# US 2019/0377789 A1 · System and method for identifying correlated operator action events based on text analytics of operator actions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0377789 A1 - Document ID: US20190377789A1 - Status: Published application - Kind: A1 - Application number: 16/002,812 - Filed: 2018-06-07 - Published: 2019-12-12 - Earliest claimed: 2018-06-07 - Assignees: Honeywell International Inc. - Applicants: Honeywell International Inc. - Inventors: Nadesh Kumar Jegannathan; Suresh Daniel - Web page: https://patentgrep.com/patent/US20190377789A1 ## CPC - G06F 40/295: Named entity recognition - G06F 40/253: Grammatical analysis; Style critique - G06F 40/268: Morphological analysis - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F 40/30: Semantic analysis - G05B 23/0208: {characterized by the configuration of the monitoring system} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## Abstract A method includes obtaining, from an event log, first text of an alarm associated with an industrial process in a process control system, and processing the first text to obtain first key terms. The method also includes obtaining, from the event log, second text of an operator response, and processing the second text to obtain second key terms. The method further includes filtering and segmenting at least one of the first key terms and the second key terms. The method also includes performing text matching on the first key terms and the second key terms to identify a correlation between the first text and the second text. In addition, the method includes storing the first text, the second text, and the correlation between the first text and the second text in a data store. ## Claims ### Claim 1 A method comprising: obtaining, from an event log, first text of an alarm associated with an industrial process in a process control system, and processing the first text to obtain first key terms; obtaining, from the event log, second text of an operator response, and processing the second text to obtain second key terms; filtering and segmenting at least one of the first key terms and the second key terms; performing text matching on the first key terms and the second key terms to identify a correlation between the first text and the second text; and storing the first text, the second text, and the correlation between the first text and the second text in a data store. ### Claim 2 (depends on 1) The method of claim 1, wherein the event log is populated with events, alarms, and operator responses associated with the industrial process over time. ### Claim 3 (depends on 1) The method of claim 1, wherein filtering and segmenting at least one of the first key terms and the second key terms comprises grouping multiple filtered terms with a unique group or class name. ### Claim 4 (depends on 1) The method of claim 1, wherein filtering and segmenting at least one of the first key terms and the second key terms comprises filtering and segmenting both the first key terms and the second key terms. ### Claim 5 (depends on 1) The method of claim 1, wherein the first text comprises at least one of an operation procedure, an alarm response recommendation, an alarm description, an event description, an alarm documentation, an operator log, and an operator comment. ### Claim 6 (depends on 1) The method of claim 1, wherein the text matching comprises at least one of exact word matching or word similarity matching. ### Claim 7 (depends on 1) The method of claim 1, wherein the processing of the first and second text comprises at least one of tokenization, sentence splitting, and part-of-speech analysis. ### Claim 8 (depends on 1) The method of claim 1, further comprising: mining the stored text in the data store for use in at least one of: generation of performance metrics, operator training, and regulatory compliance. ### Claim 9 An apparatus comprising: at least one processing device configured to: obtain, from an event log, first text of an alarm associated with an industrial process in a process control system, and process the first text to obtain first key terms; obtain, from the event log, second text of an operator response, and process the second text to obtain second key terms; filter and segment at least one of the first key terms and the second key terms; perform text matching on the first key terms and the second key terms to identify a correlation between the first text and the second text; and store the first text, the second text, and the correlation between the first text and the second text in a data store. ### Claim 10 (depends on 9) The apparatus of claim 9, wherein the event log is populated with events, alarms, and operator responses associated with the industrial process over time. ### Claim 11 (depends on 9) The apparatus of claim 9, wherein to filter and segment the at least one of the first key terms and the second key terms, the at least one processing device is configured to group multiple filtered terms with a unique group or class name. ### Claim 12 (depends on 9) The apparatus of claim 9, wherein to filter and segment the at least one of the first key terms and the second key terms, the at least one processing device is configured to filter and segment both the first key terms and the second key terms. ### Claim 13 (depends on 9) The apparatus of claim 9, wherein the first text comprises at least one of an operation procedure, an alarm response recommendation, an alarm description, an event description, an alarm documentation, an operator log, and an operator comment. ### Claim 14 (depends on 9) The apparatus of claim 9, wherein the text matching comprises at least one of exact word matching or word similarity matching. ### Claim 15 (depends on 9) The apparatus of claim 9, wherein to process the first and second text, the at least one processing device is configured to perform at least one of tokenization, sentence splitting, and part-of-speech analysis. ### Claim 16 (depends on 9) The apparatus of claim 9, wherein the at least one processing device is further configured to: mine the stored text in the data store for use in at least one of: generation of performance metrics, operator training, and regulatory compliance. ### Claim 17 A non-transitory computer readable medium containing instructions that when executed cause at least one processing device to: obtain, from an event log, first text of an alarm associated with an industrial process in a process control system, and process the first text to obtain first key terms; obtain, from the event log, second text of an operator response, and process the second text to obtain second key terms; filter and segment at least one of the first key terms and the second key terms; perform text matching on the first key terms and the second key terms to identify a correlation between the first text and the second text; and store the first text, the second text, and the correlation between the first text and the second text in a data store. ### Claim 18 (depends on 17) The non-transitory computer readable medium of claim 17, wherein the event log is populated with events, alarms, and operator responses associated with the industrial process over time. ### Claim 19 (depends on 17) The non-transitory computer readable medium of claim 17, wherein the instructions to filter and segment the at least one of the first key terms and the second key terms comprise instructions to group multiple filtered terms with a unique group or class name. ### Claim 20 (depends on 17) The non-transitory computer readable medium of claim 17, wherein the instructions to filter and segment the at least one of the first key terms and the second key terms comprise instructions to filter and segment both the first key terms and the second key terms.