Unified smart connector
AssigneeVisa International Service Association
InventorsSabu Peter, Karthikeyan Kandasamy, Hong Zhu, Anna Meklin
Life of this patent
Estimating the term…
Abstract
Techniques are provided for centrally analyzing data in a cloud environment. Data can be received from a cloud provider and a machine learning model of a unified smart connector is applied to the data in order to create modeled data. An operation status can be determined based on the modeled data and the unified smart connector can independently determine, for example, if additional data is needed, the type of data needed, and the source of the data.
Claims20
A method of centrally analyzing data in a cloud environment, the method comprising:
- receiving, by a unified smart connector, data from one or more cloud data sources;
- sending the received data to a table for storage;
- applying a machine learning model to the data stored in the table to create modeled data;
- predicting a status of an operation based on the modeled data;
- determining whether the status of the operation satisfies a predetermined threshold;
- and
- in response to the status being below the predetermined threshold, automatically determining, by the unified smart connector, that additional data is needed from the one or more cloud data sources.
A device comprising:
- one or more processors;
- and
- a memory coupled to the one or more processors, the memory comprising code for causing the one or more processors to implement a method comprising:
- receiving, by a unified smart connector, data from one or more cloud data sources;
- sending the received data to a table for storage;
- applying a machine learning model to the data stored in the table to create modeled data;
- predicting a status of an operation based on the modeled data;
- determining whether the status of the operation satisfies a predetermined threshold;
- and
- in response to the status being below the predetermined threshold, automatically determining, by the unified smart connector, that additional data is needed from the one or more cloud data sources.
A non-transitory computer-readable storage medium storing a plurality of instructions executable by one or more processors to cause the one or more processors to perform operations comprising:
- receiving, by a unified smart connector, data from one or more cloud data sources;
- sending the received data to a table for storage;
- applying a machine learning model to the data stored in the table to create modeled data;
- predicting a status of an operation based on the modeled data;
- determining whether the status of the operation satisfies a predetermined threshold;
- and
- in response to the status being below the predetermined threshold, automatically determining, by the unified smart connector, that additional data is needed from the one or more cloud data sources.
Dependencies are inferred from the claim text.