Unstructured extensions to rpa
Embodiments herein describe an automated process for identifying tasks that can be converted from primarily being driven by a human agent into bot-driven RPAs. This disclosure describes techniques for automatically generating RPAs by monitoring the actions of the agent and identifying corresponding events. These events can be performed on unstructured data sources and structured data sources. The events are clustered into different tasks where pattern detection techniques are used to identify common (or overlapping) events and causal relationships between the events. Using these causal relationships, the system can map events performed on unstructured data sources to events performed on structured data source. The system can then generate respective bot-RPAs for the tasks. The system can monitor, in real-time, data received from unstructured and/or structured data sources and when it identifies data for one of the bot-RPAs, automatically execute the RPA to perform the task.
1. A computer-implemented method comprising:
identifying events based on monitoring agent actions performed on a workstation when performing a task multiple times, wherein the identified events correspond to both unstructured and structured data sources, wherein identifying the events comprises:
assigning individual utterances in the unstructured data source as a first set of events,
identifying operating system (OS)-level events performed on the structured data source by monitoring actions of the OS in the workstation, and
identifying intra-application input/output (I/O) events performed on the structured data source by monitoring an I/O device used by the agent;
adding timestamps to the first set of events, the OS-level events, and the intra-application I/O events;
identify groupings of duplicate events in the identified events that each correspond to a common event using pattern matching;
identify causal relationships between the common events based on the timestamps;
mapping, based on at least one of the causal relationships, a first common event corresponding to the unstructured data source to a second common event corresponding to the structured data source; and
generating an ordered list of instructions for a robotic process automation (RPA) of a bot based on the mapped events.
2. The computer-implemented method of claim 1 , wherein the unstructured data source originates from a human user and comprises at least one of a telephone conversation, a chat, or an electronic communication.
3. The computer-implemented method of claim 1 , further comprising:
monitoring, in real-time, data generated by a first unstructured data source;
identifying inputs in the data generated by the first unstructured data source for the RPA; and
executing the RPA using the bot and the inputs.
4. The computer-implemented method of claim 3 , wherein the RPA is executed automatically by the bot without user instruction.
5. The computer-implemented method of claim 1 , further comprising:
identifying second events based on monitoring agent actions performed on the workstation when performing a plurality of different tasks; and
identifying a set of second events corresponding to each of the plurality of different tasks using clustering; and
generating, based on the sets of second events, respective lists of instructions for a plurality of RPAs, each of the plurality of RPAs corresponding to one of the plurality of different tasks.
6. A system, comprising:
a processor; and
memory comprising one or more applications configured to perform an operation when executed by the processor, the operation comprises:
identifying events based on monitoring agent actions performed on a workstation when performing a task multiple times, wherein the identified events correspond to both unstructured and structured data sources, wherein identifying the events comprises:
assigning individual utterances in the unstructured data source as a first set of events,
identifying operating system (OS)-level events performed on the structured data source by monitoring actions of the OS in the workstation, and
identifying intra-application input/output (I/O) events performed on the structured data source by monitoring an I/O device used by the agent;
adding timestamps to the first set of events, the OS-level events, and the intra-application I/O events;
identify groupings of duplicate events in the identified events that each correspond to a common event using pattern matching;
identify causal relationships between the common events based on the timestamps;
mapping, based on at least one of the causal relationships, a first common event corresponding to the unstructured data source to a second common event corresponding to the structured data source; and
generating an ordered list of instructions for a robotic process automation (RPA) of a bot based on the mapped events.
7. The system of claim 6 , wherein the unstructured data source originates from a human user and comprises at least one of a telephone conversation, a chat, or an electronic communication.
8. The system of claim 6 , wherein the operation further comprises:
monitoring, in real-time, data generated by a first unstructured data source;
identifying inputs in the data generated by the first unstructured data source for the RPA; and
executing the RPA using the bot and the inputs.
9. The system of claim 8 , wherein the RPA is executed automatically by the bot without user instruction.
10. The system of claim 6 , wherein the operation further comprises:
identifying second events based on monitoring agent actions performed on the workstation when performing a plurality of different tasks; and
identifying a set of second events corresponding to each of the plurality of different tasks using clustering; and
generating, based on the sets of second events, respective lists of instructions for a plurality of RPAs, each of the plurality of RPAs corresponding to one of the plurality of different tasks.
11. A computer program product for programmatically generating an RPA based on monitoring agent actions, the computer program product comprising:
a computer readable storage medium having computer readable program code embodied therewith, the computer-readable program code executable by one or more computer processors to perform an operation, the operation comprising:
identifying events based on monitoring the agent actions performed on a workstation when performing a task multiple times, wherein the identified events correspond to both unstructured and structured data sources, wherein identifying the events comprises:
assigning individual utterances in the unstructured data source as a first set of events,
identifying operating system (OS)-level events performed on the structured data source by monitoring actions of the OS in the workstation, and
identifying intra-application input/output (I/O) events performed on the structured data source by monitoring an I/O device used by the agent;
adding timestamps to the first set of events, the OS-level events, and the intra-application I/O events;
identifying groupings of duplicate events in the identified events that each correspond to a common event using pattern matching;
identifying causal relationships between the common events based on the timestamps;
mapping, based on at least one of the causal relationships, a first common event corresponding to the unstructured data source to a second common event corresponding to the structured data source; and
generating an ordered list of instructions for the RPA of a bot based on the mapped events.
12. The computer program product of claim 11 , wherein the unstructured data source originates from a human user and comprises at least one of a telephone conversation, a chat, or an electronic communication.
13. The computer program product of claim 11 , wherein the operation further comprises:
monitoring, in real-time, data generated by a first unstructured data source;
identifying inputs in the data generated by the first unstructured data source for the RPA; and
executing the RPA using the bot and the inputs.
14. The computer program product of claim 13 , wherein the RPA is executed automatically by the bot without user instruction.
15. The computer program product of claim 11 , wherein the operation further comprises:
identifying second events based on monitoring agent actions performed on the workstation when performing a plurality of different tasks; and
identifying a set of second events corresponding to each of the plurality of different tasks using clustering; and
generating, based on the sets of second events, respective lists of instructions for a plurality of RPAs, each of the plurality of RPAs corresponding to one of the plurality of different tasks.