Impact analyzer for a computer network

Abstract

Network management technology as disclosed herein performs an impact analysis of actual or hypothetical network commands, and presents the impact analysis results to facilitate the user's understanding of the predicted consequences of the actual or hypothetical commands on network operations, management, or security.

1 - 27 . (canceled) 
     
     
         28 . A method comprising:
 receiving, via a microphone, a signal comprising natural language input that relates to a computer network;   extracting, from the natural language input, a first network device identifier and a network action;   constructing a query that includes the first network device identifier and the network action;   executing the query on a stored network model that models behavior of the computer network to produce query results;   using the query results, computing a score that indicates a predicted impact, on a network device identified by a second network identifier, of executing the network action on the computer network;   mapping the score and the second network identifier to a template to produce a natural language response to the natural language input;   using the microphone, outputting computer-generated speech that corresponds to the natural language response;   wherein the method is performed by one or more computing devices.   
     
     
         29 . The method of  claim 28 , wherein the natural language input comprises speech, and the method comprises executing an automated speech recognition process on the natural language input using a stored language model that has been trained to convert speech containing words or phrases that are associated with computer network security to text. 
     
     
         30 . The method of  claim 28 , wherein the extracting comprises using a stored network security dialog model that has been trained to recognize network security key words or key phrases to extract the first network device identifier and the network action from the natural language input. 
     
     
         31 . The method of  claim 28 , wherein the constructing comprises executing a parser to create a parse tree that assigns semantics to portions of the natural language input including associating a user identifier with the natural language input. 
     
     
         32 . The method of  claim 28 , wherein computing the score comprises evaluating a criticality label associated with the network device identified by the second network identifier. 
     
     
         33 . The method of  claim 28 , wherein computing the score comprises evaluating a predicted count of network flows involving the network device identified by the second network identifier that would be blocked or redirected as a result of executing the network action on the computer network. 
     
     
         34 . The method of  claim 28 , wherein the stored network model comprises, for the computer network, data pertaining to any one or more of the following: a user name, a role, a geographic location, a business objective, an application, a layer of a network protocol stack and associations between the data and one or more network events. 
     
     
         35 . The method of  claim 28 , wherein the template comprises natural language text and one or more parameters. 
     
     
         36 . The method of  claim 28 , wherein the natural language response comprises a summary of an analysis that was used to compute the score. 
     
     
         37 . The method of  claim 28 , wherein the microphone is coupled to any one or more of the following: a smart phone, a display device, a wearable computing device, smart glasses, augmented reality goggles, virtual reality goggles, a tablet computer, a laptop computer, a desktop computer. 
     
     
         38 . One or more non-transitory computer-readable media having stored thereon a plurality of instructions, which, when executed by one or more processors, cause the one or more processors to perform operations comprising:
 receiving, via a microphone, a signal comprising natural language input that relates to a computer network;   extracting, from the natural language input, a first network device identifier and a network action;   constructing a query that includes the first network device identifier and the network action;   executing the query on a stored network model that models behavior of the computer network to produce query results;   using the query results, computing a score that indicates a predicted impact, on a network device identified by a second network identifier, of executing the network action on the computer network;   mapping the score and the second network identifier to a template to produce a natural language response to the natural language input;   using the microphone, outputting computer-generated speech that corresponds to the natural language response;   wherein the method is performed by one or more computing devices.   
     
     
         39 . The one or more non-transitory computer-readable media of  claim 38 , wherein the natural language input comprises speech, and the instructions are configured to cause the one or more processors to perform operations comprising executing an automated speech recognition process on the natural language input using a stored language model that has been trained to convert speech containing words or phrases that are associated with computer network security to text. 
     
     
         40 . The one or more non-transitory computer-readable media of  claim 38 , wherein the extracting comprises using a stored network security dialog model that has been trained to recognize network security key words or key phrases to extract the first network device identifier and the network action from the natural language input. 
     
     
         41 . The one or more non-transitory computer-readable media of  claim 38 , wherein the constructing comprises executing a parser to create a parse tree that assigns semantics to portions of the natural language input including associating a user identifier with the natural language input. 
     
     
         42 . The one or more non-transitory computer-readable media of  claim 38 , wherein computing the score comprises evaluating a criticality label associated with the network device identified by the second network identifier. 
     
     
         43 . The one or more non-transitory computer-readable media of  claim 38 , wherein computing the score comprises evaluating a predicted count of network flows involving the network device identified by the second network identifier that would be blocked or redirected as a result of executing the network action on the computer network. 
     
     
         44 . The one or more non-transitory computer-readable media of  claim 38 , wherein the stored network model comprises, for the computer network, data pertaining to any one or more of the following: a user name, a role, a geographic location, a business objective, an application, a layer of a network protocol stack and associations between the data and one or more network events. 
     
     
         45 . The one or more non-transitory computer-readable media of  claim 38 , wherein the template comprises natural language text and one or more parameters. 
     
     
         46 . The one or more non-transitory computer-readable media of  claim 38 , wherein the natural language response comprises a summary of an analysis that was used to compute the score. 
     
     
         47 . The one or more non-transitory computer-readable media of  claim 38 , wherein the microphone is coupled to any one or more of the following: a smart phone, a display device, a wearable computing device, smart glasses, augmented reality goggles, virtual reality goggles, a tablet computer, a laptop computer, a desktop computer.