Google Inc.

Reto Strobl

Jay Yagnik

Hrishikesh Balkrishna Aradhye

Luciano Sbaiz

Steven G Dropsho

Juan Carlos Niebles Duque

Raimundo Mirisola

Oliver Heckmann

Lane Patrick Shackleton

Thomas James Broxton

Baljeet Singh

Thomas Weich

Jonathan Goldman

Oliver Thomas Gaymond

Hristo Stefanov Stefanov

Florian Buron

Nick Jakobi

Michael Hatscher

Ralitsa Lyudmilova Angelova

Tamas Foldenyi

Andras Nemeth

Thierry Le Boulengé

Andras Orban

Haakon Dybdahl

To provide secure single-source panel audience measurement data while providing confidentiality and security of panel membership, an audience measurement server may capture content identifiers and client identifiers of devices receiving content. A panel provider may generate a probabilistic data structure via a hash of the client identifiers. The audience measurement server may utilize the filter array to extract a subset of measurement data including the data of the panel members, as well as data of some non-panel members as false positives, without being able to distinguish between the members and non-members. The audience measurement server may encrypt the extracted subset of data with each client identifier corresponding to an item of data as a key, and send the encrypted data to the panel provider, thus including both panel and some non-panel data, with the panel provider only able to decrypt data corresponding to its own panel members.

Systems and methods for audience measurement

Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium, including a method for determining bids for campaigns. The method comprises receiving an indication from a sponsor to create a video campaign and presenting a user interface for the sponsor to designate a goal for the video campaign. The goal is expressed in terms of a balance between maximizing any views versus engaged views. Engaged views arise when a user indicates their desire to view a video content item or where the user performs one or more actions related to the video content item while or after viewing the video content item. The method further comprises receiving a sponsor selection of a goal, receiving a maximum bid to be applied to all video campaign formats, automatically determining an adjusted maximum bid for each format based on the maximum bid and sponsor goal selection, and storing the campaign.

Format-specific bids based on goal-oriented targeting of content

A demographics analysis trains classifier models for predicting demographic attribute values of videos and users not already having known demographics. In one embodiment, the demographics analysis system trains classifier models for predicting demographics of videos using video features such as demographics of video uploaders, textual metadata, and/or audiovisual content of videos. In one embodiment, the demographics analysis system trains classifier models for predicting demographics of users (e.g., anonymous users) using user features based on prior video viewing periods of users. For example, viewing-period based user features can include individual viewing period statistics such as total videos viewed. Further, the viewing-period based features can include distributions of values over the viewing period, such as distributions in demographic attribute values of video uploaders, and/or distributions of viewings over hours of the day, days of the week, and the like.

Video content analysis for automatic demographics recognition of users and videos

Aspects and implementations of the present disclosure are directed to methods of and systems for search lift remarketing. In general, in some implementations, a first content item is distributed to client devices and search lift attributable to the first content item is measured by examining subsequent requests received from client devices to which the first content item has been distributed as compared to requests received from similar client devices to which the first content item has not been distributed. Keywords benefiting from search-lift attributable to the first content item are used to determine when to send a second content item in response to requests from client devices in a select audience. In some implementations, requests are compared to identify a set of keywords invoked more frequently after presentation of the first content item where an increase in usage exceeds a threshold or otherwise indicates a statistical significance.

Search lift remarketing

A graphical interface is provided that enables advertisers to iteratively define an audience of video database users that is most likely to purchase the good or service they are advertising and view detailed information associated with the audience.

Audience definition based on video database usage

Methods and systems for serving at least one online resource item to a user based on a state of the user are provided. A host computing device in communication with a memory receives data representing a record of movements of a user device. A user device profile associates locations of the user device with points in time, and with a state of a user. Following receipt of a resource request from the user device, a state of the user is determined. After at least one candidate online resource item responsive to the resource request are received, at least one online resource item relevant to the state of the user is identified and served to the user device.

Online resource serving to a traveling user

Methods, systems, user interfaces, and apparatus, including computer programs encoded on a computer-readable storage medium, for providing performance estimates for a content campaign. A method includes identifying a campaign including one or more targeting criteria for targeting content items to users; identifying historical auction results; storing the historical auction results as a plurality of documents; evaluating the plurality of documents to determine an estimated number of impressions that would occur in the plurality of documents based on the targeting criteria; determining an estimated total number of impressions for the targeting criteria in the time period based at least in part on the estimated number of impressions in the plurality of documents; and determining a total number of unique targeted users including determining a frequency of impression and determining the total number of unique targeted users as the total number of impressions divided by the frequency of impression.

System and method for online unique users and frequency estimation for advertisements on a video sharing website based on auction history results

Growing community of inventors

Walenstadt, Switzerland

Reto Strobl