公开(公告)号：US20200259777A1

公开(公告)日：2020-08-13

申请号：US16789200

申请日：2020-02-12

Applicant: Dropbox, Inc.

Inventor： Aditi Jain ,  Manveer Singh Chawla ,  Thomas Berg ,  Swapnil Zarekar ,  Robert Kajic ,  Karandeep Johar ,  Aaron Feldstein ,  Walter Kim ,  Joe Nudell ,  Jenny Dong ,  Jared Wilson ,  Luke Thompson ,  David Kriegman

IPC: H04L12/58 ,  G06F9/50 ,  H04L29/08 ,  H04L29/06

Abstract: Techniques are provided for delayed processing for arm policy determination for content management system messaging, including, during a delayed processing window, receiving reward data for arm actions taken, where the arm actions were chosen based on a previous version of an arm choice policy, and the previous version of the arm choice policy was determined based on a previous set of reward data for a previous set of arm actions taken. When the delayed processing window has closed, a new arm choice policy is determined based at least in part on the action-reward data, and the previous set of reward data and/or the previous arm choice policy. After a request to choose an arm choice is received, a particular arm action to take is determined based on the new arm choice policy. This chosen arm is provided in response to the request.

公开(公告)号：US11171909B2

公开(公告)日：2021-11-09

申请号：US16789200

申请日：2020-02-12

Applicant: Dropbox, Inc.

Inventor： Aditi Jain ,  Manveer Singh Chawla ,  Thomas Berg ,  Swapnil Zarekar ,  Robert Kajic ,  Karandeep Johar ,  Aaron Feldstein ,  Walter Kim ,  Joe Nudell ,  Jenny Dong ,  Jared Wilson ,  Luke Thompson ,  David Kriegman

IPC: H04L12/58 ,  H04L29/06 ,  H04L29/08 ,  G06F9/50

Abstract: Techniques are provided for delayed processing for arm policy determination for content management system messaging, including, during a delayed processing window, receiving reward data for arm actions taken, where the arm actions were chosen based on a previous version of an arm choice policy, and the previous version of the arm choice policy was determined based on a previous set of reward data for a previous set of arm actions taken. When the delayed processing window has closed, a new arm choice policy is determined based at least in part on the action-reward data, and the previous set of reward data and/or the previous arm choice policy. After a request to choose an arm choice is received, a particular arm action to take is determined based on the new arm choice policy. This chosen arm is provided in response to the request.

公开(公告)号：US10608976B2

公开(公告)日：2020-03-31

申请号：US15793787

申请日：2017-10-25

Applicant: Dropbox, Inc.

Inventor： Aditi Jain ,  Manveer Singh Chawla ,  Thomas Berg ,  Swapnil Zarekar ,  Robert Kajic ,  Karandeep Johar ,  Aaron Feldstein ,  Walter Kim ,  Joe Nudell ,  Jenny Dong ,  Jared Wilson ,  Luke Thompson ,  David Kriegman

IPC: H04L12/58 ,  H04L29/06 ,  H04L29/08 ,  G06F9/50

Abstract: Computer-implemented techniques include, during a delayed processing window, receiving reward data for arm actions taken, where the arm actions were chosen based on a previous version of an arm choice policy, and the previous version of the arm choice policy was determined based on a previous set of reward data for a previous set of arm actions taken. When the delayed processing window has closed, a new arm choice policy is determined based at least in part on the action-reward data, and the previous set of reward data and/or the previous arm choice policy. After a request to choose an arm choice is received, a particular arm action to take is determined based on the new arm choice policy. This chosen arm is provided in response to the request.

公开(公告)号：US20160253708A1

公开(公告)日：2016-09-01

申请号：US14632289

申请日：2015-02-26

Applicant: Dropbox, Inc.

Inventor： Viraj Mody ,  Robert Kajic ,  Pranav Piyush ,  Lilian Weng

IPC: G06Q30/02

CPC classification number: G06Q30/0269

Abstract: Techniques for efficiently selecting upsell content to serve to users of an online service based on complex user archetypes. Serving upsell content to a user may include selecting upsell content to serve to the user based on efficiently matching the user to a complex user archetype in response to receiving a request from a computing device of the user. The user archetype may be complex in the sense that it represents a specific pattern of user interaction with the online service over a period of time, as opposed to being based solely on user demographic information such as the users' age, sex, gender, ethnicity, location of residence, profession, and the like. In addition, the specific pattern may vary depending on the type of online service. For example, according to some of the disclosed embodiments, upsell content may be efficiently selected to serve to a user of a content item management service based on the user having added five or more work files to the content item management service or edited one or more work files hosted with the content item management service during the last twenty-eight days.

Abstract translation: 用于有效地选择加售内容以便基于复杂用户原型为在线服务的用户服务的技术。 为用户提供加售内容可以包括：响应于接收到来自用户的计算设备的请求，基于将用户有效地匹配到复杂用户原型，来选择提供给用户的加售内容。 用户原型可能是复杂的，因为它表示用户在一段时间内与在线服务交互的特定模式，而不是仅仅基于用户的年龄，性别，性别，种族等用户人口统计信息 ，居住地，职业等。 此外，具体模式可能会根据在线服务的类型而有所不同。 例如，根据所公开的实施例中的一些，可以基于已经向内容项目管理服务添加了五个或更多个工作文件的用户或者编辑一个或多个文件来高效地选择加售内容以用于内容项目管理服务的用户 在过去二十八天内由内容管理服务托管的工作文件。