International Business Machines Corporation

Piotr Mierzejewski

Calisto Paul Zuzarte

Ian R Finlay

Nattavut Sutyanyong

Shaikh Shahriar Quader

David C Kalmuk

Marin Litoiu

Mona Nashaat Ali Elmowafy

Emmanouil Papangelis

Sumona Mukhopadhyay

Nicolas Andres Jaramillo Duran

Classification of erroneous cell data includes performing unsupervised pre-training of a machine learning model to learn a bidirectional encoder representation of data cells, obtaining an initial training set, with labeled training examples that correlate observed cell data to correct cell data, for training the machine learning model to classify cell data, automatically augmenting the initial training set to produce an augmented training set, where the augmenting includes identifying patterns in the labeled training examples, generating transformation functions, and using the transformation functions, learning an augmentation strategy and automatically generating additional training examples correlating erroneous data values to correct data values, and training the machine learning model using the augmented training set.

Classification of erroneous cell data

A DBMS training subsystem trains a DBMS workload-manager model with training data identifying resources used to execute previous DBMS data-access requests. The subsystem integrates each request's high-level features and compile-time operations into a vector and clusters similar vectors into templates. The requests are divided into workloads each represented by a training histogram that describes the distribution of templates associated with the workload and identifies the total amounts and types of resources consumed when executing the entire workload. The resulting knowledge is used to train the model to predict production resource requirements by: i) organizing production queries into candidate workloads; ii) deriving for each candidate a histogram similar in form and function to the training histograms; iii) using the newly derived histograms to predict each candidate's resource requirements; iv) selecting the candidate with the greatest resource requirements capable of being satisfied with available resources; and v) executing the selected workload.

Learning-based workload resource optimization for database management systems

A computer-implemented method includes receiving an artifact and a problem pattern, transforming the artifact into an abstracted artifact structure, and transforming the problem pattern into a query. The query is matched against the abstracted artifact structure. Any matched portions of the abstracted artifact structure are related back to corresponding result portions of the artifact. The corresponding result portions of the artifact are returned. The method may be embodied in a corresponding computer system or computer program product.

Optimizer problem determination

Growing community of inventors

Markham, Canada

Piotr Mierzejewski