Accenture Global Solutions Limited

Manish Sharma Kolachalam

Madhan Kumar Srinivasan

Arun Purushothaman

Guruprasad Pv

Michael S Eisenstein

Siddesha Swamy

Manisha Dubey

Kanakalata Narayanan

Rajnikant Dutt

Suket Kumar Jain

Ranjan Kumar Jena

A system and method provide a trained model that uses vectorized word embeddings that are averaged or summed to form representations for sentences and phrases. The representations are processed in a Siamese neural network including multiple LSTM stages to find semantically related matches in catalogs for non-catalog queries. The model is trained using catalog data and randomized data using a contrastive loss function to generate similarity metrics for catalog-non-catalog pairs.

Catalog adoption in procurement

A multi-layer consumption unit estimation (CUE) stack may generate a consumption preview for prescribing cloud computing resource utilization. An input layer of the CUE stack may obtain computing resource utilization tracking data, consumption metric data, application execution tracking data, and computing resource reservation data for a set of computing resources. A configuration layer of the CUE stack may determine a CUE interval and determine consumption metric modifiers for a selected identity associated with the set of computing resources. A CUE engine layer may generate a consumption preview by advancing a dynamic consumption credit input/output flow analysis and executing a direct utilization consumption determination. The pre-prescriptive analysis layer may apply a filter metric to mark the preservable computing resource and the correctable computing resource for exclusion from prescriptive utilization processing and initiate the prescriptive utilization processing on the set of computing resources without computing resources marked for exclusion.

Consumption unit estimation analytics for prescribing cloud computing resources utilization

A multi-layer resource aggregation (RA) stack may generate prescriptive activation timetables for controlling activation states for computing resources. To facilitate operator control and adjustment, the RA stack may, at an aggregation engine layer, aggregate the computing resource into one or more resource aggregates. The computing resources within the resource aggregates may have similar individual activation prescription patterns. Machine learning techniques may be used by the RA stack to identify these related individual activation prescription patterns and aggregate the computing resources accordingly. Once aggregated, the RA stack may make a uniform activation determination for the aggregates as single units. Therefore, the computing resources within the aggregate may be controlled and/or adjust together. Thus, the RA stack increases the scalability of implementation of prescriptive computing resource activation state determinations.

Machine-learning-based aggregation of activation prescriptions for scalable computing resource scheduling

A multi-layer committed compute reservation stack may generate prescriptive reservation matrices for controlling static reservation for computing resources. A transformation layer of the committed compute reservation stack may generate a time-mapping based on historical utilization and tagging data. An iterative analysis layer may determine a consumption-constrained committed compute state of a distribution of static reservation and dynamic requisition that achieves one or more consumption efficiency goals. Once the consumption-constrained committed compute state is determined, the prescriptive engine layer may generate a reservation matrix that may be used to control computing resource static reservation prescriptively.

Prescriptive analytics based committed compute reservation stack for cloud computing resource scheduling

A multi-layer storage class placement stack may generate a token containing storage class placement prescriptions for controlling the placement of stored items within a selection of classes for storage. An input layer of the storage class placement stack may generate time-collated activity data based on historical access data, volume metric data, and/or tagging data. The time-collated activity data may include data groupings using timestamps or other timing indicators. A transformation layer may further process the time-collated activity data to generate defined-period summation data that provides summary detail for defined durations across a period of analysis. The defined-period summation data may be used by a prescriptive engine layer to generate prescriptions for placement of individual stored items by associating the prescriptions with storage identifiers for the individual items. Using the prescriptions, the prescriptive engine layer may generate the token to send to a host interface for management of the stored items.

Prescriptive analytics based storage class placement stack for cloud computing

A multi-layer activation timetable stack may generate prescriptive activation timetables for controlling activation states for computing resources. An input layer of the activation timetable stack may generate time-scaled pattern data. A transformation layer may identify trends and variables at era timescales. A data treatment layer may flag activation states based on the trends identified at the era timescales. Once the activation states a flagged, the prescriptive engine layer may generate an activation timetable that may be used to control computing resource activation prescriptively.

Growing community of inventors

Bengaluru, India

Manish Sharma Kolachalam