Ajith C Muralidharan

20210133642, May 6, 2021

Nov 5, 2019

16/674422

- Redmond WA, US
Ajith Muralidharan - Sunnyvale CA, US
Shaunak Chatterjee - Sunnyvale CA, US
Preetam Nandy - Santa Clara CA, US
Shipeng Yu - Sunnyvale CA, US
Miao Cheng - Sunnyvale CA, US

G06Q 10/04
G06F 9/54
G06Q 10/06
G06N 20/00

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.

20210096933, Apr 1, 2021

Sep 30, 2019

16/588232

- Redmond WA, US
Matthew Hsing Hung Walker - Mountain View CA, US
Ajith Muralidharan - Sunnyvale CA, US
Adriel Fuad - Sunnyvale CA, US
Yingkai Hu - Sunnyvale CA, US

G06F 9/54
G06N 20/00

Technologies for determining whether to send notification messages, from different sources, to a target user are provided. The disclosed techniques include receiving a first notification event from a first notification service and receiving a second notification event from a second notification service. The first and second notification services are different services. Using a machine-learned model to assign a first score to the first notification event and a second score to the second notification event. Based on the first score, a determination is made to generate a first notification message for the first notification event. The first notification message is then sent to a target user. Based on the second score, a determination is made not to generate a second notification message for the second notification event.

20200410018, Dec 31, 2020

Jun 27, 2019

16/454622

- Redmond WA, US
Ajith Muralidharan - Sunnyvale CA, US
Pratik Daga - Sunnyvale CA, US
Sandor Nyako - Sunnyvale CA, US
Nirav Nalinbhai Shingala - Santa Clara CA, US
Matthew H. Walker - Mountain View CA, US

G06F 16/9535
G06K 9/62
G06N 20/00

Technologies for generating dynamic notification content for notification messages using a machine learned model are provided. The disclosed techniques include identifying an event related to a particular user, where the event has a particular notification type that represents a subject type of the event. Based on the particular notification type of the event, a set of candidate headline and call-to-action combinations corresponding to the particular notification type are identified. Using the machine learned model, scores are calculated for each headline and call-to-action combination in the set of candidate headline and call-to-action combinations. One or more particular headline and call-to-action combinations from the set of candidate headline and call-to-action combinations are selected based upon the scores calculated for each combination of the set of candidate headline and call-to-action combinations. A notification message is generated for the event that includes the one or more particular headline and call-to-action combinations selected.

20200252467, Aug 6, 2020

Jan 31, 2019

16/264322

- Redmond WA, US
Yiping Yuan - Sunnyvale CA, US
Ajith Muralidharan - Sunnyvale CA, US
Padmini Jaikumar - Sunnyvale CA, US
Shipeng Yu - Sunnyvale CA, US

H04L 29/08

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.

20200213408, Jul 2, 2020

Dec 31, 2018

16/237213

- Redmond WA, US
Ajith Muralidharan - Sunnyvale CA, US
Bethany J. Wang - Sunnyvale CA, US

H04L 29/08
G06F 16/9535

Techniques for identifying and delivering notifications of user-generated content to network-limited users are provided. In one technique, for each selected target entity that has a limited network, one or more topics associated with the target entity are identified and the target entity is assigned to one or more entity-topic buckets for the identified topics. For each selected content item, one or more topics associated with the content item are identified and the content item is assigned to one or more content-topic buckets for the identified topics. The entity-topic buckets are matched to the content-topic buckets, resulting in assigning, for each selected target entity, zero or more content items to that target entity. For each target entity that is assigned one or more content items based on the matching, a notification is generated and transmitted over a computer network to a computing device of the target entity.

20200201870, Jun 25, 2020

Dec 20, 2018

16/226974

- Redmond WA, US
Smriti Ramakrishnan - Belmont CA, US
Shaunak Chatterjee - Sunnyvale CA, US
Ajith Muralidharan - Sunnyvale CA, US
Shipeng Yu - Sunnyvale CA, US
Aklil Ibssa - San Francisco CA, US
Liliya Mclean - San Jose CA, US
Pratik Daga - Sunnyvale CA, US
Jeffrey Zundel - Sunnyvale CA, US
Jingshu Huang - Mountain View CA, US
Naman Goel - San Jose CA, US
Manoj Sivakumar - Mountain View CA, US

G06F 16/2457
G06F 16/901

Systems and techniques for content creator messaging framework are described herein. Information that indicates member activities corresponding to a content item corresponding to a content segment may be obtained for a date range. A set of distinct members may be determined that are associated with the information that indicates member activities. Edges may be identified in a connections network between each member of the set of distinct members and the content creator. An edge weight may be calculated for each edge using a number of interactions between content items created by the content creator and the member. A content creator ranking may be generated for the content creator using the edge weight for each edge. A content creator notification may be transmitted to the content creator based on determining that the content creator ranking is outside a threshold.

20200104420, Apr 2, 2020

Sep 27, 2018

16/144848

- Redmond WA, US
Ajith Muralidharan - Sunnyvale CA, US
Viral Gupta - Sunnyvale CA, US
Yijie Wang - Sunnyvale CA, US
Deepak Agarwal - Sunnyvale CA, US

G06F 17/30
G06F 17/18
G06F 15/18

In an example embodiment, a machine learned model is used to determine whether to send a notification for a feed object to a user. This machine learned model is optimized not just based on the likelihood that the notification will cause the user to interact with the feed object, but also the likely short-term and long-term impacts of the user interacting with the feed object. This machine learned model factors in not only the viewer's probability of immediate action, such as clicking on a feed object, but also the probability of long-term impact, such as the display causing the viewer to contribute content to the network or the viewer's response encouraging more people to contribute content to the network. As such, the machine learned model is optimized not just on notification interactivity but also on feed objects interactivity.

20200106685, Apr 2, 2020

Sep 27, 2018

16/145024

- Redmond WA, US
Shaunak Chatterjee - Sunnyvale CA, US
Ajith Muralidharan - Sunnyvale CA, US
Ye Tu - Sunnyvale CA, US

H04L 12/26
G06F 17/50

Techniques for minimizing variance in the estimation of the effects of a treatment on an online network are disclosed herein. In some embodiments, a computer system determines different permutations of selection parameters for selecting treatment entities from an online network of entities, calculating a corresponding variance in an effect value representing an effect of a treatment on the online network for each permutation of selection parameters in the plurality of permutations of selection parameters, selecting one of the different permutations of selection parameters based on the corresponding variance of the different permutation of selection parameters being lower than the corresponding variances of all of the other permutations of selection parameters, selecting a group of treatment entities from the online network of entities based on the selected permutation of selection parameters, and applying the treatment to the group of treatment entities based on the selecting of the group of treatment entities.