Correlating causes and effects associated with network activity
Embodiments are directed to monitoring network traffic using a monitoring engine that monitors network traffic in networks to provide metrics. An inference engine may provide activity profiles based on portions of the network traffic where each activity profile includes features associated with the portions of network traffic. The inference engine may determine other activity profiles correlated with the activity profiles based on correlation models such that the determination of the other activity profiles occurs prior to monitoring an occurrence of other portions of the network traffic. The inference engine may modify monitoring actions of the monitoring engine based on the other activity profiles. The inference engine may provide reports based on the portions of the network traffic, the activity profiles, the other portions of the network traffic, or the other activity profiles.
1. A method for monitoring network traffic over one or more networks using one or more network computers, wherein execution of instructions by the one or more network computers perform the method comprising:
providing one or more metrics based on network traffic that is associated with a plurality of entities in one or more portions of the one or more networks based on one or more device relation models;
providing one or more activity profiles for the one or more portions of the network traffic;
determining one or more other activity profiles that correlate to the one or more activity profiles based on one or more correlation models;
providing one or more other metrics associated with other entities in one or more other portions of the network traffic based on the one or more device relation models, wherein one or more scores for the one or more correlation models are determined based on the one or more other portions of network traffic occurring subsequent to the one or more portions of the network traffic;
re-training each correlation model based on a corresponding determined score having a value below a threshold; and
providing one or more reports to one or more users.
2. The method of claim 1 , further comprising:
employing one or more requests that include one or more parameters to select network traffic that is associated with the one or more activity profiles.
3. The method of claim 1 , further comprising:
employing one or more features of the one or more activity profiles and one or more activity profile histories to generate the one or more correlation models; and
employing the one or more correlation models to determine one or more correlations between one or more portions of the one or more activity profiles or the one or more other activity profiles.
4. The method of claim 1 , further comprising:
monitoring performance of each of the one or more correlation models to provide one or more correlations between the one or more activity profiles and the one or more other activity profiles; and
deactivating each of the one or more correlation models associated with each determined score having a value below the threshold.
5. The method of claim 1 , further comprising:
Periodically retraining each of the one or more correlation models based on one or more of a score, a priority, or a category.
6. The method of claim 1 , further comprising:
monitoring the one or more other portions of the network traffic based on the one or more other activity profiles; and
determining the one or more other activity profiles separate from the monitoring of the one or more other portions of the network traffic.
7. The method of claim 1 , further comprising:
providing one or more weights to one or more correlations determined between one or more portions of the one or more activity profiles and the one or more other activity profiles, wherein the one or more weights are based on an importance of the one or more correlations to the one or more users.
8. A system for monitoring network traffic over one or more networks, comprising:
one or more network computers, including:
a memory that stores at least instructions; and
one or more processors that execute instructions that enable performance of actions, comprising:
providing one or more metrics based on network traffic that is associated with a plurality of entities in one or more portions of the one or more networks based on one or more device relation models;
providing one or more activity profiles for the one or more portions of the network traffic;
determining one or more other activity profiles that correlate to the one or more activity profiles based on one or more correlation models;
providing one or more other metrics associated with other entities in one or more other portions of the network traffic based on the one or more device relation models, wherein one or more scores for the one or more correlation models are determined based on the one or more other portions of network traffic occurring subsequent to the one or more portions of the network traffic;
re-training each correlation model based on a corresponding determined score having a value below a threshold; and
providing one or more reports to one or more users.
9. The system of claim 8 , further comprising:
employing one or more requests that include one or more parameters to select network traffic that is associated with the one or more activity profiles.
10. The system of claim 8 , further comprising:
employing one or more features of the one or more activity profiles and one or more activity profile histories to generate the one or more correlation models; and
employing the one or more correlation models to determine one or more correlations between one or more portions of the one or more activity profiles or the one or more other activity profiles.
11. The system of claim 8 , further comprising:
monitoring performance of each of the one or more correlation models to provide one or more correlations between the one or more activity profiles and the one or more other activity profiles; and
deactivating each of the one or more correlation models associated with each determined score having a value below the threshold.
12. The system of claim 8 , further comprising:
periodically retraining each of the one or more correlation models based on one or more of a score, a priority, or a category.
13. The system of claim 8 , further comprising:
monitoring the one or more other portions of the network traffic based on the one or more other activity profiles; and
determining the one or more other activity profiles separate from the monitoring of the one or more other portions of the network traffic.
14. The system of claim 8 , further comprising:
providing one or more weights to one or more correlations determined between one or more portions of the one or more activity profiles and the one or more other activity profiles, wherein the one or more weights are based on an importance of the one or more correlations to the one or more users.
15. A processor readable non-transitory storage media that includes instructions for monitoring network traffic over a network using one or more network monitoring computers, wherein execution of the instructions by one or more processors of the one or more network computers performs actions comprising:
providing one or more metrics based on network traffic that is associated with a plurality of entities in one or more portions of the one or more networks based on one or more device relation models;
providing one or more activity profiles for the one or more portions of the network traffic;
determining one or more other activity profiles that correlate to the one or more activity profiles based on one or more correlation models;
providing one or more other metrics associated with other entities in one or more other portions of the network traffic based on the one or more device relation models, wherein one or more scores for the one or more correlation models are determined based on the one or more other portions of network traffic occurring subsequent to the one or more portions of the network traffic;
re-training each correlation model based on a corresponding determined score having a value below a threshold; and
providing one or more reports to one or more users.
16. The processor readable non-transitory storage media of claim 15 , wherein execution of the instructions by one or more processors of the one or more network computers performs further actions comprising:
employing one or more requests that include one or more parameters to select network traffic that is associated with the one or more activity profiles.
17. The processor readable non-transitory storage media of claim 15 , wherein execution of the instructions by one or more processors of the one or more network computers performs further actions comprising:
employing one or more features of the one or more activity profiles and one or more activity profile histories to generate the one or more correlation models; and
employing the one or more correlation models to determine one or more correlations between one or more portions of the one or more activity profiles or the one or more other activity profiles.
18. The processor readable non-transitory storage media of claim 15 , wherein execution of the instructions by one or more processors of the one or more network computers performs further actions comprising:
monitoring performance of each of the one or more correlation models to provide one or more correlations between the one or more activity profiles and the one or more other activity profiles; and
deactivating each of the one or more correlation models associated with each determined score having a value below the threshold.
19. The processor readable non-transitory storage media of claim 15 , wherein execution of the instructions by one or more processors of the one or more network computers performs further actions comprising:
periodically retraining each of the one or more correlation models based on one or more of a score, a priority, or a category.
20. The processor readable non-transitory storage media of claim 15 , wherein execution of the instructions by one or more processors of the one or more network computers performs further actions comprising:
monitoring the one or more other portions of the network traffic based on the one or more other activity profiles; and
determining the one or more other activity profiles separate from the monitoring of the one or more other portions of the network traffic.