Multi-dimensional impact detect and diagnosis in cellular networks

Abstract

A method for multi-dimensional impact detection and diagnosis of networks. The methods and systems dynamically explore only those network feature combinations that are likely to have problems by using a summary structure Sketch, for example. The method and systems capture fine-grained anomalies at a coarse level which allows for on-demand zoom into the finer-grained levels for further analysis.

What is claimed: 
     
         1 . An apparatus comprising:
 a processor; and   memory coupled with the processor, the memory storing executable instructions that when executed by the processor cause the processor to effectuate operations comprising:
 obtaining one or more records; 
 generating a lattice based on the one more records; 
 analyzing a plurality of nodes of the lattice for anomalies; 
 determining an anomalous node of the plurality of nodes, wherein the anomalous node have anomalous performance; 
 determining a root cause of the anomalous node having anomalous performance, wherein the root cause comprises one or more features; and 
 providing an indication of the root cause of the anomalous performance for the anomalous node. 
   
     
     
         2 . The apparatus of  claim 1 , the operations further comprising in response to the indication of the root cause, sending instructions to set a lower threshold for use of the one or more features. 
     
     
         3 . The apparatus of  claim 1 , the operations further comprising in response to the indication of the root cause, sending instructions to not allow devices to operate in a network that include the one or more features. 
     
     
         4 . The apparatus of  claim 1 , wherein the one or more features comprises a software version. 
     
     
         5 . The apparatus of  claim 1 , wherein the one or more features comprises handover associated information. 
     
     
         6 . The apparatus of  claim 1 , wherein the one or more features comprises a hardware version. 
     
     
         7 . The apparatus of  claim 1 , wherein the one or more features comprises a location-centric features. 
     
     
         8 . The apparatus of  claim 1 , wherein the determining the root cause is based on a compressive sensing method. 
     
     
         9 . The apparatus of  claim 1 , wherein the determining the root cause is based on a neural network method. 
     
     
         10 . A method comprising:
 obtaining one or more records;   generating a lattice based on the one more records;   analyzing a plurality of nodes of the lattice for anomalies;   determining an anomalous node of the plurality of nodes, wherein the anomalous node have anomalous performance;   determining a root cause of the anomalous node having anomalous performance, wherein the root cause comprises one or more features; and   providing an indication of the root cause of the anomalous performance for the anomalous node.   
     
     
         11 . The method of  claim 10 , further comprising in response to the indication of the root cause, sending instructions to set a lower threshold for use of the one or more features. 
     
     
         12 . The method of  claim 10 , further comprising in response to the indication of the root cause, sending instructions to not allow devices to operate in a network that include the one or more features. 
     
     
         13 . The method of  claim 10 , wherein the one or more features comprises a software version. 
     
     
         14 . The method of  claim 10 , wherein the one or more features comprises handover associated information. 
     
     
         15 . The method of  claim 10 , wherein the one or more features comprises a hardware version. 
     
     
         16 . The method of  claim 10 , wherein the one or more features comprises a location-centric features. 
     
     
         17 . The method of  claim 10 , wherein the determining the root cause is based on a compressive sensing method. 
     
     
         18 . The method of  claim 10 , wherein the determining the root cause is based on a neural network method. 
     
     
         19 . A system comprising:
 one or more processors; and   memory coupled with the one or more processors, the memory storing executable instructions that when executed by the one or more processors cause the one or more processors to effectuate operations comprising:
 obtaining one or more records associated with one or more properties; 
 generating a lattice based on the one more records; 
 analyzing a plurality of nodes of the lattice for anomalies; 
 determining an anomalous node of the plurality of nodes, wherein the anomalous node have anomalous performance; 
 determining a root cause of the anomalous node having anomalous performance, wherein the root cause comprises one or more features; and 
 providing an indication of the root cause of the anomalous performance for the anomalous node. 
   
     
     
         20 . The system of  claim 19 , the operations further comprising in response to the indication of the root cause, sending instructions to set a lower threshold for use of the one or more features.