Oracle International Corporation

Kendra Mariko Chen

David Abraham Wiener

Guohan Gao

John Patrick Connelly

Vernon W Hui

James Kong Hsu

Man Chan

Stephen John Papa

Abe Taha

Aleksandar Mastilovic

Sherene Wael Hilal

Jeevan Gheevarghese Joseph

Ben Hekster

Anping Wang

Matthew Perry Abrams

Adison Hana Wongkar

Vernon Wah-Non Hui

Padmanabhan Natarajan

Hyunjung Lee

Sanjeev Khodaskar

A method, system, and computer program product for managing user identification codes in an interne advertising environment. One aspect implements a system including a database engine to store a plurality of signals comprising characteristics and/or values received from a user device. A user ID generator calculates collision statistics and/or fragmentation statistics to form a first mapping function that is in turn used to generate a plurality of identification codes based at least in part a first set of selected signals. A calibration module produces measurements determined from collision quantities and/or fragmentation quantities using the first mapping function, wherein the measurements are determined by comparing the plurality of identification codes to entries in a known ID database. A sequencing module generates updated sequences of mapping functions.

Tunable statistical ids

A server receives incoming data records comprising an ID value and respective user attributes corresponding to a user activity that originates at a user device. Characteristics of the activity and/or characteristics of the user device are considered in order to assign a probabilistic confidence value, which is in turn used to generate links from an incoming data record to other previously-received data records, and in so doing, generates a probabilistic link between one set of user attributes from the incoming data record and another set of user attributes from previously-received data records. A messaging campaign specification that describes target user attributes is used to identify a matching set of target audience member records. The determination of a match or not is based on the probabilistic confidence value and a threshold can be varied to extend audience reach. The identified set of target audience member records are transmitted over a network.

Extending audience reach in messaging campaigns using probabilistic ID linking

A method, system, and computer program product for managing user identification codes in an internet advertising environment. One aspect implements a system including a database engine to store a plurality of signals comprising characteristics and/or values received from a user device. A user ID generator calculates collision statistics and/or fragmentation statistics to form a first mapping function that is in turn used to generate a plurality of identification codes based at least in part a first set of selected signals. A calibration module produces measurements determined from collision quantities and/or fragmentation quantities using the first mapping function, wherein the measurements are determined by comparing the plurality of identification codes to entries in a known ID database. A sequencing module generates updated sequences of mapping functions.

Tunable statistical IDs

Techniques are provided to quickly process stored objects to generate an accurate estimate of the number of live objects that will be responsive to a client's filtering request defined at least in part based on a filtering parameter. Stored objects generated from user interactions with webpages are modified to simulate live objects and processed by a live object-intake simulator. The simulated results are then filtered using the filtering parameter to form a subset of matching objects. An estimate of the number of live objects produced by the filtering parameter is generated using at least the count of the objects in the subset. A confidence metric of the estimate is computed, in some cases using a statistical model. Under certain conditions, the estimate is delivered, the confidence metric is delivered, and/or live object intake based on the filtering parameter is initiated.

Object count estimation by live object simulation

Techniques are provided for accurately and quickly processing distributed stored objects to provide a timely and accurate prediction of the number of live objects a parameterized file request will produce. Stored objects representing previous user webpage visit interactions are stored in different storage locations in a data store. The stored objects at each storage location are processed in parallel by hashing stored objects with a hash function such that they are spread somewhat uniformly into buckets. Sub-buckets in each bucket are formed that correspond to selected category identifiers. Also in parallel, K-minimum values are computed for each sub-bucket to estimate the count of stored objects in the data store. The K-minimum values for sub-buckets corresponding to the same category ID across all buckets are combined, in some cases harmonically, and used to generate a predicted number of live objects responsive to a parameterized file request.

Object count prediction using distributed processing

Growing community of inventors

San Jose, CA, United States of America

Kendra Mariko Chen