公开(公告)号：US20180025003A1

公开(公告)日：2018-01-25

申请号：US15658361

申请日：2017-07-24

Applicant: EVERNOTE CORPORATION

Inventor： Dylan Marriott ,  Daniel Nicolae ,  Ruben Bakker ,  Alexander Pashintsev ,  Zdzislaw Pawel Losvik ,  Eugene Livshitz ,  Vitaly Glazkov ,  Boris Gorbatov ,  Ilya Buryak

IPC: G06F17/30

CPC classification number: G06F16/51 ,  G06F16/5846 ,  G06F16/5866

Abstract: This application is directed to a method for automatically identifying and transferring relevant image data implemented at a server with a processor and memory including one or programs executable by the processor. The server obtains content items from a personal content collection of a user, analyzes the content items to identify attributes associated with the images, generates rule sets based on the identified attributes, applies the generated rule sets to a plurality of unclassified images, identifies a first set of one or more of the unclassified images, associates each image of the first set with the content items and stores the first set in the personal content collection. A second set of unclassified images is placed in a candidate list to be periodically, without user intervention, monitored and updated for storing in the personal content collection. The generated rule sets are updated after images are stored in the content collection.

公开(公告)号：US10929461B2

公开(公告)日：2021-02-23

申请号：US15658361

申请日：2017-07-24

Applicant: EVERNOTE CORPORATION

Inventor： Dylan Marriott ,  Daniel Nicolae ,  Ruben Bakker ,  Alexander Pashintsev ,  Zdzislaw Pawel Losvik ,  Eugene Livshitz ,  Vitaly Glazkov ,  Boris Gorbatov ,  Ilya Buryak

IPC: G06F16/51 ,  G06F16/58 ,  G06F16/55 ,  G06F16/583

Abstract: This application is directed to a method for automatically identifying and transferring relevant image data implemented at a server with a processor and memory including one or programs executable by the processor. The server obtains content items from a personal content collection of a user, analyzes the content items to identify attributes associated with the images, generates rule sets based on the identified attributes, applies the generated rule sets to a plurality of unclassified images, identifies a first set of one or more of the unclassified images, associates each image of the first set with the content items and stores the first set in the personal content collection. A second set of unclassified images is placed in a candidate list to be periodically, without user intervention, monitored and updated for storing in the personal content collection. The generated rule sets are updated after images are stored in the content collection.

公开(公告)号：US20210240757A1

公开(公告)日：2021-08-05

申请号：US17170697

申请日：2021-02-08

Applicant: EVERNOTE CORPORATION

Inventor： Dylan Marriott ,  Daniel Nicolae ,  Ruben Bakker ,  Alexander Pashintsev ,  Zdzislaw Pawel Losvik ,  Eugene Livshitz ,  Vitaly Glazkov ,  Boris Gorbatov ,  Ilya Buryak

IPC: G06F16/51 ,  G06F16/583 ,  G06F16/58 ,  G06F16/55

Abstract: This application is directed to a method for automatically identifying and transferring relevant image data. The method includes obtaining a plurality of content items from a personal content collection and determining attributes based on the plurality of content items. The method includes generating a plurality of relevance rules. The method further includes obtaining unclassified content items and determining for a first unclassified content item a plurality of aggregate relevance scores using the plurality of relevance rules. The method include determining whether a first aggregate relevance score and/or a second aggregate relevance score satisfy threshold score. The method includes, in accordance with a determination that the first aggregate relevance score and the second aggregate relevance score do not satisfy the threshold score, forgoing determining the attributes corresponding to the first unclassified content item, and storing the first unclassified content item in a candidate list of the personal content collection.