Blue Kai, Inc.

Workday, Inc.

Intuit, Inc.

Lucian Vlad Lita

Michael David Bigby

John Patrick Connelly

Efraim David Feinstein

Jonathan Goldman

Omar Tawakol

Vladimir Giverts

Charles Yang

Kristy Gateley

Adeyemi Ajao

Barzel Segal

Phil Monroe

Jan Prach

Tarek Rabbani

Anuranjita Tewary

Frank Wisniewski

Guohan Gao

Tobias Ullrich

Lars Pfannenschmidt

Thorsten Kruger

Brian W Gardner

Kurt Peterson

Todd Enerson

Maojin Jiang

Embodiments are directed towards collecting, aggregating and indexing unique and non-unique user data from a plurality of users. The result for a query of this indexed aggregation of user data is provided in a plurality of sub-sets of aggregated user data. Each subset of aggregated user data corresponds to a particular portion of the plurality of users. Also, each of these particular portions of the users is set at least large enough to provide general anonymity for the individual users. User data may be collected by one or more user data suppliers and provided to a user data aggregator. In some embodiments, user data may be collected as unique user data, non-unique user data, or any combination thereof. In some embodiments, user data may be aggregated by zip code, expanded zip code, and/or one or more attributes.

Profile noise anonymity for mobile users

A system, method, apparatus, and processor readable non-transitive storage media are described for matching items in large datasets based on non-invasive fingerprints of users so that collected metric data for advertisements (media) and behavioral data may be reconciled and analyzed. Since user fingerprints may not generate a unique one to one correspondence or mapping under certain constraints, the various embodiments employ a sampling method that optimally matches the output of a random sampling of non-invasive fingerprints. The use of non-invasive fingerprints and specialized sampling enables the various embodiments to provide advanced analytics for advertising content and metric data in targeted behavior advertising campaigns. To compare impressions with user profile data, the various embodiments employ in part the time stamp dimension of user profiles to generate temporally unique persistent non-invasive fingerprints.

Non-invasive sampling and fingerprinting of online users and their behavior

The disclosed embodiments relate to a system that facilitates making a copy of a profile store while the profile store is being updated. During operation, the system retrieves profiles from a profile snapshot queue, wherein the profile snapshot queue is periodically populated by accessing each profile in the profile store, and recording a snapshot of each accessed profile in the profile snapshot queue. The system then stores the profiles retrieved from the profile snapshot queue into the copy of the profile store. Next, the system retrieves updates to profiles from a live update queue, which contains a sequential list of updates to profiles in the profile store, wherein the updates are retrieved starting with a first update that occurred after the process of sequentially accessing the profiles was commenced up to a most recent update. Finally, the system uses the retrieved updates to update corresponding profiles in the copy of the profile store.

Making a copy of a profile store while processing live updates

A system, method, apparatus and processor readable media are described for real-time prediction of an advertising audience volume through analysis of historical audience data, and tuning of the predicted audience volume. Embodiments enable a user to specify a query for audience volume prediction. Such a query may be a Boolean combination of various audience categories. A time range may be determined that indicates the amount of historical data that is to be analyzed to make the audience volume prediction in real time. Employing the user-specified query, an audience volume prediction may be provided for a future time period, based on an analysis of retrieved historical audience data for the time range. Embodiments may also enable a user to tune the predicted audience volume through modification of the query through one or more iterations.

Real time audience forecasting

A system, method, apparatus, and processor readable storage media are described for real-time computation of statistics between audiences including, but not limited to, correlations, comparative metrics, and/or other statistical analysis for the audiences. Embodiments enable a user to specify a query that defines a specific audience for analysis in real-time. A past time period may be determined that indicates the amount of historical data that is to be analyzed to generate the statistical comparisons and/or correlations. Employing the user-specified query, statistical comparisons and/or correlation may be provided, based on an analysis of retrieved historical audience data for the time period. Embodiments may also enable a user to generate new statistics in real-time through modification of the audience in one or more iterations. Embodiments may also enable a user to filter, sort, and search through audiences by setting desired statistical boundaries for the resulting audience set.

Real time statistics extraction from arbitrary advertising audiences

A system for determining a canonical title includes an interface and a processor. The interface is to receive a new title. The processor is to generate a set of n-grams based on the new title; look up n-grams in canonical database to assign one or more labels; and map the new title to a canonical title based on the one or more labels.

Method for systematic mass normalization of titles

A method for normalizing raw titles to canonical titles is described. The method includes designating a set of canonical titles, generating a set of n-grams for each canonical title, assigning a set of attributes to each n-gram, assigning a set of labels to each of the attributes, and storing the labeled canonical title and labeled n-grams in a database. In some examples, a new title may be mapped to an existing canonical title in the database by generating a set of n-grams for the new title, looking up the n-grams in the database of canonical titles, retrieving the set of labels assigned to n-grams in the database that match n-grams from the new title, and assigning those labels to the corresponding attributes of the new title. The new title may then be mapped to a canonical title on the basis of similarly labeled attributes.

Growing community of inventors

Sunnyvale, CA, United States of America

Lucian Vlad Lita