Using an event graph schema for root cause identification and event classification in system monitoring

1. A computer program product, the computer program product being tangibly embodied on a non-transitory computer-readable storage medium and comprising instructions that, when executed by at least one computing device, are configured to cause the at least one computing device to:

determine an event graph schema for a technology landscape, the technology landscape being characterized by scores assigned to performance metrics for the technology landscape, wherein the event graph schema includes a plurality of nodes corresponding to the performance metrics and the scores, and includes directional edges connecting node pairs of the plurality of nodes, each directional edge having a score-dependent validity criterion defined by the scores of a corresponding node pair;

determine anomalous scores of the scores associated with an event within the technology landscape;

determine, from the anomalous scores, anomalous nodes;

generate an event graph instance of the event graph schema to obtain at least one causal path, including designating, in the event graph schema, at least one invalid edge of the directional edges for which a corresponding score-dependent validity criterion of a corresponding node pair is not met, and instantiating valid edges from the directional edges for inclusion in the at least one causal path, each valid edge connecting two of the anomalous nodes and meeting the score-dependent validity criterion of corresponding directional edges;

determine the at least one causal path that includes the valid edges and connected anomalous nodes; and

traverse the at least one causal path to identify at least one of the connected anomalous nodes as a root cause node of the event.

2. The computer program product of claim 1 , wherein the scores have positive and negative signs, and satisfaction of the score-dependent validity criterion is defined based on combinations of the positive and negative signs, and on score values of the scores.

3. The computer program product of claim 1 , wherein each directional edge defines a cause and effect relationship between the corresponding node pair.

4. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

determine the anomalous scores from scores assigned to the performance metrics using a trained machine learning model.

5. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

display the event graph instance, including visually identifying the at least one causal path and the root cause node.

6. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

determine a second causal path, including second valid edges, second anomalous nodes, and a second root cause node;

display the event graph instance with a selection option for displaying either or both of the second causal path and the at least one causal path; and

classify the event with respect to inclusion of both the second causal path and the at least one causal path.

7. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

traverse the at least one causal path including traversing from a path end node of the at least one causal path to a first node of the at least one causal path;

evaluate whether the first node qualifies as a potential root cause node;

if so, designate the first node as the root cause node; and

if not, traverse the at least one causal path back towards the path end node until the root cause node is reached.

8. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

determine that a limit breach node of the nodes is associated with a limit breach value that exceeds a limit breach threshold; and

include the limit breach node within the at least one causal path.

9. The computer program product of claim 8 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

display the event graph instance with the at least one causal path; and

visually identify the root cause node and the limit breach node within the event graph instance.

10. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:

store the scores in association with the event to obtain labelled training data;

train a machine learning model using the labelled training data and a supervised machine learning algorithm; and

predict a future event, based on the trained machine learning model and current values of the scores.

11. The computer program product of claim 1 , wherein the instructions, when executed by the at least one computing device, are configured to cause the at least one computing device to:

determine the at least one causal path at a first time;

determine second anomalous scores associated with a second event within the technology landscape at a second time;

generate, based on the second anomalous scores, a second instance of the event graph schema to obtain a second causal path; and

traverse the second causal path to identify at least one of the connected anomalous nodes as a second root cause node of the second event.

12. A computer-implemented method, the method comprising:

accessing, from a memory, an event graph schema for a technology landscape, the technology landscape being characterized by scores assigned to performance metrics for the technology landscape, wherein the event graph schema includes a plurality of nodes corresponding to the performance metrics and the scores, and includes directional edges connecting node pairs of the plurality of nodes, each directional edge having a score-dependent validity criterion defined by scores of a corresponding node pair;

interfacing with components of the technology landscape to determine anomalous scores of the scores associated with an event within the technology landscape, to thereby determine anomalous nodes;

generate an event graph instance of the event graph schema to obtain at least one causal path, including designating, in the event graph schema, at least one invalid edge of the directional edges for which a corresponding score-dependent validity criterion of a corresponding node pair is not met, and instantiating valid edges from the directional edges for inclusion in the at least one causal path, each valid edge connecting two of the anomalous nodes and meeting the score-dependent validity criterion of corresponding directional edges;

determining the at least one causal path that includes the valid edges and connected anomalous nodes;

traversing the at least one causal path to identify at least one of the connected anomalous nodes as a root cause node of the event; and

displaying the root cause node.

13. The method of claim 12 , further comprising:

determining the anomalous scores from scores assigned to the performance metrics using a trained machine learning model.

14. The method of claim 12 , further comprising:

displaying the event graph instance including the at least one causal path, including visually identifying the root cause node.

15. The method of claim 12 , further comprising:

determining a second causal path, including second valid edges, second anomalous nodes, and a second root cause node;

displaying the event graph instance with a selection option for displaying either or both of the second causal path and the at least one causal path; and

classifying the event with respect to inclusion of both the second causal path and the at least one causal path.

16. The method of claim 12 , further comprising:

traversing the at least one causal path including traversing from a path end node of the at least one causal path to a first node of the at least one causal path;

evaluating whether the first node qualifies as a potential root cause node;

if so, designating the first node as the root cause node; and

if not, traversing the at least one causal path back towards the path end node until the root cause node is reached.

17. A system comprising:

at least one memory including instructions; and

at least one processor that is operably coupled to the at least one memory and that is arranged and configured to execute the instructions, which, when executed, cause the at least one processor to:

determine an event graph schema for a technology landscape, the technology landscape being characterized by scores assigned to performance metrics for the technology landscape, wherein the event graph schema includes a plurality of nodes corresponding to the performance metrics and the scores, and includes directional edges connecting node pairs of the plurality of nodes, each directional edge having a score-dependent validity criterion defined by scores of a corresponding node pair;

determine, from anomalous scores of the scores associated with an event within the technology landscape, anomalous nodes of the nodes;

generate an event graph instance of the event graph schema to obtain at least one causal path, including designating, in the event graph schema, at least one invalid edge of the directional edges for which a corresponding score-dependent validity criterion of a corresponding node pair is not met, and instantiating valid edges from the directional edges for inclusion in the at least one causal path, each valid edge connecting two of the anomalous nodes and meeting the score-dependent validity criterion of corresponding directional edges;

determine the at least one causal path that includes the valid edges and connected anomalous nodes; and

traverse the at least one causal path to identify at least one of the connected anomalous nodes as a root cause node of the event.

18. The system of claim 17 , wherein the instructions, when executed, are further configured to cause the at least one processor to:

determine the anomalous scores from scores assigned to the performance metrics using a trained machine learning model.

19. The system of claim 17 , wherein the instructions, when executed, are further configured to cause the at least one processor to:

display the event graph instance including the at least one causal path, including visually identifying the root cause node.

20. The system of claim 17 , wherein the instructions, when executed, are further configured to cause the at least one processor to:

determine a second causal path, including second valid edges, second anomalous nodes, and a second root cause node;

display the event graph instance with a selection option for displaying either or both of the second causal path and the at least one causal path; and

classify the event with respect to inclusion of both the second causal path and the at least one causal path.

21. The system of claim 17 , wherein the instructions, when executed, are further configured to cause the at least one processor to:

traverse the at least one causal path including traversing from a path end node of the at least one causal path to a first node of the at least one causal path;

evaluate whether the first node qualifies as a potential root cause node;

if so, designate the first node as the root cause node; and

if not, traverse the at least one causal path back towards the path end node until the root cause node is reached.