Critical event management using predictive models, and related methods and software
Analytics dashboards for critical event management systems that include artificial-intelligence (AI) functionalities, and related software. AI functionalities disclosed include pattern recognition and predictive modelling. One or more pattern-recognition algorithms can be used, for example, to identified patterns or other groupings within stored critical events, which can then be used to improve response performance and/or to inform the generation of predictive models. One or more predictive-modeling algorithms can be used to generate one or more predictive models that can then be used, for example, to make predictions about newly arriving critical events that can then be used, among other things, to provide optimal response performance and allow users to efficiently and effectively manage responses critical events. These and other features are described in detail.
1. A method of assisting a user with critical-event management, the method being performed by a computing system and comprising:
displaying, to a user via a graphical user interface (GUI) of the computing system, information concerning a first stored critical event;
soliciting, via the GUI, a user to provide one or more attribute annotations for one or more corresponding respective attributes of the first stored critical event;
receiving, from the user via the GUI, the one or more attribute annotations;
storing, in memory of the computing system, the one or more attribute annotations in an analytics table comprising values for a plurality of attributes of each of a plurality of stored critical events, including the first stored critical event;
executing at least one first predictive algorithm that operates on contents of the analytics table so as to build one or more predictive models representing at least some of the plurality of stored critical events; and
storing, in a memory of the computing system, the one or more predictive models;
wherein the first stored critical event is a closed critical event.
2. The method of claim 1 , further comprising:
receiving, via an event notification interface, a notification of a new critical event;
executing a second predictive algorithm that uses the one or more predictive models to automatically classify one or more attributes of the new critical event; and
based on the automatic classifying, predicting a value for each of the one or more attributes of the new critical event.
3. The method of claim 2 , further comprising displaying, to the user on the GUI, the value for at least one of the one or more attributes.
4. The method of claim 2 , wherein one of the one or more attributes comprises a cost associated with resolving the new critical event, and at least one of the values includes a predicted cost amount.
5. The method of claim 2 , wherein one of the one or more attributes comprises a response team identification, and at least one of the values includes a suggested response team.
6. The method of claim 2 , wherein one of the one or more attributes comprises a time to resolution, and at least one of the values includes a predicted time to resolution value.
7. The method of claim 2 , wherein one of the one or more attributes comprises a resolution cost, and at least one of the values includes a predicted resolution cost value.
8. The method of claim 2 , wherein one of the one or more attributes comprises a return on investment, and at least one of the values includes a predicted return on investment value.
9. The method of claim 2 , further comprising:
retrieving, from a datastore in memory of the computing system, data contained in an analytics table comprising values for a plurality of attributes of each of a plurality of currently active critical events, including the value for each of the one or more attributes of the new critical event;
executing at least one pattern-recognition algorithm that has been trained to identify patterns within the plurality of attributes among the plurality of currently active critical events and to assign differing portions of the data to differing clusters based on the patterns, wherein executing that at least one pattern-recognition algorithm includes operating on the data in the analytics table so as to assign the differing portions of the data to the differing clusters;
executing a visualization algorithm to generate a visualization depicting the differing clusters to which the at least one pattern-recognition algorithm has assigned the differing portions of the data; and
displaying, via the GUI of the computing system, the visualization to the user;
wherein the visualization graphically depicts each of the plurality of currently active critical events, including the new critical event, as a graphical indicator configured as a control that, upon user selection, causes the GUI to display to the user information regarding the corresponding one of the currently active critical events.
10. The method of claim 9 , wherein the information includes an action the user can select, the action displayed in conjunction with a user-selectable control that allows a user to select the action.
11. The method of claim 10 , wherein the plurality of currently active critical events have a first attribute, and the action includes allowing the user to change a first value of the first attribute via the GUI.
12. The method of claim 11 , wherein the action includes allowing the user to change a priority of a corresponding one of the plurality of currently active critical events via the GUI.
13. The method of claim 11 , further comprising receiving the first value via the GUI and updating the analytics table with the first value.
14. The method of claim 1 , further comprising:
receiving, via an event notification interface, a notification of a new critical event affecting a resource;
executing a second predictive algorithm that uses the one or more predictive models to automatically determine one or more suggested actions that a responder can take in resolving the critical event;
based on the resource affected, automatically determining one or more services associated with the resource affected;
displaying, via the GUI of the computing system, a service-dependency graph visually depicting the one or more services, the resource affected, and an impact that the critical event has on the one or more services, wherein the resource affected is represented by a user-selectable icon;
receiving via the GUI a user selection of the user-selectable icon; and
in response to the user selection, displaying to the user via the GUI a popup window that allows a user to view the one or more suggested actions.
15. The method of claim 14 , wherein at least one of the one or more suggested actions includes machine-executable script for performing the corresponding action automatically.
16. The method of claim 15 , further comprising receiving a user selection of that at least one suggested action having the machine-executable script and, in response, executing the machine-executable script.
17. The method of claim 16 , further comprising receiving a notification that the machine-executable script has been successfully executed and displaying to the user via the GUI an indication of the successful execution.
18. The method of claim 14 , further comprising displaying via the GUI and in association with the user-selectable icon a visual indication of the critical event.
19. The method of claim 14 , wherein the critical event is an information-technology event.
20. A machine-readable storage medium containing computer-executable instructions that, when executed by a computing system, perform the method of claim 1 .