Automated method of identifying troubleshooting and system repair instructions using complementary machine learning models
US-11294755-B2 · Apr 5, 2022 · US
US11403165B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11403165-B2 |
| Application number | US-202016861364-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 29, 2020 |
| Priority date | Apr 29, 2020 |
| Publication date | Aug 2, 2022 |
| Grant date | Aug 2, 2022 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
Generating a new disaster recovery workflow is provided. In response to determining that a failed action was detected during execution of a disaster recovery workflow, reasons and fixes corresponding to the failed action are acquired from a data source. A set of correlated corrective actions that are potential fixes for the failed action is identified based on natural language processing of the reasons and fixes corresponding to the failed action. A weightage value is assigned to each correlated corrective action in the set of correlated corrective actions based on a plurality of factors to form a set of corrective actions with weightage values. A recommended new disaster recovery workflow is generated by embedding the set of corrective actions with weightage values within the disaster recovery workflow.
Opening claim text (preview).
What is claimed is: 1. A computer-implemented method for generating a new disaster recovery workflow, the computer-implemented method comprising: responsive to a computer determining that a failed action was detected during execution of a disaster recovery workflow, acquiring, by the computer, reasons and fixes corresponding to the failed action from a data source; identifying, by the computer, a set of correlated corrective actions that are potential fixes for the failed action based on natural language processing of the reasons and fixes corresponding to the failed action; assigning, by the computer, a weightage value to each correlated corrective action in the set of correlated corrective actions based on a plurality of factors to form a set of corrective actions with weightage values, wherein the plurality of factors includes a number of times a particular corrective action was used previously, a time when the particular corrective action was last used, and whether the particular corrective action was used on a same data processing environment or not; and generating, by the computer, a recommended new disaster recovery workflow by embedding the set of corrective actions with weightage values within the disaster recovery workflow. 2. The computer-implemented method of claim 1 further comprising: presenting, by the computer, the recommended new disaster recovery workflow having an embedded set of corrective actions with weightage values in a user interface for review by a user; and receiving, by the computer, a selection of a corrective action within the embedded set of corrective actions in the user interface by the user. 3. The computer-implemented method of claim 2 further comprising: generating, by the computer, the new disaster recovery workflow based on the corrective action selected by the user; and executing, by the computer, the new disaster recovery workflow. 4. The computer-implemented method of claim 1 further comprising: building, by the computer, a knowledgebase from historical data of disaster recovery workflow executions; and analyzing, by the computer, historical data in the knowledgebase corresponding to failed disaster recovery workflow executions to generate the recommended new disaster recovery workflow with an embedded set of corrective actions and corresponding weightage values to increase a success rate of disaster recovery workflow execution. 5. The computer-implemented method of claim 4 , wherein the knowledgebase includes an action library of all available workflow actions, a correlation mapping of previously failed actions mapped to potential corrective actions, and a weightage store of weightage values assigned to each corrective action. 6. The computer-implemented method of claim 1 , wherein the disaster recovery workflow is a sequence of multiple actions configured to execute a disaster recovery process, and wherein an action is an operation in the disaster recovery workflow. 7. The computer-implemented method of claim 1 , wherein the reasons and fixes corresponding to the failed action obtained from the data source are in free form text, and further comprising: preprocessing, by the computer, the free form text to clean and remove noise to form preprocessed reasons and fixes corresponding to the failed action. 8. The computer-implemented method of claim 1 , wherein the data source is at least one of an internal data source and an external data source, and wherein the internal data source includes a ticketing system and user input, and wherein the external data source includes troubleshooting services and troubleshooting documentation. 9. The computer-implemented method of claim 1 , wherein the computer embeds the set of corrective actions with weightage values adjacent to the failed action within the disaster recovery workflow. 10. A computer system for generating a new disaster recovery workflow, the computer system comprising: a bus system; a storage device connected to the bus system, wherein the storage device stores program instructions; and a processor connected to the bus system, wherein the processor executes the program instructions to: acquire reasons and fixes corresponding to a failed action from a data source in response to determining that the failed action was detected during execution of a disaster recovery workflow; identify a set of correlated corrective actions that are potential fixes for the failed action based on natural language processing of the reasons and fixes corresponding to the failed action; assign a weightage value to each correlated corrective action in the set of correlated corrective actions based on a plurality of factors to form a set of corrective actions with weightage values, wherein the plurality of factors includes a number of times a particular corrective action was used previously, a time when the particular corrective action was last used, and whether the particular corrective action was used on a same data processing environment or not; and generate a recommended new disaster recovery workflow by embedding the set of corrective actions with weightage values within the disaster recovery workflow. 11. The computer system of claim 10 , wherein the processor further executes the program instructions to: present the recommended new disaster recovery workflow having an embedded set of corrective actions with weightage values in a user interface for review by a user; and receive a selection of a corrective action within the embedded set of corrective actions in the user interface by the user. 12. The computer system of claim 11 , wherein the processor further executes the program instructions to: generate the new disaster recovery workflow based on the corrective action selected by the user; and execute the new disaster recovery workflow. 13. The computer system of claim 10 , wherein the processor further executes the program instructions to: build a knowledgebase from historical data of disaster recovery workflow executions; and analyze historical data in the knowledgebase corresponding to failed disaster recovery workflow executions to generate the recommended new disaster recovery workflow with an embedded set of corrective actions and corresponding weightage values to increase a success rate of disaster recovery workflow execution. 14. The computer system of claim 13 , wherein the knowledgebase includes an action library of all available workflow actions, a correlation mapping of previously failed actions mapped to potential corrective actions, and a weightage store of weightage values assigned to each corrective action. 15. A computer program product for generating a new disaster recovery workflow, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform a method comprising: responsive to the computer determining that a failed action was detected during execution of a disaster recovery workflow, acquiring, by the computer, reasons and fixes corresponding to the failed action a data source; identifying, by the computer, a set of correlated corrective actions that are potential fixes for the failed action based on natural language processing of the reasons and fixes corresponding to the failed action; assigning, by the computer, a weightage value to each correlated corrective action in the set of correlated corrective actions based on a plurality of factors to form a set of corrective actions with weightage values, wherein the plurality of factors includes a numb
Remedial or corrective actions (recovery from an exception in an instruction pipeline G06F9/3861; by retry G06F11/1402; for recovering from a failure of a protocol instance or entity H04L69/40) · CPC title
Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title
Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title
Natural language analysis (semantic analysis of natural language G06F40/30) · CPC title
Storage of error reports, e.g. persistent data storage, storage using memory protection · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.