Intelligent selection of images to create image narratives
US-10242034-B1 · Mar 26, 2019 · US
US2021103611A1 · US · A1
| Field | Value |
|---|---|
| Publication number | US-2021103611-A1 |
| Application number | US-201916591913-A |
| Country | US |
| Kind code | A1 |
| Filing date | Oct 3, 2019 |
| Priority date | Oct 3, 2019 |
| Publication date | Apr 8, 2021 |
| Grant date | — |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Embodiments of the present invention provide systems, methods, and computer storage media for organization of digital media in which a digital media gallery is organized based on underlying events or occasions by leveraging content tags associated with media. Content tags and their corresponding confidence scores for a set of media are compared with correlation scores of content tags with certain event types. Upon receipt of a set of media, candidate event types may be determined based on content tags associated with the set of media and relevant tags for different event types. The candidate event types are scored based on the confidence scores and the correlations scores for each candidate event type. The highest scoring candidate event type may be presented to the user as the event type for the set of media.
Opening claim text (preview).
What is claimed is: 1 . A computer method for determining an event type for a set of media, the method comprising: determining a plurality of content tags corresponding to a plurality of event types, each of the content tags including a correlation score indicating a likelihood that a content tag represents one of the plurality of event types; receiving a set of media, each media of the set of media associated with at least one content tag of the plurality of content tags; determining a confidence score for each media of the set of media, the confidence score corresponding to a likelihood that the at least one content tag of the plurality of content tags is relevant to the media; generating a plurality of event candidate scores for the set of media for at least some of the plurality of event types, the event candidate scores based at least in part on the correlation scores for the plurality of content tags and the confidence scores for each of the media of the set of media; selecting an event type of the plurality of event types having a highest event candidate score of the plurality of event candidate scores among the at least some of the plurality of event types; and causing to present, via a user interface, the selected event type for the set of media. 2 . The method of claim 1 , wherein determining the plurality of content tags corresponding to a plurality of event types includes determining, for each event type of the plurality of event types, a corresponding portion of the plurality of content tags, the portion of the plurality of content tags being relevant to the corresponding event type. 3 . The method of claim 3 , wherein the event candidate scores for the each event type of the plurality of event types are based at least in part on the correlation scores for the portion of the plurality of content tags associated with the event type. 4 . The method of claim 1 , wherein the event candidate scores are further based on the total number of media in the set of media. 5 . The method of claim 1 , wherein causing to present the selected event type includes presenting an event album with an album title being the selected event type and the event album including the set of media. 6 . The method of claim 1 , wherein each of the at least some of the plurality of event types includes a corresponding plurality of relevant tags, the plurality of relevant tags being at least a portion of the plurality of content tags, and determining the at least some of the plurality of event types is based on a threshold percentage of media in the set of media including tags matching at least one of the plurality of relevant tags. 7 . The method of claim 1 , wherein each of the at least some of the plurality of event types includes a corresponding plurality of relevant tags, the plurality of relevant tags being at least a portion of the plurality of content tags, and determining the at least some of the plurality of event types is based on tags associated with the set of media including a predetermined threshold number of the plurality of relevant tags. 8 . The method of claim 1 , the method further comprising selecting the set of media from a digital media gallery based at least in part on a timestamp associated with each of the media in the digital media gallery. 9 . The method of claim 1 , the method further comprising selecting the set of media from a digital media gallery based at least in part on a timestamp and a location associated with each of the media in the digital media gallery. 10 . The method of claim 1 , wherein the at least one content tag of the plurality of content tags indicates a corresponding characteristic of the corresponding media. 11 . One or more computer storage media storing computer-useable instructions that, when used by one or more computing devices, cause the one or more computing devices to perform operations comprising: receiving a set of images, each image of the set of images associated with a plurality of tags; determining a category event candidate score indicating a likelihood that the set of images depict a category of event types, the category event candidate score determined based on the plurality of tags matching a set of relevant tags for the category of event type, the category of event types including a plurality of event types; in response to the category event candidate score being over a predetermined threshold, determining a first event candidate score, the first event candidate score corresponding to a likelihood that the set of images belongs to a first event type, the first event type being an event type of the plurality of event types; and in response to the first event candidate score being over a predetermined first threshold, causing to present the first event type as the selected event type for the set of images. 12 . The media of claim 11 , wherein the operations further comprise: in response to the first event candidate score being below the predetermined first threshold, determining a second event candidate score, the second event candidate score corresponding to a likelihood that the set of images belongs to a second event, the second event being another event type of the plurality of event types; and in response to the second event candidate score being over a predetermined second threshold, causing to present the second event as the selected event type for the set of images. 13 . The media of claim 11 , wherein the category of event types includes one of holiday events, life events, travel events, or sports events. 14 . The media of claim 11 , wherein the category of event types comprises holiday events, and wherein the operations further comprise determining the first event candidate score based at least on a date stamp associated with each of the images in the set of images, the date stamp including a range of dates corresponding to a festival. 15 . The media of claim 11 , wherein the category of event types comprises life events, wherein the first event is a wedding and the second event is a birthday. 16 . The media of claim 11 , wherein the operations further comprise determining the category event candidate score further based on at least two or more tags of the plurality of tags including one or more of relevant tags of the set of relevant tags, and the at least two or more tags of the plurality of tags being included in a predetermined percentage of images of the set of images. 17 . The media of claim 11 , wherein the set of relevant tags include one or more of party, celebration, birthday, cake, balloon, wedding, bride, groom, Christmas, gift, candle, decoration, ceremony, anniversary and reception. 18 . The media of claim 15 , wherein the operations further comprise: determining the first event candidate score based on a first threshold percentage of images of the set of images including tags of the plurality of tags being wedding, bride, or groom; and determining the second event candidate score based on a second threshold percentage of images of the set of images including tags of the plurality of tags being cake, birthday or balloon. 19 . A media organization system comprising: one or more hardware processors and memory configured to provide computer program instructions to the one or more hardware processors; a media organization environment configured to use the one or more hardware processors to: receive a set of images; analyze each image of the set of images to generate a plurality of tags associated with each image, each tag of t
using metadata automatically derived from the content · CPC title
using information manually generated, e.g. tags, keywords, comments, manually generated location and time information · CPC title
Presentation of query results · CPC title
using geographical or spatial information, e.g. location · CPC title
Browsing; Visualisation therefor · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.