-
公开(公告)号：US10558852B2
公开(公告)日：2020-02-11
申请号：US15814979
申请日：2017-11-16
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：US20190303995A1
公开(公告)日：2019-10-03
申请号：US15943807
申请日：2018-04-03
Applicant: Adobe Inc.
Inventor： Shuai Li , Zheng Wen , Yasin Abbasi Yadkori , Vishwa Vinay , Branislav Kveton
Abstract: The present disclosure is directed toward systems, methods, and computer readable media for training and utilizing an item-level importance sampling model to evaluate and execute digital content selection policies. For example, systems described herein include training and utilizing an item-level importance sampling model that accurately and efficiently predicts a performance value that indicates a probability that a target user will interact with ranked lists of digital content items provided in accordance with a target digital content selection policy. Specifically, systems described herein can perform an offline evaluation of a target policy in light of historical user interactions corresponding to a training digital content selection policy to determine item-level importance weights that account for differences in digital content item distributions between the training policy and the target policy. In addition, the systems described herein can apply the item-level importance weights to training data to train item-level importance sampling model.
-
公开(公告)号：US10332015B2
公开(公告)日：2019-06-25
申请号：US14885799
申请日：2015-10-16
Applicant: Adobe Inc.
Inventor： Jaya B. Kawale , Branislav Kveton , Hung H. Bui
Abstract: Particle Thompson Sampling for online matrix factorization recommendation is described. In one or more implementations, a recommendation system provides a recommendation of an item to a user using Thompson Sampling. The recommendation system then receives a rating of the item from the user. Unlike conventional solutions which only update the user latent features, the recommendation system updates both user latent features and item latent features in a matrix factorization model based on the rating of the item. The updating is performed in real time which enables the recommendation system to quickly adapt to the user ratings to provide new recommendations. In one or more implementations, to update the user latent features and the item latent features in the matrix factorization model, the recommendation system utilizes a Rao-Blackwellized particle filter for online matrix factorization.
-
公开(公告)号：US12182713B2
公开(公告)日：2024-12-31
申请号：US16203263
申请日：2018-11-28
Applicant: Adobe Inc.
Inventor： Handong Zhao , Zheng Wen , Sungchul Kim , Sheng Li , Branislav Kveton
Abstract: Systems and techniques for multi-task equidistant embedding are described that process categorical feature data to explore feature interactions. A digital analytics system enforces an equidistant relationship among features within a category while extracting high-order feature interactions by punishing both positive correlations and negative correlations among low-dimensional representations of different features. By enforcing an equidistant embedding, information is retained and accuracy is increased while higher order feature interactions are determined. Further, the digital analytics system shares knowledge among different tasks by connecting a shared network representation common to multiple tasks with exclusive network representations specific to particular tasks.
-
公开(公告)号：US11080732B2
公开(公告)日：2021-08-03
申请号：US15180582
申请日：2016-06-13
Applicant: ADOBE INC.
Inventor： Trevor Paulsen , Craig Mathis , Nikolaos Vlassis , Branislav Kveton , Kristopher Paries , Ivan Andrus , Hung Bui , Michael Rimer
IPC: G06Q30/02 , G06F3/0484
Abstract: Systems and methods are disclosed herein for providing a user interface representing differences between segments of end users. The systems and methods receive user input on a user interface identifying a first segment, the first segment being a subset of the end users having a particular characteristic, determine differences between the first segment and a second segment, and represent, on the user interface, the differences between the first segment and the second segment based on relative significances of the differences. The marketer using the user interface is able to quickly and easily identify the metrics, dimensions, and/or relationships to other segments that most distinguish the compared segments from one another.
-
Patent Agency Ranking
公开(公告)号：US10984058B2
公开(公告)日：2021-04-20
申请号：US15892085
申请日：2018-02-08
Applicant: Adobe Inc.
Inventor： Branislav Kveton , Zheng Wen , Prakhar Gupta , Iftikhar Ahamath Burhanuddin , Harvineet Singh , Gaurush Hiranandani
IPC: G06F16/00 , G06F16/9535 , G06N20/00 , G06F16/248 , G06F16/2457 , G06Q30/02
Abstract: A machine-learning framework uses partial-click feedback to generate an optimal diverse set of items. An example method includes estimating a preference vector for a user based on diverse cascade statistics for the user, the diverse cascade statistics including previously observed responses and previously observed topic gains. The method also includes generating an ordered set of items from the item repository, the items in the ordered set having highest topic gain weighted by similarity with the preference vector, providing the ordered set for presentation to the user, and receiving feedback from the user on the ordered set. The method also includes, responsive to the feedback indicating a selected item, updating the diverse cascade statistics for observed items, wherein the updating results in penalizing the topic gain for items of the observed items that are not the selected item and promoting the topic gain for the selected item.
-
7.发明申请公开(公告)号：US20190311394A1
公开(公告)日：2019-10-10
申请号：US15944980
申请日：2018-04-04
Applicant: Adobe Inc.
Inventor： Branislav Kveton , Zheng Wen , Yasin Abbasi Yadkori , Mohammad Ghavamzadeh , Claire Vernade
IPC: G06Q30/02
Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for determining parameters for digital campaign content in connection with executing digital campaigns using a rank-one assumption and a best-arm identification algorithm. For example, the disclosed system alternately explores response data in the first dimension and response data in the second dimension using the rank-one assumption and the best-arm identification algorithm to estimate highest sampling values from each dimension. In one or more embodiments, the disclosed system uses the estimated highest sampling values from the first and second dimension to determine a combination with a highest sampling value in a parameter matrix constructed based on the first dimension and the second dimension, and then executes the digital campaign using the determined combination.
-
公开(公告)号：US20190243923A1
公开(公告)日：2019-08-08
申请号：US15892085
申请日：2018-02-08
Applicant: Adobe Inc.
Inventor： Branislav Kveton , Zheng Wen , Prakhar Gupta , Iftikhar Ahamath Burhanuddin , Harvineet Singh , Gaurush Hiranandani
CPC classification number: G06F16/9535 , G06F16/24578 , G06F16/248 , G06N20/00
Abstract: A machine-learning framework uses partial-click feedback to generate an optimal diverse set of items. An example method includes estimating a preference vector for a user based on diverse cascade statistics for the user, the diverse cascade statistics including previously observed responses and previously observed topic gains. The method also includes generating an ordered set of items from the item repository, the items in the ordered set having highest topic gain weighted by similarity with the preference vector, providing the ordered set for presentation to the user, and receiving feedback from the user on the ordered set. The method also includes, responsive to the feedback indicating a selected item, updating the diverse cascade statistics for observed items, wherein the updating results in penalizing the topic gain for items of the observed items that are not the selected item and promoting the topic gain for the selected item.
-
公开(公告)号：US11354720B2
公开(公告)日：2022-06-07
申请号：US16847156
申请日：2020-04-13
Applicant: Adobe Inc.
Inventor： Hung Bui , Branislav Kveton , Suvash Sedhain , Nikolaos Vlassis , Jaya Kawale
Abstract: Techniques disclosed herein provide more efficient and more relevant item recommendations to users in large-scale environments in which only positive interest information is known. The techniques use a rank-constrained formulation that generalizes relationships based on known user interests in items and/or use a randomized singular value decomposition (SVD) approximation technique to solve the formulation to identify items of interest to users in an efficiently, scalable manner.
-
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.
-
-
-
-
-
-
-
-
-
Search Results
22
records
(took 0.03 seconds)
