Back to results
US 11,238,077 B2Granted
Auto derivation of summary data using machine learning
AssigneeSap SE
InventorsPanish Ramakrishna, Ashutosh Patel, Nithya Rajagopalan
Life of this patent
Estimating the term…
Abstract
A method of processing raw data as it is received from a data provider via an input channel is disclosed. Values are derived from the raw data as it is received from the data provider via the input channel. The derived values correspond to custom fields of a summary table. The summary table is configured to store a summary of the raw data. The custom fields correspond to data capable of improving an analysis of an entity by an analysis tool. The derived values are inserted into the custom fields of the summary table. Access to the summary table is provided as enriched data for use by the analysis tool to improve the analysis of the entity.
Claims20
A system comprising:
- one or more computer processors;
- one or more computer memories;
- and
- a set of instructions incorporated into the one or more computer memories, the set of instructions configuring the one or more computer processors to perform operations comprising:
- receiving a metric from a computing device associated with an entity, the metric comprising a summary flag;
- adding a custom field to a summary table corresponding to the metric;
- training a machine learning model based on historical raw data and historical values for the metric to identify patterns in the historical raw data that indicate a true or false value for the summary flag represented by the custom field;
- associating a handler for deriving a value from raw data as it is received with the custom field added to the summary table, the handler identifying the trained machine learning model and identifying inputs to the trained machine learning model;
- adding the handler to a set of handlers for processing the raw data;
- as the raw data is received from a data provider via an input channel, performing operations comprising:
- invoking the handler and providing at least a portion of the raw data as an input into the trained machine learning model associated with the handler to generate an output from the machine learning model, the output comprising a true or false value;
- determining a value for the summary flag based on the output of the machine learning model;
- and
- inserting the determined value for the summary flag into the custom field of the summary table;
- and
- providing access to the summary table as enriched data for use by an analysis tool.
13 more elements
A method comprising:
- receiving a metric from a computing device associated with an entity, the metric comprising a summary flag;
- adding a custom field to a summary table corresponding to the metric;
- training a machine learning model based on historical raw data and historical values for the metric to identify patterns in the historical raw data that indicate a true or false value for the summary flag represented by the custom field;
- associating a handler for deriving a value from raw data as it is received with the custom field added to the summary table, the handler identifying the trained machine learning model and identifying inputs to the trained machine learning model;
- adding the handler to a set of handlers for processing the raw data;
- as the raw data is received from a data provider via an input channel, performing operations comprising:
- invoking the handler and providing at least a portion of the raw data as an input into the trained machine learning model associated with the handler to generate an output from the machine learning model, the output comprising a true or false value;
- determining a value for the summary flag based on the output of the machine learning model;
- and
- inserting the determined value for the summary flag into the custom field of the summary table;
- and
- providing access to the summary table as enriched data for use by an analysis tool.
9 more elements
A non-transitory machine-readable medium storing instructions that, when executed by one or more computer processors, cause the one or more computer processors to perform operations comprising:
- receiving a metric from a computing device associated with an entity, the metric comprising a summary flag;
- adding a custom field to a summary table corresponding to the metric;
- training a machine learning model based on historical raw data and historical values for the metric to identify patterns in the historical raw data that indicate a true or false value for the summary flag represented by the custom field;
- associating a handler for deriving a value from raw data as it is received with the custom field added to the summary table, the handler identifying the trained machine learning model and identifying inputs to the trained machine learning model;
- adding the handler to a set of handlers for processing the raw data;
- as the raw data is received from a data provider via an input channel, performing operations comprising:
- invoking the handler and providing at least a portion of the raw data as an input into the trained machine learning model associated with the handler to generate an output from the machine learning model, the output comprising a true or false value;
- determining a value for the summary flag based on the output of the machine learning model;
- and
- inserting the determined value for the summary flag into the custom field of the summary table;
- and
- providing access to the summary table as enriched data for use by an analysis tool.
9 more elements
Dependencies are inferred from the claim text.