SYSTEM FOR IDENTIFYING AND ASSISTING IN THE CREATION AND IMPLEMENTATION OF A NETWORK SERVICE CONFIGURATION USING HIDDEN MARKOV MODELS (HMMs)

Abstract

A device may receive a request for a network service configuration (NSC) that is to be used to configure network devices. The device may select a graphical data model that has been trained via machine learning to analyze a dataset that includes information relating to a set of network configuration services, where aspects of a subset of the set of network configuration services have been created over time. The device may determine, by using the graphical data model, a path through a set of states of the graphical data model, where the path corresponds to a particular NSC. The device may select the particular NSC based on the path determined. The device may perform a first group of actions to provide data identifying the particular NSC for display, and/or a second group of actions to implement the particular NSC on the network devices.

What is claimed is: 
     
         1 . A method, comprising:
 selecting, by a device, a model, from a set of graphical data models, that is to be used to configure a set of network devices,
 wherein the model is selected based on one or more guidelines for one or more network service configurations; 
   determining, by the device and by using the model, a path through the model,
 wherein the path corresponds to a particular network service configuration of a set of candidate network service configurations; 
   selecting, by the device, the particular network service configuration, of the set of candidate network service configurations, based on the path determined using the model; and   performing, by the device, one or more actions based on selecting the particular network service configuration,
 wherein the one or more actions include at least one of:
 one or more actions to provide data identifying the particular network service configuration that is being recommended, or 
 one or more actions to implement the particular network service configuration on the set of network devices. 
 
   
     
     
         2 . The method of  claim 1 , wherein the particular network service configuration includes at least one of:
 a network service,   one or more network service features, or   a chain of network services.   
     
     
         3 . The method of  claim 1 , further comprising:
 receiving a request with parameter data;   locating an identifier of the model that was stored in association with identifiers that match parameter data of the request; and   wherein selecting the model comprises:
 selecting the model based on the parameter data included in the request. 
   
     
     
         4 . The method of  claim 1 , further comprising:
 using the model to determine likelihoods of network service features satisfying a service request made by a client organization.   
     
     
         5 . The method of  claim 1 , wherein determining the path through the model comprises:
 selecting a state of a set of states by referencing a set of state transition probabilities to select one or more additional states based on each additional state having a highest available state transition probability to determine the path.   
     
     
         6 . The method of  claim 1 , wherein the path includes one or more states,
 a first state, of the one or more states, being one or more of:
 a firewall service state, 
 an intrusion prevention system (IPS) service state, or 
 a data leak prevention (DLP) service state. 
   
     
     
         7 . The method of  claim 1 , further comprising:
 determining an overall confidence score that represents a likelihood of the particular network service configuration satisfying a request,
 the overall confidence score being based on a set of confidence scores that represent likelihoods of particular states in the path satisfying the request. 
   
     
     
         8 . A device, comprising:
 one or more memories; and   one or more processors to:
 select a Hidden Markov Model (HMM), from a set of graphical data models, that is to be used to configure a set of network devices,
 wherein the HMM model is selected based on one or more guidelines for one or more network service configurations; 
 
 determine, by using the HMM model, a path through the model,
 wherein the path corresponds to a particular network service configuration of a set of candidate network service configurations; 
 
 select the particular network service configuration, of the set of candidate network service configurations, based on the path determined using the HMM model; and 
 perform, by the device, one or more actions based on selecting the particular network service configuration,
 wherein the one or more actions include at least one of:
 one or more actions to provide data identifying the particular network service configuration that is being recommended, or 
 one or more actions to implement the particular network service configuration on the set of network devices. 
 
 
   
     
     
         9 . The device of  claim 8 , wherein the particular network service configuration includes at least one of:
 a network service,   one or more network service features, or   a chain of network services.   
     
     
         10 . The device of  claim 8 , wherein the one or more processors are further to:
 receive a request with parameter data;   locate an identifier of the HMM model that was stored in association with identifiers that match parameter data of the request, and   wherein the one or more processors, to select the HMM model, are to:
 select the HMM model based on the parameter data included in the request. 
   
     
     
         11 . The device of  claim 8 , wherein the one or more processors are further to:
 use the HMM model to determine likelihoods of network service features satisfying a service request made by a client organization.   
     
     
         12 . The device of  claim 8 , wherein the one or more processors, to determine the path through the HMM model, are to:
 select a state of a set of states by referencing a set of state transition probabilities to select one or more additional states based on each additional state having a highest available state transition probability to determine the path.   
     
     
         13 . The device of  claim 8 , wherein the one or more processors, to determine the path, are to:
 perform a Viterbi analysis to determine the path through a set of states,
 wherein the path represents a sequence of the set of states and is determined based on a given sequence of observations. 
   
     
     
         14 . The device of  claim 8 , wherein the one or more processors are further to:
 provide a user device with the data identifying the particular network service configuration that is being recommended.   
     
     
         15 . A non-transitory computer-readable medium storing instructions, the instructions comprising:
 one or more instructions that, when executed by one or more processors of a device, cause the one or more processors to:
 select a model, from a set of graphical data models, that is to be used to configure a set of network devices,
 wherein the model is selected based on one or more guidelines for one or more network service configurations; 
 
 determine, by using the model, a path through the model,
 wherein the path corresponds to a particular network service configuration of a set of candidate network service configurations; 
 
 select the particular network service configuration, of the set of candidate network service configurations, based on the path determined using the model; and 
 perform, one or more actions based on selecting the particular network service configuration,
 wherein the one or more actions include at least one of:
 one or more actions to provide data identifying the particular network service configuration that is being recommended, or 
 one or more actions to implement the particular network service configuration on the set of network devices. 
 
 
   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein the particular network service configuration includes at least one of:
 a network service,   one or more network service features, or   a chain of network services.   
     
     
         17 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
 receive a request with parameter data;   locate an identifier of the model that was stored in association with identifiers that match parameter data of the request; and   wherein the one or more instructions, that cause the one or more processors to select the model, cause the one or more processors to:
 select the model based on the parameter data included in the request. 
   
     
     
         18 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, when executed by the one or more processors, further cause the one or more processors to:
 use the model to determine likelihoods of network service features satisfying a service request made by a client organization.   
     
     
         19 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, that cause the one or more processors to determine the path through the model, cause the one or more processors to:
 select a state of a set of states by referencing a set of state transition probabilities to select one or more additional states based on each additional state having a highest available state transition probability to determine the path.   
     
     
         20 . The non-transitory computer-readable medium of  claim 15 , wherein the one or more instructions, that cause the one or more processors to select the particular network service configuration, cause the one or more processors to:
 select a chain of network services,
 wherein the chain of network services is an ordered combination of network services, and 
   select one or more network service features for at least one of the network services included in the chain.