System and method for compact tree representation for machine learning
Aspects of the present disclosure involve systems, methods, devices, and the like for generating compact tree representations applicable to machine learning. In one embodiment, a system is introduced that can retrieve a decision tree structure to generate a compact tree representation model. The compact tree representation model may come in the form of a matrix design to maintain the relationships expressed by the decision tree structure.
1. A system comprising:
a non-transitory memory storing instructions; and
a processor configured to execute instructions to cause the system to:
in response to a determination that new data is available for processing, retrieve a data tree structure of the new data;
determine, from the new data, nodes on the data tree structure, the nodes corresponding to processes running on at least one secondary machine, wherein the processes comprise executable code;
calculate, using the data tree structure, a frequency and a relationship between the nodes that includes determining whether a pair of nodes is related by determining whether a process corresponding to a first node of the pair calls a process corresponding to a second node of the pair;
generate, using the frequency and the relationship between the nodes, a compact tree representation model, the compact tree representation model including a matrix, wherein a first cell of the matrix associated with the pair of nodes indicates a number of times the process corresponding to the first node calls the process corresponding to the second node; and
process, using a machine learning technique, the compact tree representation model comprising a pattern identification.
2. The system of claim 1 , wherein executing the instructions further causes the system to:
input, into the system, the compact tree representation model, the compact tree representation model represented in a string format.
3. The system of claim 2 , wherein the string format includes digits representing each cell in the matrix.
4. The system of claim 1 , wherein the pattern identification includes a learned sequence from the processes running on the at least one secondary machine.
5. The system of claim 4 , wherein executing the instructions further causes the system to:
monitor one or more process sequences on the at least one secondary machine;
identify, based on the learned sequence, one or more errors; and
correct the one or more errors identified.
6. The system of claim 5 , wherein the one or more errors identified include an error in the learned sequence.
7. The system of claim 1 , wherein the compact tree representation model is used for the data tree structure and a second data tree structure.
8. A method comprising:
in response to determining that new data is available for processing, retrieving a data tree structure of the new data;
determining, from the new data, nodes on the data tree structure, the nodes corresponding to processes running on at least one secondary machine, wherein the processes comprise executable code;
calculating, using the data tree structure, a frequency and a relationship between the nodes that includes determining whether a pair of nodes is related by determining whether a process corresponding to a first node of the pair called a process corresponding to a second node of the pair;
generating, using the frequency and the relationship between the nodes, a compact tree representation model, the compact tree representation model including a matrix, wherein a first cell of the matrix associated with the pair of nodes indicates a number of times the process corresponding to the first node calls the process corresponding to the second node; and
processing, using a machine learning technique, the compact tree representation model comprising a pattern identification.
9. The method of claim 8 , further comprising:
inputting, into a machine learning model employing the machine learning technique, the compact representation tree model, the compact tree representation model represented in a string format.
10. The method of claim 9 , wherein the string format includes digits representing each cell in the matrix.
11. The method of claim 8 , wherein the pattern identification includes a learned sequence from the processes running on the at least one secondary machine.
12. The method of claim 11 , further comprising:
monitoring one or more process sequences on the at least one secondary machine;
identifying, based on the learned sequence, one or more errors; and
correcting the one or more errors identified.
13. The method of claim 12 , wherein the one or more errors identified include an error in the learned sequence.
14. The method of claim 9 , wherein the compact tree representation model is used for the data tree structure and a second data tree structure.
15. A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:
determining that new data is available for processing;
retrieving a data tree structure of the new data;
determining, from the new data, nodes on the data tree structure, the nodes corresponding to processes running on at least one secondary machine, wherein the processes comprise executable code;
calculating, using the data tree structure, a frequency and a relationship between the nodes comprising determining whether a pair of nodes is related by determining whether a process corresponding to a first node of the pair calls a process corresponding to a second node of the pair;
generating, using the frequency and the relationship between the nodes, a compact tree representation model, the compact tree representation model including a matrix, wherein a first cell of the matrix associated with the pair of nodes indicates a number of times the process corresponding to the first node calls the process corresponding to the second node; and
processing, using a machine learning technique, the compact tree representation model comprising a pattern identification.
16. The non-transitory medium of claim 15 , the operations further comprising:
inputting, into a machine learning model employing the machine learning technique, the compact representation tree model, the compact tree representation model represented in a string format.
17. The non-transitory medium of claim 16 , wherein the string format includes digits representing each cell in the matrix.
18. The non-transitory medium of claim 15 , wherein the pattern identification includes a learned sequence from the processes running on the at least one secondary machine.
19. The non-transitory medium of claim 18 , the operations further comprising:
monitoring one or more process sequences on the at least one secondary machine;
identifying, based on the learned sequence, one or more errors; and
correcting the one or more errors identified.
20. The non-transitory medium of claim 19 , wherein the one or more errors identified include an error in the learned sequence.