Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for allocating computation resources for a plurality of databases. For each database, the system identifies a respective initial computation capacity tier for the respective database based at least on the respective utilization of the respective database. For each of a set of optimization orders, the system determines a respective set of candidate resource pools for accommodating the plurality of databases. The system selects an optimization order and determines a final set of resource pools for the plurality of databases. The system outputs data specifying the final set of resource pools.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a machine-learning model for predicting event tags. The system obtains event data that specifies, for each of a plurality of events, a respective set of text fields characterizing the respective event. The system generates, from the event data, encoded language features for the plurality of events. The system also obtains knowledge data that specifies information of the event data. The system generates, from the event data and the knowledge data, tag data specifying a respective tag for each of the plurality of events. The system generates, from the tag data and the encoded language features, a respective encoded feature vector for each of the plurality of events. The system combines the tag data with the encoded feature vectors to generate a plurality of training examples.

Abstract: A multi-layer serverless sizing stack may determine a compute sizing correction for a serverless function. The serverless sizing stack may analyze historical data to determine a base compute allocation and compute buffer range. The serverless sizing stack may traverse the compute buffer range in an iterative analysis to determine a compute size for the serverless function to support efficient computational-operation when the serverless function is instantiated.

Abstract: A multi-layer serverless sizing stack may determine a compute sizing correction for a serverless function. The serverless sizing stack may analyze historical data to determine a base compute allocation and compute buffer range. The serverless sizing stack may traverse the compute buffer range in an iterative analysis to determine a compute size for the serverless function to support efficient computational-operation when the serverless function is instantiated.

Abstract: Embodiments of this disclosure include a method and system for machine learning based evaluation of user experience on information technology (IT) support service. The method may include obtaining a field data of an IT support service ticket and obtaining a multi-score prediction engine. The method may further include predicting metric scores of a plurality of IT support service metrics for the support service ticket based on the field data by executing the multi-score prediction engine. The method may further include obtaining system-defined weights and user-defined weights for the plurality of service metrics and calculating a support service score for the support service ticket based on the metric scores, the system-defined weights, and the user-defined weights. The method may further include evaluating user experience based on the support service score.

Abstract: A system includes a multi-layer capacity configuration optimization (CCO) stack to generate a token containing prescriptions for optimize capacity configuration of a database container in a NoSQL database cloud service. The system may aggregate the capacity utilization data; predict, based on the aggregated capacity utilization data, respective prediction-based processing capacity utilizations for the database container; determine a target processing capacity utilization value from the prediction-based processing capacity utilizations; calculate respective provisioned processing capacity utilizations based on the target processing capacity utilization value; evaluate a consumption metric based on the prediction-based processing capacity utilizations and the provisioned processing capacity utilizations; select one of the predetermined capacity modes as a recommended capacity mode for the database container based on the consumption metric.

Abstract: A system includes a multi-layer capacity configuration optimization (CCO) stack to generate a token containing prescriptions for optimize capacity configuration of a database container in a NoSQL database cloud service. The system may aggregate the capacity utilization data; predict, based on the aggregated capacity utilization data, respective prediction-based processing capacity utilizations for the database container; determine a target processing capacity utilization value from the prediction-based processing capacity utilizations; calculate respective provisioned processing capacity utilizations based on the target processing capacity utilization value; evaluate a consumption metric based on the prediction-based processing capacity utilizations and the provisioned processing capacity utilizations; select one of the predetermined capacity modes as a recommended capacity mode for the database container based on the consumption metric.

Abstract: A multi-layer cluster node optimization (CNO) stack may generate a token containing cluster node optimization prescriptions for detaching nodes from a storage cluster. A prescriptive engine layer of the CNO stack may select target computing resource nodes from a selected cluster based on the utilization tracking data, the optimization metric thresholds, and the CNO interval; utilize a prediction engine to predict respective storage utilizations over a next operation cycle for the nodes of the selected cluster; generate an aggregated storage utilization prediction for the selected cluster based on the predicted storage utilizations; determine a network traffic coefficient for the selected cluster based on the network traffic data; perform a cluster determination whether to execute a cluster node optimization for the selected cluster based on the aggregated storage utilization prediction and the network traffic coefficient; and generate a CNO token based on the cluster determination.

Abstract: A mufti-layer duster node optimization (CNO) stack may generate a token containing cluster node optimization prescriptions for detaching nodes from a storage cluster. A prescriptive engine layer of the ONO stack may select target computing resource nodes from a selected cluster based on the utilization tracking data, the optimization metric thresholds, and the ONO interval; utilize a prediction engine to predict respective storage utilizations over a next operation cycle for the nodes of the selected cluster; generate an aggregated storage utilization prediction for the selected cluster based on the predicted storage utilizations; determine a network traffic coefficient for the selected cluster based on the network traffic data; perform a cluster determination whether to execute a cluster node optimization for the selected cluster based on the aggregated storage utilization prediction and the network traffic coefficient; and generate a CNO token based on the cluster determination.

Abstract: A multi-layer rate sizing stack may generate prescriptive operation-rate tokens for controlling sizing adjustments for operation-rates. The input layer of the rate sizing stack may generate operation pattern data based on operation-rate data received via network connection. A prescriptive engine layer may determine a prescriptive allowed operation-rate based on the operation pattern data. Based on the prescriptive allowed operation-rate, the prescriptive engine layer may generate the operation-rate tokens that that may be used to control rate sizing adjustments prescriptively.

Abstract: A multi-layer rate sizing stack may generate prescriptive operation-rate tokens for controlling sizing adjustments for operation-rates. The input layer of the rate sizing stack may generate operation pattern data based on operation-rate data received via network connection. A prescriptive engine layer may determine a prescriptive allowed operation-rate based on the operation pattern data. Based on the prescriptive allowed operation-rate, the prescriptive engine layer may generate the operation-rate tokens that that may be used to control rate sizing adjustments prescriptively.