Google Inc.

Sarvjeet Singh

Robert Michael Saliba

Roee Livne

Kiley McEvoy

Jay Yagnik

Thomas Price

Ryan Michael Rifkin

Nitin Khandelwal

Tushar Deepak Chandra

Tania Bedrax-Weiss

Deepak Ramachandran

Rasmus Munk Larsen

Anandsudhakar Kesari

Prachi Gupta

Deepak Ramamurthi Sivaramapuram Chandrasekaran

Akshay Goel

Yi-Fan Chen

David Sanchez

Jonathan Eccles

John Roberts Anderson

Gustavo Menezes Ponte Moreira

Grady Simon

Peter Brandt

Ashwin Ram

Bo Fu

Sue Yi Chew

Kunal Jain

Jierui Xie

Implementations described herein utilize an independent server for facilitating secure exchange of data between multiple disparate parties. The independent server receives client data, via an automated assistant application executing at least in part at a client device, that is to be transmitted to a given third-party application. The independent server processes the client data, using a first encoder-decoder model, to generate opaque client data, and transmits the opaque client data to the given third-party application and without transmitting any of the client data. Further, the independent server receives response data, via the given third-party application, that is generated based on the opaque client data and that is to be transmitted back to the client device. The independent server processes the response data, using a second encoder-decoder model, to generate opaque response data, and transmits the opaque response data to the client device and without transmitting any of the response data.

Method(s) and system(s) for utilizing an independent server to facilitate secure exchange of data

Techniques are disclosed that enable the generation of a content agent based on content parameter(s) determined from an initial user request for content as well as a dialog session to further refine the request for content. Various implementations include using the content agent to render additional content responsive to an additional user request. Additional or alternatively implementations include using the content agent to proactively render content to the user.

Rendering content using a content agent and/or stored content parameter(s)

Balancing content distribution between a machine learning model and a statistical model provides a baseline assurance in combination with the benefits of a well-trained machine learning model for content selection. In some implementations, a server receiving requests for a content item assigns a first proportion of the received requests to a first group and assigns remaining requests to a second group. The server uses a machine learning model to select variations of the requested content item for responding to requests assigned to the first group and uses a statistical model to select content variations for requests assigned to the second group. The server obtains performance information, e.g., acceptance rates for the different variations, and compares performance of the different models used for content selection. Audience share assigned to the machine learning model is increased when it outperforms the statistical model and decreased when it underperforms the statistical model.

Assessing accuracy of a machine learning model

Techniques are disclosed that enable the generation of candidate endorsements for recommended items of content using an ensemble of nominators. Various implementations include each nominator in the ensemble providing a candidate endorsement for each recommended item of content. Additionally or alternatively, an endorsement is selected to present to the user based on a score determined for each candidate endorsement.

Generating content endorsements using machine learning nominator(s)

An indication of a content item being provided to a content item platform may be received. Users associated with the content item platform may be identified and a plurality of classifications may be received. A first portion of the users associated with a first classification and a second portion of the users associated with a second classification may be identified. Notifications identifying the content item may be sent to the first portion of the users. A determination may be made as to whether an amount of time that has elapsed since the notifications have been sent to the first portion of the users satisfies a threshold amount of time. Responsive to determining that the amount of time that has elapsed satisfies the threshold amount of time, the notifications identifying the content item may be sent to the second portion of the users associated with the second classification.

Staggered notification by affinity to promote positive discussion

An indication of a content item being provided to a channel of a content item sharing platform may be received. Users associated with the channel of the content item sharing platform may be identified. Classifications of feedback of the users that are based on evaluations of the feedback from the plurality of users for other content items on the content item sharing platform may be received. A first portion of the plurality of users associated with a first classification indicating a higher rating than a second portion of the plurality of users associated with a second classification indicating a lower rating may be identified. Notifications identifying the content item may be sent to the first portion of the plurality of users associated with the first classification indicating the higher rating before the second portion associated with the second classification indicating the lower rating.

Implementations include systems and methods for scoring candidates for set recommendation problems. An example method includes repeating, for each code in code arrays for items in a set of items, determining a most common value for the code. In some implementations, the method includes determining that the most common value occurs with a frequency that meets an occurrence threshold and adding the code and the most common value to set-inclusion criteria. In other implementations, the method includes determining a value for the code from a code array for a seed item and adding the code and the most common value to set-inclusion criteria when the value for the code from the code array for the seed item matches the most common value. The method may also include evaluating a similarity with a candidate item based on the set-inclusion criteria and basing a recommendation regarding the candidate item on the similarity.

Scoring candidates for set recommendation problems

Growing community of inventors

Palo Alto, CA, United States of America

Sarvjeet Singh