公开(公告)号：US11144939B2

公开(公告)日：2021-10-12

申请号：US14959890

申请日：2015-12-04

Applicant: Adobe Inc.

Inventor： Eunyee Koh ,  Nedim Lipka

IPC: G06Q30/02 ,  H04L29/08 ,  H04L12/24

Abstract: An analytics server receives data characterizing consumer interactions that are observed by a cross-section of data providers, which may include, for example, website administrators, campaign managers, application developers, and the like. Such observational data includes device and login identifiers for a particular interaction, and optionally, timestamp information indicating when the interaction occurred. A statistical device graph model is generated based on this observational data. The statistical device graph model allows inferences to be drawn with respect to whether a given device is a private device, a shared device, or a public device. This, in turn, allows private devices which are “owned” by a single consumer to be identified. Depending on the type of observational data collected by the data providers, a wide range of additional insights can be drawn from the statistical device graph model, including for example, device usage patterns and confidence levels.

公开(公告)号：US20210271705A1

公开(公告)日：2021-09-02

申请号：US16804750

申请日：2020-02-28

Applicant: Adobe Inc.

Inventor： Eunyee Koh ,  Xin Qian ,  Sungchul Kim ,  Sana Malik Lee

IPC: G06F16/583 ,  G06F40/169 ,  G06N3/08 ,  G06N3/04 ,  G06F17/16

Abstract: Techniques of captioning for figures includes generating a caption unit for a figure by defining a finite set of caption types. From each caption type, additional input for that caption type, as well as figure image data and figure metadata, an automated system may generate a respective caption unit, each caption unit including a sequence of words. Further, the generated caption for a figure includes a combination of the generated caption units.

公开(公告)号：US10783361B2

公开(公告)日：2020-09-22

申请号：US16723619

申请日：2019-12-20

Applicant: ADOBE INC.

Inventor： Sungchul Kim ,  Deepali Jain ,  Deepali Gupta ,  Eunyee Koh ,  Branislav Kveton ,  Nikhil Sheoran ,  Atanu Sinha ,  Hung Hai Bui ,  Charles Li Chen

IPC: G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06F16/954 ,  G06K9/62

Abstract: Systems and methods provide for generating predictive models that are useful in predicting next-user-actions. User-specific navigation sequences are obtained, the navigation sequences representing temporally-related series of actions performed by users during navigation sessions. To each navigation sequence, a Recurrent Neural Network (RNN) is applied to encode the navigation sequences into user embeddings that reflect time-based, sequential navigation patterns for the user. Once a set of navigation sequences is encoded to a set of user embeddings, a variety of classifiers (prediction models) may be applied to the user embeddings to predict what a probable next-user-action may be and/or the likelihood that the next-user-action will be a desired target action.

公开(公告)号：US20200285951A1

公开(公告)日：2020-09-10

申请号：US16296076

申请日：2019-03-07

Applicant: ADOBE INC.

Inventor： Sungchul Kim ,  Scott Cohen ,  Ryan A. Rossi ,  Charles Li Chen ,  Eunyee Koh

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06F17/28

Abstract: Embodiments of the present invention are generally directed to generating figure captions for electronic figures, generating a training dataset to train a set of neural networks for generating figure captions, and training a set of neural networks employable to generate figure captions. A set of neural networks is trained with a training dataset having electronic figures and corresponding captions. Sequence-level training with reinforced learning techniques are employed to train the set of neural networks configured in an encoder-decoder with attention configuration. Provided with an electronic figure, the set of neural networks can encode the electronic figure based on various aspects detected from the electronic figure, resulting in the generation of associated label map(s), feature map(s), and relation map(s). The trained set of neural networks employs a set of attention mechanisms that facilitate the generation of accurate and meaningful figure captions corresponding to visible aspects of the electronic figure.

公开(公告)号：US10514842B2

公开(公告)日：2019-12-24

申请号：US16169877

申请日：2018-10-24

Applicant: Adobe Inc.

Inventor： Byungmoon Kim ,  Jihyun Lee ,  Eunyee Koh

IPC: G09G5/00 ,  G06F3/0488 ,  G02B27/01 ,  G06F3/01 ,  G06F3/023

Abstract: Systems and methods for detecting a user interaction by identifying a touch gesture on a touch interface on a virtual reality headset. The touch gestures are received on a front surface that is on the opposite side of the headset's inner display screen so that correspondence between the touch location and displayed content is intuitive to the user. The techniques of the invention display a cursor and enable the user to move the cursor by one type of input and make selections with the cursor using a second type of input. In this way, the user is able to intuitively control a displayed cursor by moving a finger around (e.g., dragging) on the opposite side of the display in the cursor's approximate location. The user then uses another type of touch input to make a selection at the cursor's current location.

公开(公告)号：US20190272559A1

公开(公告)日：2019-09-05

申请号：US15910926

申请日：2018-03-02

Applicant: Adobe Inc.

Inventor： Tak Yeon Lee ,  Eunyee Koh

IPC: G06Q30/02 ,  G06F17/27

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for determining and resolving semantic misalignments between digital messages containing links and corresponding external digital content. For example, in one or more embodiments, the disclosed systems compare semantic message features from the digital message with semantic external digital content features from the external digital content. More specifically, in at least one embodiment, the disclosed systems compare semantic message feature vectors and semantic external digital content feature vectors to determine a relevance score for the digital message and identify semantic misalignments. Additionally, in one or more embodiments, the disclosed systems provide for display a user interface that presents a plurality of digital messages, the linked external digital content, and identified semantic misalignments.

公开(公告)号：US20250124023A1

公开(公告)日：2025-04-17

申请号：US18486603

申请日：2023-10-13

Applicant: ADOBE INC.

Inventor： Yeuk-Yin Chan ,  Victor S. Bursztyn ,  Eunyee Koh ,  Nathan Ross ,  Vasanthi Holtcamp

IPC: G06F16/242

Abstract: Systems and methods for generating hierarchical queries from text queries are described. Embodiments are configured to encode a text query to obtain a text embedding. Then, embodiments select a field of a data schema by comparing the text embedding to a field embedding corresponding to the field. Subsequently, embodiments generate a hierarchical query including a value corresponding to the selected field. Some embodiments further include one or more formatting models configured to format values included in the text query.

公开(公告)号：US20250036936A1

公开(公告)日：2025-01-30

申请号：US18358502

申请日：2023-07-25

Applicant: ADOBE INC.

Inventor： Ryan A. Rossi ,  Ryan Aponte ,  Shunan Guo ,  Jane Elizabeth Hoffswell ,  Nedim Lipka ,  Chang Xiao ,  Yeuk-yin Chan ,  Eunyee Koh

IPC: G06N3/08

Abstract: A method, apparatus, and non-transitory computer readable medium for hypergraph processing are described. Embodiments of the present disclosure obtain, by a hypergraph component, a hypergraph that includes a plurality of nodes and a hyperedge, wherein the hyperedge connects the plurality of nodes; perform, by a hypergraph neural network, a node hypergraph convolution based on the hypergraph to obtain an updated node embedding for a node of the plurality of nodes; and generate, by the hypergraph component, an augmented hypergraph based on the updated node embedding.

公开(公告)号：US12182493B2

公开(公告)日：2024-12-31

申请号：US18484674

申请日：2023-10-11

Applicant: Adobe Inc.

Inventor： Md Main Uddin Rony ,  Fan Du ,  Iftikhar Ahamath Burhanuddin ,  Ryan Rossi ,  Niyati Himanshu Chhaya ,  Eunyee Koh

IPC: G06F17/00 ,  G06F40/106 ,  G06F40/40

Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for facilitating generation and presentation of insights. In one implementation, a set of data is used to generate a data visualization. A candidate insight associated with the data visualization is generated, the candidate insight being generated in text form based on a text template and comprising a descriptive insight, a predictive insight, an investigative, or a prescriptive insight. A set of natural language insights is generated, via a machine learning model. The natural language insights represent the candidate insight in a text style that is different from the text template. A natural language insight having the text style corresponding with a desired text style is selected for presenting the candidate insight and, thereafter, the selected natural language insight and data visualization are providing for display via a graphical user interface.

公开(公告)号：US20240311623A1

公开(公告)日：2024-09-19

申请号：US18183387

申请日：2023-03-14

Applicant: Adobe Inc.

Inventor： Ryan Rossi ,  Eunyee Koh ,  Jane Hoffswell ,  Nedim Lipka ,  Shunan Guo ,  Sudhanshu Chanpuriya ,  Sungchul Kim ,  Tong Yu

IPC: G06N3/049

CPC classification number: G06N3/049

Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for building time-decayed line graphs from temporal graph networks for efficiently and accurately generating time-aware recommendations. For example, the time-decayed line graph system creates a line graph of the temporal graph network by deriving interaction nodes from temporal edges (e.g., timed interactions) and connecting interactions that share an endpoint node. Then, the time-decayed line graph system determines the edge weights in the line graph based on differences in time between interactions, with interactions that occur closer together in time being connected with higher weights. Notably, by using this method, the derived time-decayed line graph directly represents topological proximity and temporal proximity. Upon generating the time-decayed line graphs, the system performs downstream predictive modeling such as predicted edge classifications and/or temporal link predictions.