Remote neural network processing for guideline identification

A computer program product for identifying guidelines using remote neural network processing, the computer program product comprising a non-transitory computer readable storage device having program instructions embodied therewith, the program instructions readable and executable by a computer to:

• transmit, from a client computer, instructions to a remote guideline server to retrieve and evaluate multiple candidate guidelines, wherein the instructions direct the remote guideline server to:
• identify and retrieve multiple candidate guidelines;
• identify, by use of a neural network, a string of terms found in each of the multiple candidate guidelines that match one or more strings of terms from a model guideline;
• identify, by use of the neural network, a semantic concept of each of the multiple candidate guidelines that matches one or more semantic concepts from the model guideline, wherein the semantic concept of each of the multiple candidate guidelines is based on the string of terms found in each of the multiple candidate guidelines;
• identify, by use of the neural network, a structural pattern of each of the multiple candidate guidelines that matches one or more structural patterns of the model guideline, wherein the structural pattern of each of the multiple candidate guidelines is based on the semantic concept of each of the multiple candidate guidelines and the string of terms found in each of the multiple candidate guidelines, wherein the model guideline is a text document that describes a set of tasks for solving a problem with a computer system, wherein the structural pattern is a structure of the text document that includes a compare-contrast structure in which the text document examines similarities and differences between two or more troubleshooting processes;
• a cause-effect structure in which the text document presents causal relationships between events described in the text document;
• a sequence structure in which the text document provides a sequential chronological description of steps to be taken in accordance with the model guideline;
• a problem-structure structure in which the text document presents the problem with the computer system, a solution to the problem, and an explanation of advantages and disadvantages of the solution;
• and a descriptive structure in which the text document presents a general description of the solution to the problem with the computer system in order to give the user a high-level understanding of the model guideline;
• compare, by use of the neural network, a combination of the string of terms, the semantic concept, and the structural pattern for each of the multiple candidate guidelines to the string of terms, the semantic concept, and the structural pattern of the model guideline;
• and
• identify, by use of the neural network, one or more of the multiple candidate guidelines whose string of terms, semantic concepts, and structural patterns match the string of terms, semantic concept, and structural pattern of the model guideline in order to identify one or more identified guidelines;
• receive, from a client computer, a request for one or more guidelines that have been identified by the remote guideline server;
• and
• transmit, to the client computer, the one or more identified guidelines from the remote guideline server.

A system comprising:

• one or more processors;
• one or more computer readable memories operably coupled to the one or more processors;
• one or more computer readable storage mediums operably coupled to the one or more computer readable memories;
• and
• program instructions stored on at least one of the one or more computer readable storage mediums for execution by at least one of the one or more processors via at least one of the one or more computer readable memories, the program instructions comprising:
• program instructions to transmit, from a client computer, instructions to a remote guideline server to retrieve and evaluate multiple candidate guidelines, wherein the instructions direct the remote guideline server to:
• identify and retrieve multiple candidate guidelines;
• identify, by use of a neural network, a string of terms found in each of the multiple candidate guidelines that match one or more strings of terms from a model guideline;
• identify, by use of the neural network, a semantic concept of each of the multiple candidate guidelines that matches one or more semantic concepts from the model guideline, wherein the semantic concept of each of the multiple candidate guidelines is based on the string of terms found in each of the multiple candidate guidelines;
• identify, by use of the neural network, a structural pattern of each of the multiple candidate guidelines that matches one or more structural patterns of the model guideline, wherein the structural pattern of each of the multiple candidate guidelines is based on the semantic concept of each of the multiple candidate guidelines and the string of terms found in each of the multiple candidate guidelines, wherein the model guideline is a text document that describes a set of tasks for solving a problem with a computer system, wherein the structural pattern is a structure of the text document that includes a compare-contrast structure in which the text document examines similarities and differences between two or more troubleshooting processes;
• a cause-effect structure in which the text document presents causal relationships between events described in the text document;
• a sequence structure in which the text document provides a sequential chronological description of steps to be taken in accordance with the model guideline;
• a problem-structure structure in which the text document presents the problem with the computer system, a solution to the problem, and an explanation of advantages and disadvantages of the solution;
• and a descriptive structure in which the text document presents a general description of the solution to the problem with the computer system in order to give the user a high-level understanding of the model guideline;
• compare, by use of the neural network, a combination of the string of terms, the semantic concept, and the structural pattern for each of the multiple candidate guidelines to the string of terms, the semantic concept, and the structural pattern of the model guideline;
• and
• identify, by use of the neural network, one or more of the multiple candidate guidelines whose string of terms, semantic concepts, and structural patterns match the string of terms, semantic concept, and structural pattern of the model guideline in order to identify one or more identified guidelines;
• program instructions to transmit, from the client computer to the remote guideline server, a request for one or more guidelines that have been identified by the remote guideline server;
• and
• program instructions to receive, by the client computer, the one or more identified guidelines from the remote guideline server.