Microsoft Technology Licensing, LLC

Rohan Rajiv

Haichao Wei

Nihar Niranjan Mehta

Alexandros Ntoulas

Shu Zhang

Jie Xiao

Abhinav Singh

Lihong Pei

Nirav Nalinbhai Shingala

Yanbo Ma

Pei Qun Yu

Samira Tasharofi

Yaolin Wang

Faezeh Hajiaghajani Memar

Alice Hing-Yee Leung

Christopher D Erbach

Anshu Basia

Wenqiong Liu

Pierre Y Monestie

Sameer Ulhas Shenai

Rohan Koundal

Joseph Michael Esposito

Roberto Alexis Rodriguez

Kean Loong Tan

Yuhao Zhang

A device may provide a prompt to a first machine learning model. The prompt may include at least one instruction to cause the first machine learning model to use at least first natural language input associated with a use of a conversational search system to rank data sources, generate a first search query and reasoning, and use the first search query and the reasoning to generate a second search query. The first search query may include data obtained from at least one of the ranked data sources. The reasoning may include an explanation of how the first machine learning model generated the first search query. A second machine learning model may synthesize a response determined via execution of the second search query. The synthesized response may be provided for presentation via the conversational search system.

Digital content generation with in-prompt hallucination management for conversational agent

Techniques for optimizing content item delivery for installations or activations of a mobile application are provided. In one technique, a machine-learned model is trained based on multiple training instances that individually indicate whether an entity performed a particular action relative to a mobile application. In response to receiving a content item request from a third-party content delivery exchange, it is determined whether a client device that initiated the content item request has activated a particular application. In response to determining that the client device has not activated the particular application, multiple feature values of the content item request are identified. Based on inputting the feature values into the model, a score is generated that indicates a likelihood that an entity of the client device will perform the particular action relative to the particular application. Based on the score, a content item is transmitted over a network to the client device.

Optimizing content item delivery for installations of a mobile application

Techniques for optimizing network-transferred multi-card content items are provided. In one technique, a first content item selection event is initiated that involves a set of content delivery campaigns that includes a content delivery campaign that includes a content item that comprises multiple cards. The content delivery campaign is selected and the content item is transmitted to a first computing device, where the multiple cards have a first card configuration. One or more events that are associated with the first computing device displaying at least one card of the plurality of cards is identified. Based on the events, a second card configuration is determined. Another content item selection event that involves the content delivery campaign is initiated and the content delivery campaign is selected. The content item is transmitted to a second computing device, where the multiple cards have the second card configuration.

Optimization of network-transferred multi-card content items

Growing community of inventors

Santa Clara, CA, United States of America

Rohan Rajiv