公开(公告)号：US20230267158A1

公开(公告)日：2023-08-24

申请号：US17675290

申请日：2022-02-18

Applicant: Adobe Inc.

Inventor： Matvey Kapilevich ,  Margarita R. Savova ,  Anup Bandigadi Rao ,  Tung Thanh Mai ,  Lakshmi Shivalingaiah ,  Liron Goren Snai ,  Charles Menguy ,  Vijeth Lomada ,  Moumita Sinha ,  Harleen Sahni

IPC: G06F16/9538 ,  G06F16/901 ,  G06F16/28

CPC classification number: G06F16/9538 ,  G06F16/9024 ,  G06F16/283 ,  G06N20/00

Abstract: Multi-modal machine-learning model training techniques for search are described that overcome conventional challenges and inefficiencies to support real time output, which is not possible in conventional training techniques. In one example, a search system is configured to support multi-modal machine-learning model training. This includes use of a preview mode and an expanded mode. In the preview mode, a preview segment is generated as part of real time training of a machine learning model. In the expanded mode, the preview segment is persisted as an expanded segment that is used to train and utilize an expanded machine-learning model as part of search.

公开(公告)号：US10373197B2

公开(公告)日：2019-08-06

申请号：US13726308

申请日：2012-12-24

Applicant: Adobe Inc.

Inventor： Nicholas M. Jordon ,  Margarita R. Savova ,  Matvey Kapilevich ,  Paul Mackles ,  David M. Weinstein

IPC: G06Q30/02

Abstract: Tunable algorithmic segment techniques are described. In one or more implementations, a target audience definition is obtained that is input to initiate creation of a look-alike model. The target audience definition indicates traits associated with a baseline group of consumers who have interacted with online resources in a designated manner, such as by buying a product, visiting a website, using a service, and so forth. Tuning parameters designated for the look-alike model are ascertained and the look-alike model is built based on the target audience definition and the tuning parameters. The tuning parameters may include at least a setting selectable to control reach versus accuracy for the look-alike model. Segment data indicative of market segments generated according to the look-alike model may then be exposed for manipulation by a client. The manipulation may include selectable control over the tuning parameters to generate different look-alike groups from the segment data.

公开(公告)号：US11914665B2

公开(公告)日：2024-02-27

申请号：US17675290

申请日：2022-02-18

Applicant: Adobe Inc.

Inventor： Matvey Kapilevich ,  Margarita R. Savova ,  Anup Bandigadi Rao ,  Tung Thanh Mai ,  Lakshmi Shivalingaiah ,  Liron Goren Snai ,  Charles Menguy ,  Vijeth Lomada ,  Moumita Sinha ,  Harleen Sahni

IPC: G06F16/248 ,  G06F16/9538 ,  G06F16/28 ,  G06F16/901 ,  G06N20/00

CPC classification number: G06F16/9538 ,  G06F16/248 ,  G06F16/283 ,  G06F16/9024 ,  G06N20/00

Abstract: Multi-modal machine-learning model training techniques for search are described that overcome conventional challenges and inefficiencies to support real time output, which is not possible in conventional training techniques. In one example, a search system is configured to support multi-modal machine-learning model training. This includes use of a preview mode and an expanded mode. In the preview mode, a preview segment is generated as part of real time training of a machine learning model. In the expanded mode, the preview segment is persisted as an expanded segment that is used to train and utilize an expanded machine-learning model as part of search.

公开(公告)号：US20230297430A1

公开(公告)日：2023-09-21

申请号：US17696148

申请日：2022-03-16

Applicant: Adobe Inc.

Inventor： Moumita Sinha ,  Anup Bandigadi Rao ,  Tung Thanh Mai ,  Vijeth Lomada ,  Margarita R. Savova ,  Sapthotharan Krishnan Nair ,  Harleen Sahni

IPC: G06F9/50 ,  G06K9/62

CPC classification number: G06F9/5044 ,  G06F9/5077 ,  G06K9/6262 ,  G06K9/6257 ,  G06N20/00

Abstract: Machine-learning model retargeting techniques are described. In one example, training data is generated by extrapolating feedback data collected from entities. These techniques supports an ability to identify a wider range of thresholds and corresponding entities than those available in the feedback data. This also provides an opportunity to explore additional thresholds than those used in the past through extrapolating operations outside of a range used to define a segment, for which, the feedback data is captured. These techniques also support retargeting of a machine-learning model for a secondary label that is different than a primary label used to initially train the machine-learning model.

公开(公告)号：US10803471B2

公开(公告)日：2020-10-13

申请号：US13629330

申请日：2012-09-27

Applicant: Adobe Inc.

Inventor： David M. Weinstein ,  Matvey Kapilevich ,  Harleen S. Sahni ,  Margarita R. Savova ,  Nicholas M. Jordan ,  David A. Jared

IPC: G06Q10/10 ,  G06Q30/02

Abstract: Selection of a trait may be received. A complex segment rule may be created that is usable to evaluate one or more qualification events. For example, the segment rule may be usable to evaluate a combined recency and frequency of the one or more qualification events. The qualification events may be based on collected network data associated with the plurality of visitors with each qualification event corresponding to a separate qualification of visitor according to the trait. The qualification events may be evaluated together according to the segment rule. For example, the combined recency and frequency of the one or more qualification events may be evaluated according to the segment rule. Evaluating the segment rule may include estimating a segment population size in real-time.