Automatic story creation using semantic classifiers for digital assets and associated metadata
원문보기
IPC분류정보
국가/구분
United States(US) Patent
등록
국제특허분류(IPC7판)
G06K-009/00
G11B-027/034
G06F-017/30
G11B-027/32
출원번호
US-0935737
(2007-11-06)
등록번호
US-8934717
(2015-01-13)
발명자
/ 주소
Newell, Catherine D.
Wood, Mark D.
Costello, Kathleen M.
Poetker, Robert B.
출원인 / 주소
Intellectual Ventures Fund 83 LLC
인용정보
피인용 횟수 :
2인용 특허 :
39
초록▼
A method and system for automatically creating an image product based on media assets stored in a database. A number of stored digital media files are analyzed to determine their semantic relationship to an event and are classified according to requirements and semantic rules for generating an image
A method and system for automatically creating an image product based on media assets stored in a database. A number of stored digital media files are analyzed to determine their semantic relationship to an event and are classified according to requirements and semantic rules for generating an image product. Rule sets are applied to assets for finding one or more assets that can be include in a story product. The assets, which best meet the requirements and rules of the image product are included.
대표청구항▼
1. A method comprising: automatically grouping, by a processing system, a plurality of digital image assets into one or more groupings based on metadata for the plurality of digital image assets;classifying, by the processing system, each grouping of the one or more groupings by event type;identifyi
1. A method comprising: automatically grouping, by a processing system, a plurality of digital image assets into one or more groupings based on metadata for the plurality of digital image assets;classifying, by the processing system, each grouping of the one or more groupings by event type;identifying, by the processing system, a person portrayed in each grouping;identifying, by the processing system, a sub-classification for each grouping based upon a user profile and the identified person;identifying, by the processing system, a product theme that is associated with the identified sub-classification for each grouping and is associated with a determined interest of the identified person;identifying, by the processing system, a triggering event to evaluate the plurality of digital image assets for assets required by the product theme; andautomatically producing, by the processing system in response to the identified triggering event, a media product based upon the identified product theme, where the media product includes assets automatically selected from one of the one or more groupings of the digital image assets. 2. The method of claim 1, wherein the user profile includes an indication of a relationship of the person to a product creator, and wherein the identifying the sub-classification for each grouping based upon the user profile and the identified person comprises recognizing the relationship of the person to the product creator based on the indication of the relationship within the user profile. 3. The method of claim 1, wherein the classifying each grouping of the one or more groupings by event type and the identifying the sub-classification for each grouping is performed according to a hierarchically structured interest and activity ontology, wherein the classifying each grouping comprises determining a classification for each grouping, and wherein the sub-classification comprises a sub-classification under the classification. 4. The method of claim 3, wherein the identifying the product theme associated with the identified sub-classification comprises determining that an interest of the person is associated with the classification for the respective grouping. 5. The method of claim 1, wherein the identifying the person portrayed in each grouping comprises comparing information discerned about the person from each grouping to information about the person stored in a database. 6. The method of claim 1, further comprising providing a notification that the media product has been generated. 7. The method of claim 1, further comprises indexing, by the processing system, the plurality of digital image assets. 8. The method of claim 7, wherein the indexing comprises categorizing a scene in a digital image asset into a scene type. 9. The method of claim 7, wherein the indexing comprises: deriving, by the processing system, information from a digital image asset; andstoring the derived information as metadata with the digital image asset. 10. The method of claim 1, wherein the identifying the product theme associated with the identified sub-classification is performed on a periodic basis. 11. The method of claim 1, wherein the identifying the product theme associated with the identified sub-classification is performed in response to detecting an upcoming event. 12. The method of claim 1, wherein the identifying the product theme associated with the identified sub-classification comprises consulting a product catalog ontology that associates specific product themes with specific sub-classifications. 13. The method of claim 1, wherein the identifying the product theme associated with the identified sub-classification comprises determining that the person has an interest that is associated with the product theme. 14. The method of claim 1, wherein the triggering event comprises an approaching significant date determined, by the processing system, during the evaluation of the plurality of digital image assets, wherein the significant date is inferred based on a frequency and type of user activity during a time period near the significant date. 15. The method of claim 14, wherein the frequency and type of user activity comprises a frequency of how often one or more of the plurality of digital image assets are accessed. 16. A system comprising: a memory configured to store a plurality of digital image assets; anda computer system configured to: automatically group the plurality of digital image assets into one or more groupings based on metadata for the plurality of digital image assets;classify each grouping of the one or more groupings by event type;identify a person portrayed in each grouping;identify a sub-classification for each grouping based upon a user profile and the identified person;identify a product theme associated with the identified sub-classification for each grouping;identify a triggering event to evaluate the plurality of digital image assets for assets required by the product theme; andautomatically produce, in response to the identified triggering event, a media product based upon the identified product theme, where the media product includes assets automatically selected from one of the one or more groupings of the digital image assets. 17. The system of claim 16, wherein the user profile includes an indication of a relationship of the person to a product creator, and wherein, to identify the sub-classification for each grouping based upon the user profile and the identified person, the processing system is further configured to recognize the relationship of the person to the product creator based on the indication of the relationship within the user profile. 18. The system of claim 16, wherein the processing system is configured to classify each grouping of the one or more groupings by event type and identify the sub-classification for each grouping according to a hierarchically structured interest and activity ontology, wherein, to classify each grouping, the processing system is further configured to determine a classification for each grouping, and wherein the sub-classification comprises a sub-classification under the classification. 19. The system of claim 18, wherein, to identify the product theme associated with the identified sub-classification, the processing system is further configured to determine that an interest of the person is associated with the classification for the respective grouping. 20. A non-transitory computer-readable medium having instructions stored thereon that, upon execution by a computing device, cause the computing device to perform operations comprising: automatically grouping a plurality of digital image assets into one or more groupings based on metadata for the plurality of digital image assets;classifying each grouping of the one or more groupings by event type;identifying a person portrayed in each grouping;identifying a sub-classification for each grouping based upon a user profile and the identified person;identifying a product theme associated with the identified sub-classification for each grouping;identifying a triggering event to evaluate the plurality of digital image assets for assets required by the product theme; andautomatically producing, in response to the identified triggering event, a media product based upon the identified product theme, where the media product includes assets automatically selected from one of the one or more groupings of the digital image assets.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (39)
Calhoon, Sean; Rodriguez, Tony F., Active images through digital watermarking.
McIntyre, Dale F.; Cooper, Andrew T.; Weir, Robert F., Method and system for notifying a consumer that the photofinishing order is ready and for controlling inventory of photofinishing orders in a business.
Semple,Bruce P.; Stein,Frank L., Method and system for querying multimedia data where adjusting the conversion of the current portion of the multimedia data signal based on the comparing at least one set of confidence values to the threshold.
Neville, William Kennedy; Kravits, Donald; Groth, Barbara Ann; Cohan, Maya; Carpenter, Jason Andrew; Carpenter, Michael Andrew; Rindfuss, Robert; Norpchen, Lars Erich, Method, system and apparatus for media customization.
Canora, David J.; Colglazier, Michael A.; Goodman, Eric James; Weaver, Jr., Ronald L.; Swirsky, Robert Alan, System and method for automating the creation of customized multimedia content.
Rothschild, Leigh M., System and method of linking items in audio, visual, and printed media to related information stored on an electronic network using a mobile device.
Gallagher, Andrew C.; Loui, Alexander C.; Cerosaletti, Cathleen D.; Hibino, Stacie L.; Das, Madirakshi; Stubler, Peter O., User interface for face recognition.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.