Cognitive manufacturing systems test repair action

A system for generating test plans based on test failure root causes or symptoms, the system comprising one or more processors configured to perform a method comprising:

• generating, by the system, a heat map of manufacturing process test failures based at least in part on historical test failures and prior repair actions, wherein the heat map is presented to a user via a GUI;
• receiving, by the system, a user input via the GUI regarding a test failure of a manufacturing process, wherein the user input includes structured and unstructured data;
• searching, by the system, a database for test failure records that are relevant to the user input and prioritizing the relevant test failure records via an index score based at least in part on proximity of the relevant test failure records to the user input;
• detecting, by the system, failure records from the search having an index score that is higher than a threshold value;
• analyzing, by a machine learning engine executing on the system, unstructured text data of each of the detected failure records to identify relevant keywords and respective relevancy rates, the machine learning engine previously trained to input a failure record and to output relevant keywords and respective relevancy rates of the failure record;
• generating, by the system, a test solution priority list comprising one or more suggested test repair actions for the test failure based at least in part on the relevant keywords and the relevancy rates;
• and
• outputting, by the system, the test solution priority list to the user by at least displaying, by the system via the GUI, the one or more suggested test repair actions in a window that is separate from the heat map.

A computer program product for generating test plans based on test failure root causes or symptoms, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, wherein the computer readable storage medium is not a transitory signal per se, the program instructions executable by a system comprising one or more processors to cause the system to perform a method comprising:

• generating, by the system, a heat map of manufacturing process test failures based at least in part on historical test failures and prior repair actions, wherein the heat map is presented to a user via a GUI;
• receiving, by the system, a user input via the GUI regarding a test failure of a manufacturing process, wherein the user input includes structured and unstructured data;
• searching, by the system, a database for test failure records that are relevant to the user input and prioritizing the relevant test failure records via an index score based at least in part on proximity of the relevant test failure records to the user input;
• detecting, by the system, failure records from the search having an index score that is higher than a threshold value;
• analyzing, by a machine learning engine executing by the system, unstructured text data of each of the detected failure records to identify relevant keywords and respective relevancy rates, the machine learning engine previously trained to input a failure record and to output relevant keywords and respective relevancy rates of the failure record;
• generating, by the system, a test solution priority list comprising one or more suggested test repair actions for the test failure based at least in part on the relevant keywords and the relevancy rates;
• and
• outputting, by the system, the test solution priority list to the user by at least displaying, by the system via the GUI, the one or more suggested test repair actions in a window that is separate from the heat map.