# US 2024/0202201 A1 · Situation-aware explainability for artificial intelligence-enabled, process-aware systems using complex event processing > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2024/0202201 A1 - Document ID: US20240202201A1 - Status: Published application - Kind: A1 - Application number: 18/066,916 - Filed: 2022-12-15 - Published: 2024-06-20 - Earliest claimed: 2022-12-15 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Fabiana Fournier; Skarbovsky Yudovich Inna; Guy Amit; Lior Limonad - Web page: https://patentgrep.com/patent/US20240202201A1 ## CPC - G06F 16/24578: {using ranking} - G06F 16/244: {Grouping and aggregation} - G06F 16/24575: {using context} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Providing a machine-generated explanation of an outcome of a process execution engine includes inputting into a complex event processing (CEP) engine at least one predetermined event pattern specification and a sequence of events, the sequence of events generated, at least in part, by a process execution engine executing a predetermined process in real time. Using the CEP engine, an enriched event log is generated based on the input. The enriched event log includes the sequence of events and additionally includes one or more situational events corresponding to one or more of the sequence of events. The one or more situational events are derived by the CEP engine based on the at least one predetermined event pattern specification. A hypothesis-oriented, situationally aware explanation for the outcome of the predetermined process is determined using an artificial intelligence (AI) explainability framework with input of the enriched event log. ## Claims ### Claim 1 A method, comprising: inputting into a complex event processing (CEP) engine at least one predetermined event pattern specification and a sequence of events, wherein the sequence of events is generated, at least in part, by a process execution engine executing a predetermined process in real time; generating, using the CEP engine in response to the inputting, an enriched event log, wherein the enriched event log includes the sequence of events and additionally includes one or more situational events derived by the CEP, and wherein the one or more situational events are derived by the CEP engine based on the at least one predetermined event pattern specification; determining, using an artificial intelligence (AI) explainability tool with input of the enriched event log, a hypothesis-oriented, situationally aware explanation for an outcome of the predetermined process; and, outputting, using computer hardware, the hypothesis-oriented, situationally aware explanation. ### Claim 2 (depends on 1) The method of claim 1, wherein the determining the hypothesis-oriented, situationally aware explanation comprises: determining a plurality of factors that determine the outcome of the predetermined process; and ranking the plurality of factors in response to determining a strength of association between the outcome and each of the plurality of factors. ### Claim 3 (depends on 1) The method of claim 1, wherein the sequence of events includes one or more external events generated by a source external to the process execution engine. ### Claim 4 (depends on 1) The method of claim 1, wherein the hypothesis-oriented situationally aware explanation is generated in real time. ### Claim 5 (depends on 1) The method of claim 1, wherein the hypothesis-oriented situationally aware explanation is generated retrospectively based on a replay of an event log comprising the sequence of events. ### Claim 6 (depends on 5) The method of claim 5, wherein the event log generated by transforming the sequence of events with a data synthesis prior to the inputting into the CEP engine, wherein the data synthesis generates a data structure for each execution of the process, the data structure including an identifier for each execution, a plurality of sequential events having a same identifier, a time stamp for each of the plurality of sequential events, and one or more decision variables corresponding to one or more of the plurality of sequential events. ### Claim 7 (depends on 6) The method of claim 6, further comprising adjusting at least one of the one or more decision variables based on a user input representing a hypothetical situation. ### Claim 8 (depends on 1) The method of claim 1, further comprising merging into a combined data structure events of the enriched event log that share a common identifier, wherein the merging is performed prior to inputting the enriched event log into the AI explainability framework. ### Claim 9 A system, comprising: A processor configured to initiate operations including: inputting into a complex event processing (CEP) engine at least one predetermined event pattern specification and a sequence of events, wherein the sequence of events is generated, at least in part, by a process execution engine executing a predetermined process in real time; generating, using the CEP engine in response to the inputting, an enriched event log, wherein the enriched event log includes the sequence of events and additionally includes one or more situational events derived by the CEP, and wherein the one or more situational events are derived by the CEP engine based on the at least one predetermined event pattern specification; determining, using an artificial intelligence (AI) explainability tool with input of the enriched event log, a hypothesis-oriented, situationally aware explanation for an outcome of the predetermined process; and, outputting, using computer hardware, the hypothesis-oriented, situationally aware explanation. ### Claim 10 (depends on 9) The system of claim 9, wherein the determining the hypothesis-oriented, situationally aware explanation comprises: determining a plurality of features that determine the outcome of the predetermined process; and ranking the plurality of features in response to determining a strength of association between the outcome and each of the plurality of features. ### Claim 11 (depends on 9) The system of claim 9, wherein the sequence of events includes one or more external events generated by a source external to the process execution engine. ### Claim 12 (depends on 9) The system of claim 9, wherein the hypothesis-oriented situationally aware explanation is generated in real time. ### Claim 13 (depends on 9) The system of claim 9, wherein the hypothesis-oriented situationally aware explanation is generated retrospectively based on a replay of an event log comprising the sequence of events. ### Claim 14 (depends on 13) The system of claim 13, wherein the event log generated by transforming the sequence of events with a data synthesis prior to the inputting into the CEP engine, wherein the data synthesis generates a data structure for each execution of the process, the data structure including an identifier for each execution, a plurality of sequential events having a same identifier, a time stamp for each of the plurality of sequential events, and one or more decision variables corresponding to one or more of the plurality of sequential events. ### Claim 15 (depends on 14) The system of claim 14, wherein the processor is configured to initiate operations further including adjusting at least one of the one or more decision variables based on a user input representing a hypothetical situation. ### Claim 16 (depends on 9) The system of claim 9, wherein the processor is configured to initiate operations further including merging into a combined data structure events of the enriched event log that share a common identifier, wherein the merging is performed prior to inputting the enriched event log into the AI explainability framework. ### Claim 17 A computer program product, the computer program product comprising: one or more computer-readable storage media and program instructions collectively stored on the one or more computer-readable storage media, the program instructions executable by a processor to cause the processor to initiate operations including: inputting into a complex event processing (CEP) engine at least one predetermined event pattern specification and a sequence of events, wherein the sequence of events is generated, at least in part, by a process execution engine executing a predetermined process in real time; generating, using the CEP engine in response to the inputting, an enriched event log, wherein the enriched event log includes the sequence of events and additionally includes one or more situational events derived by the CEP, and wherein the one or more situational events are derived by the CEP engine based on the at least one predetermined event pattern specification; determining, using an artificial intelligence (AI) explainability tool with input of the enriched event log, a hypothesis-oriented, situationally aware explanation for an outcome of the predetermined process; and, outputting, using computer hardware, the hypothesis-oriented, situationally aware explanation. ### Claim 18 (depends on 17) The computer program product of claim 17, wherein the determining the hypothesis-oriented, situationally aware explanation comprises: determining a plurality of features that determine the outcome of the predetermined process; and ranking the plurality of features in response to determining a strength of association between the outcome and each of the plurality of features. ### Claim 19 (depends on 17) The computer program product of claim 17, wherein the hypothesis-oriented situationally aware explanation is generated in real time. ### Claim 20 (depends on 17) The computer program product of claim 17, wherein the hypothesis-oriented situationally aware explanation is generated retrospectively based on a replay of an event log comprising the sequence of events.