Automated troubleshooter

Abstract

The technology described herein generates automated workflows from trouble shooting guides. The automated workflow generation process described herein starts with existing TSGs as the input. A first step in the process may be identifying the computer commands in the TSG. In one aspect, the commands are identified using a sequence-to-sequence model. Once a command is identified as a command, the command is associated with an application of origin. In aspects, a second model is used to identify the application associated with the command. The second model may be a metric-based meta-learning approach to associate a command with an application. Once the commands are identified and associated with an application, they may be parsed or extracted using a regular expression, which is a special text string describing a search pattern. The structure of the natural text is then parsed to build an executable decision tree and merged with the parsed commands.

What is claimed is: 
     
         1 . One or more computer storage media comprising computer-executable instructions that when executed by a computing device cause the computing device to perform a method of generating an automated troubleshooting guide (TSG), comprising:
 identifying a starting point and an ending point for a computer command in a troubleshooting guide (TSG);   classifying, with a metric-learning machine classifier, the computer command as belonging to a first application;   extracting sub-components of the computer command with a regular expression that is specific to the first application;   building a structured collection of steps associated with troubleshooting a single problem, the structured collection built from the computer command and a natural language text adjacent to the computer command within the TSG; and   converting the structured collection of steps into an automated workflow configured to troubleshoot the single problem when executed by a computing system.   
     
     
         2 . The media of  claim 1 , wherein the classifying, with the metric-learning machine classifier, the computer command as belonging to the first application, further comprises:
 inputting the computer command to a neural network;   receiving a first representation of the computer command from the neural network; and   determining from a distance metric that the first representation is most similar to a second representation of a command belonging to the first application.   
     
     
         3 . The media of  claim 2 , wherein the neural network is a twin neural network. 
     
     
         4 . The media of  claim 2 , wherein the distance metric is generated using a Manhattan distance measure. 
     
     
         5 . The media of  claim 1 , further comprising translating conditional natural language statements within the natural language text into logical structures with program synthesis. 
     
     
         6 . The media of  claim 1 , wherein the sub-components are selected from a group consisting of commands, arguments, parameters, and attributes. 
     
     
         7 . The media of  claim 1 , wherein the regular expression is generated using programming by example. 
     
     
         8 . A computer-implemented method of generating an automated troubleshooting guide (TSG), comprising:
 identifying a starting point and an ending point for a computer command in a troubleshooting guide (TSG) using a sequence-to-sequence based model;   classifying the computer command as belonging to a first application;   extracting sub-components of the computer command with a regular expression that is specific to the first application;   translating conditional natural language statements within a natural language text, which is adjacent to the computer command within the TSG, into logical structures with a first program synthesis;   building from the natural language text and the computer command a structured collection of steps associated with troubleshooting a single problem; and   converting the structured collection of steps into an automated workflow configured to troubleshoot the single problem when executed by a computing system.   
     
     
         9 . The method of  claim 8 , wherein the classifying is with a metric-learning machine classifier and further comprises:
 inputting the computer command to a neural network;   receiving a first representation of the computer command from the neural network; and   determining from a distance metric that the first representation is most similar to a second representation of a command belonging to the first application.   
     
     
         10 . The method of  claim 9 , wherein the neural network is a twin neural network. 
     
     
         11 . The method of  claim 9 , wherein a trained embedding layer from the neural network is used with the sequence-to-sequence based model. 
     
     
         12 . The method of  claim 11 , wherein the trained embedding layer is tuned during training of the sequence-to-sequence based model. 
     
     
         13 . The method of  claim 8 , further comprising, without human intervention, troubleshooting an occurrence of the single problem with the automated workflow. 
     
     
         14 . The method of  claim 8 , wherein a depth-first search is used to build the structured collection of steps. 
     
     
         15 . The method of  claim 8 , wherein the method further comprises generating the regular expression through a second program synthesis. 
     
     
         16 . A system comprising:
 one or more processors; and   one or more computer storage media storing computer-useable instructions that, when used by the one or more processors, cause the one or more processors to perform a method, the method comprising:   identifying, with a first machine-learning model, a computer command in a troubleshooting guide (TSG), the first machine-learning model comprising an embedding layer initiated with values from a trained embedding layer from a second machine-learning model;   classifying, with the second machine-learning model, the computer command as belonging to a first application;   extracting sub-components of the computer command with a regular expression that is specific to the first application;   building a structured collection of steps associated with troubleshooting a single problem, the structured collection of steps built from the computer command and a natural language text adjacent to the computer command within the TSG;   converting the structured collection of steps into an automated workflow configured to troubleshoot the single problem when executed by a computing system; and   without human intervention, troubleshooting an occurrence of the single problem with the automated workflow.   
     
     
         17 . The system of  claim 16 , wherein the first machine-learning model is a sequence-to-sequence based model. 
     
     
         18 . The system of  claim 16 , wherein a depth-first search is used to build the structured collection of steps. 
     
     
         19 . The system of  claim 16 , wherein the second machine-learning model is a metric-learning machine classifier. 
     
     
         20 . The system of  claim 19 , wherein the classifying with the second machine-learning model further comprises:
 inputting the computer command to a neural network;   receiving a first representation of the computer command from the neural network; and   determining from a distance metric that the first representation is most similar to a second representation of a command belonging to the first application.