公开(公告)号：US12205127B2

公开(公告)日：2025-01-21

申请号：US17232591

申请日：2021-04-16

Applicant: ADOBE INC.

Inventor： Sukriti Verma ,  Shripad Deshmukh ,  Jayakumar Subramanian ,  Piyush Gupta ,  Nikaash Puri

IPC: G06Q30/0201 ,  G06N3/047 ,  G06N3/08

Abstract: Interactions between a user and an e-commerce platform are automatically guided to increase the chances of a conversion. Previous sequences of interactions (e.g., conversion journeys and non-conversion journeys) with the e-commerce platform are collected, an artificial neural network (ANN) learns how to estimate a safety value a current user state by learning from previous user interactions (e.g., conversion and non-conversion journeys), a software agent of the e-commerce platform applies a current user state of the user to the ANN to determine a current safety value, and the software agent provides content to the user based on the current safety value and the current user state.

公开(公告)号：US11960520B2

公开(公告)日：2024-04-16

申请号：US17853141

申请日：2022-06-29

Applicant: Adobe Inc.

Inventor： Tanay Anand ,  Sumit Bhatia ,  Simra Shahid ,  Nikitha Srikanth ,  Nikaash Puri

IPC: G06F16/30 ,  G06F16/33 ,  G06F16/35 ,  G06F16/93 ,  G06F18/2133 ,  G06F18/2413 ,  G06F40/30

CPC classification number: G06F16/35 ,  G06F16/3347 ,  G06F16/93 ,  G06F18/2133 ,  G06F18/24147 ,  G06F40/30

Abstract: Some techniques described herein relate to generating a hierarchical topic model (HTM), which can be used to generate custom content. In one example, a method includes determining first-level topics in a topic hierarchy related to a corpus of documents. A first-level topic of the first-level topics includes multiple words. The multiple words are grouped into clusters based on word embeddings of the multiple words. The multiple words are then subdivided into second-level topics as subtopics of the first-level topic, such that the number of second-level topics equals the number of clusters. A document of the corpus of documents is assigned to the first-level topic and to a second-level topic of the second-level topics, and an indication is received of access by a user to the document. Custom content is generated for the user based on one or more other documents assigned to the first-level topic and the second-level topic.

公开(公告)号：US20240062057A1

公开(公告)日：2024-02-22

申请号：US17818506

申请日：2022-08-09

Applicant: Adobe Inc.

Inventor： Surgan Jandial ,  Nikaash Puri ,  Balaji Krishnamurthy

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/0454

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that regularize learning targets for a student network by leveraging past state outputs of the student network with outputs of a teacher network to determine a retrospective knowledge distillation loss. For example, the disclosed systems utilize past outputs from a past state of a student network with outputs of a teacher network to compose student-regularized teacher outputs that regularize training targets by making the training targets similar to student outputs while preserving semantics from the teacher training targets. Additionally, the disclosed systems utilize the student-regularized teacher outputs with student outputs of the present states to generate retrospective knowledge distillation losses. Then, in one or more implementations, the disclosed systems compound the retrospective knowledge distillation losses with other losses of the student network outputs determined on the main training tasks to learn parameters of the student networks.

公开(公告)号：US11907816B2

公开(公告)日：2024-02-20

申请号：US17892878

申请日：2022-08-22

Applicant: Adobe Inc.

Inventor： Pinkesh Badjatiya ,  Nikaash Puri ,  Ayush Chopra ,  Anubha Kabra

IPC: G06N20/00 ,  G06N20/10 ,  G06F18/2431 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2453

CPC classification number: G06N20/00 ,  G06F18/211 ,  G06F18/214 ,  G06F18/2431 ,  G06F18/2453 ,  G06N20/10

Abstract: A data classification system is trained to classify input data into multiple classes. The system is initially trained by adjusting weights within the system based on a set of training data that includes multiple tuples, each being a training instance and corresponding training label. Two training instances, one from a minority class and one from a majority class, are selected from the set of training data based on entropies for the training instances. A synthetic training instance is generated by combining the two selected training instances and a corresponding training label is generated. A tuple including the synthetic training instance and the synthetic training label is added to the set of training data, resulting in an augmented training data set. One or more such synthetic training instances can be added to the augmented training data set and the system is then re-trained on the augmented training data set.

公开(公告)号：US11645541B2

公开(公告)日：2023-05-09

申请号：US15815899

申请日：2017-11-17

Applicant: Adobe Inc.

Inventor： Piyush Gupta ,  Nikaash Puri ,  Balaji Krishnamurthy

IPC: G06N3/086 ,  G06N20/00 ,  G06F16/35 ,  G06N3/126 ,  G06N3/08 ,  G06N5/045 ,  G06N5/025 ,  G06N5/01 ,  G06N20/20

CPC classification number: G06N3/086 ,  G06F16/353 ,  G06N3/08 ,  G06N3/126 ,  G06N5/045 ,  G06N20/00 ,  G06N5/01 ,  G06N5/025 ,  G06N20/20

Abstract: A technique is disclosed for generating class level rules that globally explain the behavior of a machine learning model, such as a model that has been used to solve a classification problem. Each class level rule represents a logical conditional statement that, when the statement holds true for one or more instances of a particular class, predicts that the respective instances are members of the particular class. Collectively, these rules represent the pattern followed by the machine learning model. The techniques are model agnostic, and explain model behavior in a relatively easy to understand manner by outputting a set of logical rules that can be readily parsed. Although the techniques can be applied to any number of applications, in some embodiments, the techniques are suitable for interpreting models that perform the task of classification. Other machine learning model applications can equally benefit.

公开(公告)号：US20220253478A1

公开(公告)日：2022-08-11

申请号：US17729515

申请日：2022-04-26

Applicant: Adobe Inc.

Inventor： Ajay Jain ,  Sanjeev Tagra ,  Sachin Soni ,  Ryan Timothy Rozich ,  Nikaash Puri ,  Jonathan Stephen Roeder

IPC: G06F16/535 ,  G06F16/583 ,  G06N20/00 ,  G06N3/04 ,  G06K9/62 ,  G06F16/9535 ,  G06Q30/06 ,  G06N3/08 ,  G06Q30/02

Abstract: Digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. The plurality of digital images each capture the object for inclusion as part of generating digital content, e.g., a webpage, a thumbnail to represent a digital video, and so on. In one example, digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. As a result, the service provider system may select a digital image of an object from a plurality of digital images of the object that has an increased likelihood of achieving a desired outcome and may address the multitude of different ways in which an object may be presented to a user.

公开(公告)号：US20210232621A1

公开(公告)日：2021-07-29

申请号：US16774681

申请日：2020-01-28

Applicant: Adobe Inc.

Inventor： Ajay Jain ,  Sanjeev Tagra ,  Sachin Soni ,  Ryan Timothy Rozich ,  Nikaash Puri ,  Jonathan Stephen Roeder

IPC: G06F16/535 ,  G06F16/583 ,  G06K9/62 ,  G06N3/04 ,  G06N20/00

Abstract: Digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. The plurality of digital images each capture the object for inclusion as part of generating digital content, e.g., a webpage, a thumbnail to represent a digital video, and so on. In one example, digital image selection techniques are described that employ machine learning to select a digital image of an object from a plurality of digital images of the object. As a result, the service provider system may select a digital image of an object from a plurality of digital images of the object that has an increased likelihood of achieving a desired outcome and may address the multitude of different ways in which an object may be presented to a user.

公开(公告)号：US10515400B2

公开(公告)日：2019-12-24

申请号：US15259832

申请日：2016-09-08

Applicant: Adobe Inc.

Inventor： Balaji Krishnamurthy ,  Raghavender Goel ,  Nikaash Puri

IPC: G06Q30/00 ,  G06F17/30 ,  G06Q30/06 ,  G06F17/27 ,  G06N3/04 ,  G06N5/04 ,  G06N3/08

Abstract: Learning vector-space representations of items for recommendations using word embedding models is described. In one or more embodiments, a word embedding model is used to produce item vector representations of items based on considering items interacted with as words and items interacted with during sessions as sentences. The item vectors are used to produce item recommendations similar to currently or recently viewed items.

公开(公告)号：US20240345707A1

公开(公告)日：2024-10-17

申请号：US18409638

申请日：2024-01-10

Applicant: Adobe Inc.

Inventor： Yaman Kumar ,  Somesh Singh ,  William Brandon George ,  Timothy Chia-chi Liu ,  Suman Basetty ,  Pranjal Prasoon ,  Nikaash Puri ,  Mihir Naware ,  Mihai Corlan ,  Joshua Marshall Butikofer ,  Abhinav Chauhan ,  Kumar Mrityunjay Singh ,  James Patrick O'Reilly ,  Hyman Chung ,  Lauren Dest ,  Clinton Hansen Goudie-Nice ,  Brandon John Pack ,  Balaji Krishnamurthy ,  Kunal Kumar Jain ,  Alexander Klimetschek ,  Matthew William Rozen

IPC: G06F3/0484 ,  G06F3/0482 ,  G06F18/2415 ,  G06F40/151 ,  G06F40/166 ,  G06T11/20 ,  G06V10/40 ,  G06V10/764

CPC classification number: G06F3/0484 ,  G06F3/0482 ,  G06F18/2415 ,  G06F40/151 ,  G06F40/166 ,  G06T11/206 ,  G06V10/40 ,  G06V10/764 ,  G06T2200/24

Abstract: Content creation techniques are described that leverage content analytics to provide insight and guidance as part of content creation. To do so, content features are extracted by a content analytics system from a plurality of content and used by the content analytics system as a basis to generate a content dataset. Event data is also collected by the content analytics system from an event data source. Event data describes user interaction with respective items of content, including subsequent activities in both online and physical environments. The event data is then used to generate an event dataset. An analytics user interface is then generated by the content analytics system using the content dataset and the event dataset and is usable to guide subsequent content creation and editing.

公开(公告)号：US12008033B2

公开(公告)日：2024-06-11

申请号：US17447908

申请日：2021-09-16

Applicant: ADOBE INC.

Inventor： Yaman Kumar ,  Vinh Ngoc Khuc ,  Vijay Srivastava ,  Umang Moorarka ,  Sukriti Verma ,  Simra Shahid ,  Shirsh Bansal ,  Shankar Venkitachalam ,  Sean Steimer ,  Sandipan Karmakar ,  Nimish Srivastav ,  Nikaash Puri ,  Mihir Naware ,  Kunal Kumar Jain ,  Kumar Mrityunjay Singh ,  Hyman Chung ,  Horea Bacila ,  Florin Silviu Iordache ,  Deepak Pai ,  Balaji Krishnamurthy

IPC: G06F7/02 ,  G06F16/00 ,  G06F16/535 ,  G06F16/54 ,  G06F16/58 ,  G06F16/583 ,  G06N20/00

CPC classification number: G06F16/5866 ,  G06F16/535 ,  G06F16/54 ,  G06F16/583 ,  G06N20/00

Abstract: Methods, computer systems, computer-storage media, and graphical user interfaces are provided for determining user affinities by tracking historical user interactions with tagged digital content and using the user affinities in content generation applications. Accordingly, the system may track user interactions with published digital content in order to generate user interaction reports whenever a user engages with the digital content. The system may aggregate the interaction reports to generate an affinity profile for a user or audience of users. A marketer may then generate digital content for a target user or audience of users and the system may process the digital content to generate a set of tags for the digital content. Based on the set of tags, the system may then evaluate the digital content in view of the affinity profile for the target user/audience to determine similarities or differences between the digital content and the affinity profile.