feature.
12 more elements
A method comprising:
- accessing a repository that comprises a collection of media content that comprises metadata that comprises geolocation data, temporal data, and content feature data;
- extracting the metadata from the collection of media content;
- generating a graph comprising a first axis representing location values, a second axis representing temporal values, and a third axis representing feature values;
- plotting representations of the media content from among the collection of media content on the graph based on the extracted metadata;
- receiving, from a client device, a user input that specifies a location and time period filter;
- filtering the plotted representations based on the location and time period filter to identify a subset of the media content;
- determining a total number of occurrences of content features within the subset of the media content;
- selecting a content feature from among the content features based on the total number of occurrences representing a most common content feature;
- identifying one or more clusters among the filtered representations based on a clustering parameter that comprises a geographical threshold and a temporal threshold, the one or more clusters comprising groupings of media content having geolocation data and temporal data within the geographical threshold and the temporal threshold of the clustering parameter;
- designating the selected content feature to the one or more clusters;
- and
- causing display of a visualization of the one or more clusters that comprises a table at the client device, the visualization including an indication of the location and the time period specified by the user input, and the designated content feature associated with the selected content feature.
9 more elements
A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
- accessing a repository that comprises a collection of media content that comprises metadata that comprises geolocation data, temporal data, and content feature data;
- extracting the metadata from the collection of media content;
- generating a graph comprising a first axis representing location values, a second axis representing temporal values, and a third axis representing feature values;
- plotting representations of the media content from among the collection of media content on the graph based on the extracted metadata;
- receiving, from a client device, a user input that specifies a location and time period filter;
- filtering the plotted representations based on the location and time period filter to identify a subset of the media content;
- determining a total number of occurrences of content features within the subset of the media content;
- selecting a content feature from among the content features based on the total number of occurrences representing a most common content feature;
- identifying one or more clusters among the filtered representations based on a clustering parameter that comprises a geographical threshold and a temporal threshold, the one or more clusters comprising groupings of media content having geolocation data and temporal data within the geographical threshold and the temporal threshold of the clustering parameter;
- designating the selected content feature to the one or more clusters;
- and
- causing display of a visualization of the one or more clusters that comprises a table at the client device, the visualization including an indication of the location and the time period specified by the user input, and the designated content feature associated with the selected content feature.
9 more elements
Dependencies are inferred from the claim text.