-
公开(公告)号：US20200019984A1
公开(公告)日：2020-01-16
申请号：US16034232
申请日：2018-07-12
Applicant: Adobe Inc.
Inventor： Yuan Yuan , Zhenyu Yan , Yiwen Sun , Xiaojing Dong , Chen Dong , Abhishek Pani
Abstract: Dynamic Hierarchical Empirical Bayes techniques and systems are described that are implemented to control output of digital content. In one example, a system identifies splitting variables included in data. An amount of loss is then determined for each of the identified splitting variables by the system using a loss function. Based on the determined amounts of loss, the system selects at least one splitting variable from the plurality of splitting variables that are to be used to partition data in a respective node, e.g., a parent node to form a plurality of child nodes. The system, for instance, may select the splitting variable that minimizes the cost, i.e., has the lowest amount of cost. The selected splitting variable is then employed by the system to generate at least one hierarchical level of the hierarchical structure of the statistical model by partitioning data from the parent node into respective child nodes.
-
Patent Agency Ranking
公开(公告)号：US20250036706A1
公开(公告)日：2025-01-30
申请号：US18226079
申请日：2023-07-25
Applicant: Adobe Inc.
Inventor： Yuan Yuan , Bei Huang , Lijing Wang , Yancheng Li , Bowen Wang , Jin Xu , Zhenyu Yan , Qilong Yuan
IPC: G06F16/957 , G06F9/451 , H04L67/50
Abstract: In some embodiments, a computing system extrapolates aggregated interaction data associated with users of an online platform by applying a mixed granularity model to generate extrapolated interaction data for each user in the users. The aggregated interaction data includes a total number of occurrences of a target action performed by the users with respect to the online platform. The extrapolated data includes a series of actions leading to the target action for each user. The computing system identifies an impact of each action in the series of actions for each user on leading to the target action based, at least in part, upon the extrapolating a series of actions associated with the user. User interfaces presented on the online platform can be modified based on at least the identified impacts to improve customization of the user interfaces to the users or enhance an experience of the users.
-
3.发明公开公开(公告)号：US20240311643A1
公开(公告)日：2024-09-19
申请号：US18185828
申请日：2023-03-17
Applicant: Adobe Inc.
Inventor： Bowen Wang , Yuan Yuan , Bei Huang , Lijing Wang , Yancheng Li , Jin Xu , Qilong Yuan , Zhenyu Yan
Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a modified analytics prediction machine learning model using an iterative transfer learning approach. For example, the disclosed systems generate an initial version of an analytics prediction machine learning model for predicting an analytics metric according to learned parameters. In some embodiments, the disclosed systems determine expected data channel contributions for the analytics metric according to prior data. Additionally, in some cases, the disclosed systems generate a modified analytics prediction machine learning model by iteratively updating model parameters such that predicted data channel contributions are within a threshold similarity of expected data channel contributions.
-
公开(公告)号：US10956930B2
公开(公告)日：2021-03-23
申请号：US16034232
申请日：2018-07-12
Applicant: Adobe Inc.
Inventor： Yuan Yuan , Zhenyu Yan , Yiwen Sun , Xiaojing Dong , Chen Dong , Abhishek Pani
Abstract: Dynamic Hierarchical Empirical Bayes techniques and systems are described that are implemented to control output of digital content. In one example, a system identifies splitting variables included in data. An amount of loss is then determined for each of the identified splitting variables by the system using a loss function. Based on the determined amounts of loss, the system selects at least one splitting variable from the plurality of splitting variables that are to be used to partition data in a respective node, e.g., a parent node to form a plurality of child nodes. The system, for instance, may select the splitting variable that minimizes the cost, i.e., has the lowest amount of cost. The selected splitting variable is then employed by the system to generate at least one hierarchical level of the hierarchical structure of the statistical model by partitioning data from the parent node into respective child nodes.
-
公开(公告)号：US11288709B2
公开(公告)日：2022-03-29
申请号：US15938449
申请日：2018-03-28
Applicant: Adobe Inc.
Inventor： Zhenyu Yan , Chen Dong , Abhishek Pani , Yuan Yuan
Abstract: The present disclosure includes systems, methods, and non-transitory computer readable media that train and utilize multi-phase learning models to predict performance during digital content campaigns and provide digital content to client devices in a real-time bidding environment. In particular, one or more embodiments leverage organizational structure of digital content campaigns to train two learning models, utilizing different data sources, to predict performance, generate bid responses, and provide digital content to client devices. For example, the disclosed systems can train a first performance learning model in an offline mode utilizing parent-level historical data. Then, in an online mode, the disclosed systems can train a second performance learning model utilizing child-level historical data and utilize the first performance learning model and the second performance learning model to generate bid responses and bid amounts in a real-time bidding environment.
-
公开(公告)号：US20190303980A1
公开(公告)日：2019-10-03
申请号：US15938449
申请日：2018-03-28
Applicant: Adobe Inc.
Inventor： Zhenyu Yan , Chen Dong , Abhishek Pani , Yuan Yuan
Abstract: The present disclosure includes systems, methods, and non-transitory computer readable media that train and utilize multi-phase learning models to predict performance during digital content campaigns and provide digital content to client devices in a real-time bidding environment. In particular, one or more embodiments leverage organizational structure of digital content campaigns to train two learning models, utilizing different data sources, to predict performance, generate bid responses, and provide digital content to client devices. For example, the disclosed systems can train a first performance learning model in an offline mode utilizing parent-level historical data. Then, in an online mode, the disclosed systems can train a second performance learning model utilizing child-level historical data and utilize the first performance learning model and the second performance learning model to generate bid responses and bid amounts in a real-time bidding environment.
-
-
-
-
-
Search Results
6
records
(took 0.011 seconds)
