Computer network troubleshooting

Patent metadata

Field	Value
Publication number	US-11206196-B2
Application number	US-202016895621-A
Country	US
Kind code	B2
Filing date	Jun 8, 2020
Priority date	Mar 8, 2018
Publication date	Dec 21, 2021
Grant date	Dec 21, 2021

Abstract

A system for troubleshooting network problems is disclosed. A model can use demographic information, network usage information, and network membership information to determine an importance of a problem. The importance of the problem for the user who reported the problem, a number of other users affected by the problem, and the importance of the problem to the other users can be used to determine a priority for resolving the problem. Before and after a work order is executed to resolve the problem, network metrics can be gathered, including aggregate network metrics, and automatically presented in various user interfaces. The analysis of the metrics can be used to update a database of which work orders are assigned in response to which problems.

First claim

What is claimed is:

1. A computer system comprising:
one or more computer processors configured to execute computer executable instructions to cause the computer system to:
receive a reported problem about a connection to a network of a first computer device;
determine a node in the network with a connection to the first computer device;
create at least a first work order based on one or more actions to be taken for the node;
determine a quantity of other users associated with the node and thereby potentially impacted by the one or more actions to be taken for the node;
calculate a first priority score based at least in part on the quantity of other users; and
cause the first work order to be executed based at least in part on the first priority score.

2. The computer system of claim 1 , wherein the computer executable instructions are further configured to cause the computer system to:
train a model to generate importance scores for aspects of network connections based on at least demographics data for users of the network and network usage data for the users of the network.

3. The computer system of claim 2 , wherein the computer executable instructions are further configured to cause the computer system to:
use the model to determine an importance score for the reported problem to a first user of the first computer device; and
assign the first priority score to the first work order based at least in part on the importance score.

4. The computer system of claim 2 , wherein the computer executable instructions are further configured to cause the computer system to:
use the model to determine a plurality of importance scores for the reported problem to the other users; and
assign the first priority score to the first work order based at least in part on the plurality of importance scores.

5. The computer system of claim 2 , wherein the model is a random forest model configured to assign a higher importance score when input factors are similar to historical variables correlated with network quality.

6. The computer system of claim 2 , wherein the model is trained to generate the importance score further based at least in part on network membership data.

7. The computer system of claim 1 , wherein the computer executable instructions are further configured to cause the computer system to:
collect first performance metrics for the node before the first work order is executed;
collect second performance metrics for the node after the first work order is executed; and
transmit a report for the node providing a comparison of performance metrics before and after the first work order is executed, wherein the comparison of performance metrics is based at least in part on the first performance metrics and the second performance metrics.

8. The computer system of claim 1 , wherein the computer executable instructions are further configured to cause the computer system to:
collect first performance metrics for a second node before the first work order is executed, wherein the second node is a neighboring node to the first node;
collect first performance metrics for a second node after the first work order is executed; and
transmit a report for the second node including a comparison of performance metrics before and after the first work order is executed, wherein the comparison of performance metrics is based at least in part on the first performance metrics and the second performance metrics.

9. The computer system of claim 8 , wherein the first work order does not include troubleshooting the second node.

10. The computer system of claim 1 , wherein the computer executable instructions are further configured to cause the computer system to:
change the first work order that is assigned in response to the reported problem.

11. A method for troubleshooting networks, the method comprising:
by one or more computer processors executing computer executable instructions:
receiving a reported problem about a connection to a network of a first computer device;
determining a node in the network with a connection to the first computer device;
creating at least a first work order based on one or more actions to be taken for the node;
determining a quantity of other users associated with the node and thereby potentially impacted by the one or more actions to be taken for the node;
calculating a first priority score based at least in part on the quantity of other users; and
causing the first work order to be executed based at least in part on the first priority score.

12. The method of claim 11 , further comprising:
by the one or more computer processors executing computer executable instructions:
training a model to generate importance scores for aspects of users' network connections based on at least demographics data for users of the network and network usage data for the users of the network.

13. The method of claim 12 , further comprising:
by the one or more computer processors executing computer executable instructions:
using the model to determine an importance score for the reported problem to the first user; and
assigning the first priority score to the first work order based at least in part on the importance score.

14. The method of claim 12 , further comprising:
by the one or more computer processors executing computer executable instructions:
using the model to determine a plurality of importance scores for the reported problem to the other users; and
assigning the first priority score to the first work order based at least in part on the plurality of importance scores.

15. The method of claim 12 , wherein the model is a random forest model configured to assign a higher importance score when input factors are similar to historical variables correlated with network quality.

16. The method of claim 12 , wherein the model is trained to generate the importance score further based at least in part on network membership data.

17. The method of claim 11 , further comprising:
by the one or more computer processors executing computer executable instructions:
collecting first performance metrics for the node before the first work order is executed;
collecting second performance metrics for the node after the first work order is executed; and
transmitting a report for the node providing a comparison of performance metrics before and after the first work order is executed, wherein the comparison of performance metrics is based at least in part on the first performance metrics and the second performance metrics.

18. The method of claim 11 , further comprising:
by the one or more computer processors executing computer executable instructions:
collecting first performance metrics for a second node before the first work order is executed, wherein the second node is a neighboring node to the first node;
collecting first performance metrics for a second node after the first work order is executed; and
transmitting a report for the second node including a comparison of performance metrics before and after the first work order is executed, wherein the comparison of performance metrics is based at least in part on the first performance metrics and the second performance metrics.

19. The method of claim 18 , wherein the first work order does not include troubleshooting the second node.

20. The method of claim 11 , further comprising:
by the one or more computer processors executing computer executable instructions:
changing the first work order that is assigned in response to

Assignees

• Palantir Technologies Inc

Inventors

• Mathur Arjun
• Ash Andrew
• Bahl Anuraag
• Chen Andy
• Keskin Aydin
• Rogers Christopher
• Prasad Anshuman
• Shankar Ankit
• Patton Casey
• Wynnyk Christopher
• Peller Joanna
• Victor Jonathan
• Bohannon Mackenzie
• Skiles Mitchell
• Taneja Nikhil
• Norris Ryan
• Adams Scott
• Sinensky Samuel
• Vempati Sri Krishna
• Mathew Thomas
• Ganesh Vinoo
• Ramsharan Rahij

Classifications

• H04L41/5074 Primary

  Handling of user complaints or trouble tickets · CPC title

• H04L41/0876 Primary

  Aspects of the degree of configuration automation · CPC title

• G06F18/24323

  Tree-organised classifiers · CPC title

• H04L41/147

  for predicting network behaviour · CPC title

• H04L41/5067

  Customer-centric QoS measurements · CPC title