Salesforce, Inc.

Pivotal Software, Inc.

Salesforce Com, Inc.

Sarah Aerni

Till Christian Bergmann

Christian Posse

Shubha Umesh Nabar

Alex Edelstein

Michael Weil

Penny Tselikis

Jason Teller

Mehmet Ezbiderli

Regunathan Radhakrishnan

Vitaly Gordon

Kin Fai Kan

Kevin Moore

Leah McGuire

Hulya Emir-Farinas

Sara Beth Asher

Mariann Micsinai

Melissa Runfeldt

Noelle L Sio

Alexis Kohnstamm Crow

Gautam Sakleshpur Muralidhar

Natalie Casey

Eric Wayman

Luke Sedney

Methods, systems, apparatuses, devices, and computer program products are described. A system may identify, from an event log including log entries for a tenant of a multi-tenant database system, a pattern of log entries corresponding to main actions and satisfying a frequency threshold. The system may identify log entries associated with the pattern and corresponding to the main actions, detailed actions, or both. The system may retrieve data corresponding to a history field of a data object associated with the pattern and may determine at least a portion of a process flow for the data object according to the pattern and based on the log entries and the historical data. The process flow may include operations to perform using the data object. In some cases, the system may transmit, to a user device, an indication of the portion of the process flow for user review and implementation.

Automatic determination of alternative paths for a process flow using machine learning

Methods, systems, apparatuses, devices, and computer program products are described. An intelligent routing system may route a data object to a path in a process flow using a model, such as a machine-learned model. The system may receive a first data object and may route the first data object along a path of the process flow using a random routing procedure, for example, for model training. The routing may involve performing operations based on the path and the features of the first data object. The system may update one or more models based on an outcome of the operations. Following training, the system may insert a model into the process flow at a decision point between paths. The system may receive a second data object and may route the second data object to a path using the model and based on features of the second data object.

Intelligent routing of data objects between paths using machine learning

The system and methods of the disclosed subject matter provide an experimentation framework to allow a user to perform machine learning experiments on tenant data within a multi-tenant database system. The system may provide an experimental interface to allow modification of machine learning algorithms, machine learning parameters, and tenant data fields. The user may be prohibited from viewing any of the tenant data or may be permitted to view only a portion of the tenant data. Upon generating an experimental model using the experimental interface, the user may view results comparing the performance of the experimental model with a current production model.

Framework for multi-tenant data science experiments at-scale

Methods and systems are provided to determine suitable hyperparameters for a machine learning model and/or feature engineering process. A suitable machine learning model and associated hyperparameters are determined by analyzing a dataset. Suitable hyperparameter values for compatible machine learning models having one or more hyperparameters in common and a compatible dataset schema are identified. Hyperparameters may be ranked according to each of their respective influences on a model performance metrics, and hyperparameter values identified as having greater influence may be more aggressively searched.

Identification and application of hyperparameters for machine learning

A method of training a predictive model to predict a likely field value for one or more user selected fields within an application. The method comprises providing a user interface for user selection of the one or more user selected fields within the application; analyzing a pre-existing, user provided data set of objects; training, based on the analysis, the predictive model; determining, for each user selected field based on the analysis, a confidence function for the predictive model that identifies the percentage of cases predicted correctly at different applied confidence levels, the percentage of cases predicted incorrectly at different applied confidence levels, and the percentage of cases in which the prediction model could not provide a prediction at different applied confidence levels; and providing a user interface for user review of the confidence functions for user selection of confidence threshold levels to be used with the predictive model.

Recognition of biases in data and models

In general, one aspect of the subject matter described in this specification is embodied in operations of processing sequence data by selecting a distribution key according to a type of one or more tasks to be performed on the data. The key is one or more data fields of a sequence data file, e.g., a sequence alignment/map (SAM) format or binary sequence alignment/map (BAM) format file, or derived from one or more data fields of a sequence data file. The sequence data is then distributed to multiple nodes of a parallel processing relational database system. The system performs the tasks of processing the sequence data by executing database queries. The system executes the database queries on multiple nodes in parallel. The system can use query optimization functions built into the database to expedite performance of each task.

Rapid processing of biological sequence data

Genetic data in row-wise flat files, such as VCF and VCF-like files, comprising a plurality of data elements of different types is analyzed using a parallel framework in an MPP shared-nothing distributed database having a plurality of distributed segments by first parsing the data into groups of data elements of the same types, converting the data into entry-wise genetic data such that the same types of data elements are in a column, and distributing and storing the entry-wise genetic data in the distributed segments. SQL database queries are used to analyze the genetic data, including locating probable significant associations between genotype and phenotype data.

In-database single-nucleotide genetic variant analysis

This document describes, among other things, a computer-implemented method. The method includes obtaining a structured data object that having a plurality of nodes that represent elements in the data object. One or more tables that define a table representation of the data object can be generated. The one or more tables can include a plurality of table entries that correspond to the plurality of nodes, respectively. For each of one or more first nodes from among the plurality of nodes, the method can include identifying information about one or more second nodes that are determined to be adjacent or otherwise related to the first node by performing window functions along two or more coordinate systems in the one or more tables. The window function can be centered on a particular table entry that corresponds to the first node of the data object.

Element identification in database

Growing community of inventors

San Francisco, CA, United States of America

Sarah Aerni