Microsoft Technology Licensing, LLC

Shipeng Yu

Shaunak Chatterjee

Yiping Yuan

Wei-Ying Ma

Ji-Rong Wen

Ajith Muralidharan

Deng Cai

Jiaqi Ge

Yan Liu

Jeffrey Gee

Deepak Kumar

Rupesh Gupta

Gungor Polatkan

Ankit Gupta

Rohan Ramanath

Jinyun Yan

Curtis Wang

Kinjal Basu

Guanchao Wang

Parinkumar D Shah

Brad Christopher Ciraulo

Sara Smoot Gerrard

Sowmitra Thallapragada

Onkar Anant Dalal

Konstantin Salomatin

Pratik Daga

Sandor Nyako

Matthew Hsing Hung Walker

Lingjie Weng

Alexandre Lee

Changji Shi

Guangde Chen

Swapnil Ghike

Manoj Sivakumar

Peng Du

Vivek Nelamangala

Eric Brownrout

Varun Bharill

Preetam Nandy

Miao Cheng

Padmini Jaikumar

Pingjie Xiao

Banu Muthukumar

In some embodiments, a computer system generates a recommendation for a user of an online service based on user actions that have been performed by the user within a threshold amount of time before the generation of the recommendation. For each user action, the computer system determines an intent classification that identifies an activity of the user and that corresponds to different types of user actions, as well as a preference classification that identifies a target of the activity, and then stores these intent and preference classifications as part of indications of the user actions for use in generating different types of recommendations using different types of recommendation models. Additionally, the computer system may use mini-batches of data from an incoming stream of logged data to train an incremental update to one or more recommendation models.

Recommendations using session relevance and incremental learning

Methods, systems, and computer programs are presented for scheduling user notifications to maximize short-term and long-term benefits from sending the notifications. One method includes an operation for identifying features of a state used for reinforcement learning. The state is associated with an action to decide if a notification to a user is to be sent and a reward for sending the notification to the user. Further, the method includes capturing user responses to notifications sent to users to obtain training data and training a machine-learning (ML) algorithm with reinforcement learning based on the features and the training data to obtain an ML model. Additionally, the method includes receiving a request to send a notification to the user, and deciding, by the ML model, whether to send the notification based on a current state. The notification is sent to the user based on the decision.

User-notification scheduling

A message spacing system evenly distributes the communication of one or more notifications to a computing device communicatively coupled with an online service. The message spacing system also instructs an application residing on the computing device to display a badge notification. The badge notification indicates a number of pending notifications awaiting review by a member of the online service. The badge notification may be overlaid an icon corresponding to an application that the member uses to access or interact with the online service. The badge notification may also be overlaid on an icon displayed on a webpage, where the icon represents a selectable topic that the member may select to interact with the online service. The notifications that the messaging spacing system may send include offline notifications and online notifications.

Message spacing system with badge notifications using online and offline notifications

A unified notification platform for offline creation and distribution of notification content from a variety of data sources is described. The notification platform provides data adaptors that are reusable for generating notifications of different types, specifically, for generating notifications of different types that have features that have meaning across different notification types such that these features can be used to generate comparable relevance scores with respect to candidate profiles. The relevance score calculated for a notification with respect to a member profile is used to determine whether the notification is to be presented to the member represented by the member profile.

Content generation and targeting

A method can include determining, based on learned parameter values, an intrinsic interest and an affinity for the user to be influenced to visit the website, determining, using the learned parameter values, intrinsic interest, and affinity for the user to be influenced to visit the website, a first probability indicating a likelihood that the user will, in response to viewing a badge notification, turn off notifications or delete an app and a second probability indicating a likelihood that the user will, in response to viewing the badge notification on the app, visit a website, in response to determining the second probability is greater than a threshold larger than the first probability, causing the app to include the badge notification when displayed on the user device.

Preventing notification blindness

Technologies for determining whether to send a notification to an entity is provided. Disclosed techniques include receiving entity features describing attributes related to observed entity sessions. A set of entity-specific session features values may be generated from the received entity features. A session-quality prediction model may be generated using the set of entity-specific session feature values. The session-quality prediction model may determine an expected session score for a new entity session for an entity, where the expected session score describes a level of interaction for the new entity session. A notification may be received for a particular entity. The session-quality prediction model may be used to determine the expected session score for a new entity session for the particular entity. A determination may be made as to whether a notification should be sent to the particular entity based upon the expected session score for the new entity session.

Driving high quality sessions through optimization of sending notifications

This disclosure relates to systems and methods for searching names using name clusters. A method includes training a supervised machine learning system to learn a connection strength between a member and peers of the member; clustering the member with the peers in response to a threshold number of profile similarities between the member and the peers and the connection strength between the member and the peers being above a connection strength threshold value; and applying an unsupervised machine learning system using output from the supervised machine learning system and the clustering to generate a connection between the member and at least one of the peers.

Network estimation

A notification platform for distribution of notification content in an on-line social network system, on-line and in near real time, is described. As a new notification is detected in the continuous stream of notifications triggered by time-sensitive events, the near real time notifications distribution system determines member profiles representing potential recipients of the notification by traversing a relationship graph. The relationship graph has nodes representing member profiles, as well as other entities maintained in the on-line social network system. The edges of the relationship graph represent relationships between entities represented by the associated nodes. For each member profile representing a potential recipient of the notification, the near real time notifications distribution system generates a relevance score, which is used to determine whether the notification is to be delivered to the potential recipient.

Near real time notifications distribution platform

Vision-based document segmentation identifies one or more portions of semantic content of a document. The one or more portions are identified by identifying a plurality of visual blocks in the document, and detecting one or more separators between the visual blocks of the plurality of visual blocks. A content structure for the document is constructed based at least in part on the plurality of visual blocks and the one or more separators, and the content structure identifies the one or more portions of semantic content of the document. The content structure obtained using the vision-based document segmentation can optionally be used during document retrieval.

Vision-based document segmentation

Growing community of inventors

Sunnyvale, CA, United States of America

Shipeng Yu