公开(公告)号：US11694165B2

公开(公告)日：2023-07-04

申请号：US17960585

申请日：2022-10-05

Applicant: Adobe Inc.

Inventor： Ayush Chauhan ,  Shiv Kumar Saini ,  Parth Gupta ,  Archiki Prasad ,  Amireddy Prashanth Reddy ,  Ritwick Chaudhry

IPC: G06F18/214 ,  G06N3/063 ,  G06F18/24 ,  G11C16/14 ,  G06Q10/109 ,  G06F7/544

CPC classification number: G06F18/214 ,  G06F18/24 ,  G06N3/063 ,  G06F7/5443 ,  G06Q10/109 ,  G11C16/14

Abstract: A system implements a key value memory network including a key matrix with key vectors learned from training static feature data and time-series feature data, a value matrix with value vectors representing time-series trends, and an input layer to receive, for a target entity, input data comprising a concatenation of static feature data of the target entity, time-specific feature data, and time-series feature data for the target entity. The key value memory network also includes an entity-embedding layer to generate an input vector from the input data, a key-addressing layer to generate a weight vector indicating similarities between the key vectors and the input vector, a value-reading layer to compute a context vector from the weight and value vectors, and an output layer to generate predicted time-series data for a target metric of the target entity by applying a continuous activation function to the context vector and the input vector.

公开(公告)号：US20220391433A1

公开(公告)日：2022-12-08

申请号：US17337801

申请日：2021-06-03

Applicant: ADOBE INC.

Inventor： PARIDHI MAHESHWARI ,  Ritwick Chaudhry ,  Vishwa Vinay

IPC: G06F16/56 ,  G06F16/538 ,  G06F16/583 ,  G06K9/46 ,  G06N3/08

Abstract: Systems and methods for image processing are described. One or more embodiments of the present disclosure identify an image including a plurality of objects, generate a scene graph of the image including a node representing an object and an edge representing a relationship between two of the objects, generate a node vector for the node, wherein the node vector represents semantic information of the object, generate an edge vector for the edge, wherein the edge vector represents semantic information of the relationship, generate a scene graph embedding based on the node vector and the edge vector using a graph convolutional network (GCN), and assign metadata to the image based on the scene graph embedding.

公开(公告)号：US20220019735A1

公开(公告)日：2022-01-20

申请号：US16929903

申请日：2020-07-15

Applicant: Adobe Inc.

Inventor： Sumit Shekhar ,  Zoya Bylinskii ,  Tushar Gurjar ,  Ritwick Chaudhry ,  Ayush Goyal

IPC: G06F40/205 ,  G06N20/00 ,  G06F16/9032 ,  G06F16/9538

Abstract: This disclosure describes methods, systems, and non-transitory computer readable media for automatically parsing infographics into segments corresponding to structured groups or lists and displaying the identified segments or reflowing the segments into various computing tasks. For example, the disclosed systems may utilize a novel infographic grouping taxonomy and annotation system to group elements within infographics. The disclosed systems can train and apply a machine-learning-detection model to generate infographic segments according to the infographic grouping taxonomy. By generating infographic segments, the disclosed systems can facilitate computing tasks, such as converting infographics into digital presentation graphics (e.g., slide carousels), reflow the infographic into query-and-response models, perform search functions, or other computational tasks.

公开(公告)号：US20210248576A1

公开(公告)日：2021-08-12

申请号：US16788841

申请日：2020-02-12

Applicant: Adobe Inc.

Inventor： Shiv Kumar Saini ,  Ritwick Chaudhry ,  Harvineet Singh ,  Bhavya Bahl ,  Sriya Sainath ,  Savya Sindhu Gupta

IPC: G06Q20/12 ,  G06F16/23 ,  G06Q30/02 ,  G06Q30/06 ,  G06N7/00 ,  G06N20/00

Abstract: Techniques for exchanging data segments between data aggregators and data consumers. In an embodiment, a value of an arbitrary data segment selected by a data consumer is computed. In particular, an individual user value is calculated for each user represented in the data segment, wherein the individual user value is a weighted sum (or other function) of the one or more features of the data segment attributable to that user, plus an additive gaussian noise. The overall value of the data segment is the sum of the individual user values. An offer price for the data segment can then be calculated using the overall value. Once a request is received from the consumer to purchase the data segment at the offer price, the data segment can be exchanged between the aggregator and consumer. Thus, a data marketplace or platform for the exchange of data segments is enabled.

公开(公告)号：US20190333400A1

公开(公告)日：2019-10-31

申请号：US15964869

申请日：2018-04-27

Applicant: ADOBE INC.

Inventor： Shiv Kumar Saini ,  Ritwick Chaudhry ,  Pradeep Dogga ,  Harvineet Singh

IPC: G09B7/00 ,  G09B5/06 ,  G06N99/00 ,  G06N7/00

Abstract: Techniques are described for jointly modeling knowledge tracing and hint-taking propensity. During a read phase, a co-learning model accepts as inputs an identification of a question and the current knowledge state for a learner, and the model predicts probabilities that the learner will answer the question correctly and that the learner will use a learning aid (e.g., accept a hint). The predictions are used to personalize an e-learning plan, for example, to provide a personalized assessment. By using these predictions to personalize a learner's experience, for example, by offering hints at optimal times, the co-learning system increases efficiencies in learning and improves learning outcomes. Once a learner has interacted with a question, the interaction is encoded and provided to the co-learning model to update the learner's knowledge state during an update phase.