Ancestry.com Operations Inc.

General Electric Company

Lei Wu

Peng Jiang

Gann Alexander Bierner

Ian James Stiles

Rey Furner

Eugene Greenwood

Atanu Roy

Jianlong Qi

Aaron Ling

Scott Charles Evans

Philip Paul Beauchamp

Shiva Prasad Kasiviswanathan

Daniel Edward Marthaler

Varian Paul Powles

Systems and methods for determining whether two tree persons in a genealogical database correspond to the same real-life individual. Embodiments include identifying two tree persons in a genealogical database and extracting a plurality of features from both tree persons to generate two vectors. Embodiments also include calculating a plurality of metrics between the two vectors to generate a metric function. Embodiments further include generating feature weights using a recursive process based on training data input by external users, and generating a score by calculating a weighted sum of the metric function being weighted by the feature weights. The generated score may then be compared to a threshold value.

Machine-learning system and method for identifying same person in genealogical databases

A method for ranking genealogical records includes using a machine learning model to rank multiple searched records based on relevancy. The relevancy may be determined by identifying features included in a record and scaling each feature by a corresponding weight factor. In addition, a method for training a machine learning model and increasing the convergence speed of the training is described. To train the model, a machine learning process is used to optimize a ranking performance metric. A set of weights corresponding to multiple features are used to rank multiple past search records in a training set. An initial set of the weights are set by the expectation values of the weights. The weights are incrementally changed to optimize the ranking performance metric. The step size of the increment is determined based on the sensitivity of the ranking performance metric relative to the step size.

Customized coordinate ascent for ranking data records

One method for developing a data loss prevention model includes receiving, at a processing device, an event record corresponding to an operation performed on a computing device. The event record includes an event type and event data. The method also includes transforming, using the processing device, the event type to an event number corresponding to the event type. The method includes transforming, using the processing device, the event data to a numerical representation of the event data. The method includes associating an indication of whether the event type and the event data correspond to a data loss event with the event number and the numerical representation. The method also includes determining the data loss prevention model using the indication, the event number, and the numerical representation.

Systems and methods for data loss prevention

Growing community of inventors

San Ramon, CA, United States of America

Lei Wu