Granted Patent B2

US 12,499,130 · App. 18/654,827 · Granted Dec 16, 2025

Inventors: Chakradhar Gottemukkala (Austin, TX); Baskaran Manohar (Dallas, TX); Koustuv Chatterjee (Gilbert, AZ)

Assignee: o9 Solutions, Inc.

G06F16/283G06F16/9024G06N20/00

Abstract

Claims (72)

1 . A system for event-based learning of alert conditions, for multi-dimensional data, comprising:

a storage device, comprising a data store to host data provided from a multi-dimensional data processing system, the data maintained in a graph cube network;

at least one processor; and

memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

evaluate a set of training data from the data store to train a problem correlation machine learning model that includes a feature set correlated to problematic performance of intersections in the graph cube network;

process data obtained from the multi-dimensional data processing system, to identify the data as corresponding to a data event;

generate a definition for the data event, including a set of key performance indicators (KPIs) for the data event;

apply a feature importance analysis machine learning algorithm to the set of KPIs to identify one or more features of the feature set that indicate a persistent issue;

establish an alert condition for the data event based on the one or more features;

store the alert condition in the multi-dimensional data processing system in correspondence with a scope of the alert condition

in response to establishment of the alert condition, evaluate the alert condition and the set of KPIs using the problem correlation machine learning model adopting the one or more features that indicate the persistent issue to calculate a probability for a root cause of the alert condition;

automatically identify the root cause of the alert condition based on the probability; and

store the root cause with the alert condition in the multi-dimensional data processing system.

2 . The system of claim 1 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

identify scopes for a set of intersections of a graph data structure corresponding to the alert condition; and

iterate through the set of intersections based on its scope to calculate measures for the set of KPIs.

3 . The system of claim 2 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

aggregate the measures for the set of KPIs to calculate a KPI metric for the alert condition; and

store the KPI metric for the data event in the multi-dimensional data processing system.

4 . The system of claim 1 , wherein to generate the definition for the data event, the instructions cause the at least one processor to use an alert measure obtained from the data.

5 . The system of claim 1 , wherein to generate the definition for the data event, the instructions cause the at least one processor to generate the data event with a representational state transfer (REST) of an application programming interface (API).

6 . The system of claim 1 , wherein the alert condition is determined based on measures calculated for the set of KPIs.

7 . The system of claim 1 , the memory further comprising instructions that cause the at least one processor to perform operations to:

create a calculation configuration for the data event based on the set of KPIs; and

evaluate historical data from the multi-dimensional data processing system with the calculation configuration to calculate the set of KPIs, wherein the calculation configuration includes a set of rules for calculating measures for the set of KPIs.

8 . The system of claim 7 , the memory further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

determine a scope for the set of KPIs, wherein the scope defines a portion of the multi-dimensional data processing system to be evaluated;

obtain a dataset from the multi-dimensional data processing system based on the scope; and

calculate measures for the set of KPIs using the dataset, wherein the alert condition is established using the measures for the set of KPIs.

9 . At least one non-transitory machine-readable medium including instructions for event-based learning of alert conditions, for multi-dimensional data that, when executed by at least one processor, cause the at least one processor to perform operations to:

evaluate a set of training data from a data store stored in a graph cube network of a multi-dimensional data processing system to train a problem correlation machine learning model that includes a feature set correlated to problematic performance of intersections in the graph cube network;

process data obtained from the multi-dimensional data processing system, to identify the data as corresponding to a data event;

generate a definition for the data event, including a set of key performance indicators (KPIs) for the data event;

apply a feature importance analysis machine learning algorithm to the set of KPIs to identify one or more features of the feature set that indicate a persistent issue;

establish an alert condition for the data event based on the one or more features;

store the alert condition in the multi-dimensional data processing system in correspondence with a scope of the alert condition;

in response to establishment of the alert condition, evaluate the alert condition and the set of KPIs using the problem correlation machine learning model adopting the one or more features that indicate the persistent issue to calculate a probability for a root cause of the alert condition;

automatically identify the root cause of the alert condition based on the probability; and

store the root cause with the alert condition in the multi-dimensional data processing system.

10 . The at least one non-transitory machine-readable medium of claim 9 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

identify scopes for a set of intersections of a graph data structure corresponding to the alert condition; and

iterate through the set of intersections based on its scope to calculate measures for the set of KPIs.

11 . The at least one non-transitory machine-readable medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

aggregate the measures for the set of KPIs to calculate a KPI metric for the alert condition; and

store the KPI metric for the data event in the multi-dimensional data processing system.

12 . The at least one non-transitory machine-readable medium of claim 9 , wherein to generate the definition for the data event, the instructions cause the at least one processor to use an alert measure obtained from the data.

13 . The at least one non-transitory machine-readable medium of claim 9 , wherein to generate the definition for the data event, the instructions cause the at least one processor to generate the data event with a representational state transfer (REST) of an application programming interface (API).

14 . The at least one non-transitory machine-readable medium of claim 9 , wherein the alert condition is determined based on measures calculated for the set of KPIs.

15 . The at least one non-transitory machine-readable medium of claim 9 , further comprising instructions that cause the at least one processor to perform operations to:

create a calculation configuration for the data event based on the set of KPIs; and

evaluate historical data from the multi-dimensional data processing system with a calculation configuration to calculate the set of KPIs, wherein the calculation configuration includes a set of rules for calculating measures for the set of KPIs.

16 . The at least one non-transitory machine-readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to:

determine a scope for the set of KPIs, wherein the scope defines a portion of the multi-dimensional data processing system to be evaluated;

obtain a dataset from the multi-dimensional data processing system based on the scope; and

calculate measures for the set of KPIs using the dataset, wherein the alert condition is established using the measures for the set of KPIs.

17 . A method for event-based learning of alert conditions, for multi-dimensional data comprising:

evaluating a set of training data from a data store stored in a graph cube network of a multi-dimensional data processing system to train a problem correlation machine learning model that includes a feature set correlated to problematic performance of intersections in the graph cube network;

processing data obtained from the multi-dimensional data processing system, to identify the data as corresponding to a data event;

generating a definition for the data event, including a set of key performance indicators (KPIs) for the data event;

applying a feature importance analysis machine learning algorithm to the set of KPIs to identify one or more features of the feature set that indicate a persistent issue;

establishing an alert condition for the data event based on the one or more features;

storing the alert condition in the multi-dimensional data processing system in correspondence with a scope of the alert condition;

in response to establishment of the alert condition, evaluating the alert condition and the set of KPIs using the problem correlation machine learning model adopting the one or more features that indicate the persistent issue to calculate a probability for a root cause of the alert condition;

automatically identifying the root cause of the alert condition based on the probability; and

storing the root cause with the alert condition in the multi-dimensional data processing system.

18 . The method of claim 17 , further comprising:

identifying scopes for a set of intersections of a graph data structure corresponding to the alert condition; and

iterating through the set of intersections based on its scope to calculate measures for the set of KPIs.

19 . The method of claim 18 , further comprising:

aggregating the measures for the set of KPIs to calculate a KPI metric for the alert condition; and

storing the KPI metric for the data event in the multi-dimensional data processing system.

20 . The method of claim 17 , wherein generating a definition for the data event, uses an alert measure obtained from the data.

Assignments (2)

Continuity (2)

References Cited (13)