Systems and methods for external system integration
The present disclosure relates generally to facilitating routing of communications across external systems. More specifically, techniques are provided to dynamically route issue tracking tickets to disparate endpoints based on the content of the ticket.
1. A computer-implemented method comprising:
receiving a message associated with a user, wherein the message represents an issue that the user wants resolved;
generating a routing determination by dynamically evaluating the message in real-time, wherein the routing determination facilitates a live communication session between the user and a bot;
dynamically detecting ongoing messages exchanged in real-time during the live communication session between the user and the bot;
training a machine learning model using the ongoing messages and historical data, wherein the historical data includes one or more previously received messages and one or more previously performed actions associated with issues similar to the issue the user wants resolved;
applying the machine learning model to the ongoing messages to automatically determine one or more current actions associated with the issue;
monitoring performance of the one or more current actions, wherein monitoring includes real-time analysis of textual or non-textual attributes of the ongoing messages; and
dynamically updating the machine learning model based on the ongoing messages, the one or more current actions, and the textual or non-textual attributes of the ongoing messages.
2. The computer-implemented method of claim 1 , wherein a plug-in is used to apply the trained machine learning model to the ongoing messages to automatically determine the one or more current actions.
3. The computer-implemented method of claim 1 , wherein the one or more current actions are performed within a messaging system.
4. The computer-implemented method of claim 1 , further comprising:
storing information corresponding to the one or more current actions; and
using the information and the machine learning model to determine a future action.
5. The computer-implemented method of claim 1 , wherein applying the machine learning model includes analyzing conversation tone from the ongoing messages.
6. The computer-implemented method of claim 1 , wherein the one or more current actions include routing the ongoing messages to an agent.
7. The computer-implemented method of claim 1 , wherein the ongoing messages include two or more messages.
8. The computer-implemented method of claim 1 , wherein analyzing the textual or the non-textual attributes of the ongoing messages includes determining a sentiment of the user based on the ongoing messages.
9. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:
receiving a message associated with a user, wherein the message represents an issue that the user wants resolved;
generating a routing determination by dynamically evaluating the message in real-time, wherein the routing determination facilitates a live communication session between the user and a bot;
dynamically detecting ongoing messages exchanged in real-time during the live communication session between the user and the bot;
training a machine learning model using the ongoing messages and historical data, wherein the historical data includes one or more previously received messages and one or more previously performed actions associated with issues similar to the issue the user wants resolved;
applying the trained machine learning model to the ongoing messages to automatically determine one or more current actions associated with the issue;
monitoring performance of the one or more current actions, wherein monitoring includes real-time analysis of textual or non-textual attributes of the ongoing messages; and
dynamically updating the machine learning model based on the ongoing messages, the one or more current actions, and the textual or non-textual attributes of the messages.
10. The computer-program product of claim 9 , wherein a plug-in is used to apply the trained machine learning model to the ongoing messages to automatically determine the one or more current actions.
11. The computer-program product of claim 9 , wherein the one or more current actions are performed within a messaging system.
12. The computer-program product of claim 9 , wherein the operations further include:
storing information corresponding to the one or more current actions; and
using the information and the machine learning model to determine a future action.
13. The computer-program product of claim 9 , wherein applying the machine learning model includes analyzing conversation tone from the ongoing messages.
14. The computer-program product of claim 9 , wherein the one or more current actions include routing the ongoing messages to an agent.
15. The computer-program product of claim 9 , wherein the ongoing messages include two or more messages.
16. The computer-program product of claim 9 , wherein analyzing the textual or the non-textual attributes of the ongoing messages includes determining a sentiment of the user based on the ongoing messages.
17. A system comprising:
one or more processors; and
one or more non-transitory machine-readable storage media containing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations including:
receiving a message associated with a user, wherein the message represents an issue that the user wants resolved;
generating a routing determination by dynamically evaluating the message in real-time, wherein the routing determination facilitates a live communication session between the user and a bot;
dynamically detecting ongoing messages exchanged in real-time during the live communication session between the user and the bot;
training a machine learning model using the ongoing messages and historical data, wherein the historical data includes one or more previously received messages and one or more previously performed actions associated with issues similar to the issue the user wants resolved;
applying the trained machine learning model to the ongoing messages to automatically determine one or more current actions associated with the issue;
monitoring performance of the one or more current actions, wherein monitoring includes real-time analysis of textual or non-textual attributes of the ongoing messages; and
dynamically updating the machine learning model based on the ongoing messages, the one or more current actions, and the textual or non-textual attributes of the messages.
18. The system of claim 17 , wherein a plug-in is used to apply the trained machine learning model to the ongoing messages to automatically determine the one or more current actions.
19. The system of claim 17 , wherein the one or more current actions are performed within a messaging system.
20. The system of claim 17 , wherein the operations further include:
storing information corresponding to the action; and
using the information and the artificial intelligence to determine a future action.
21. The system of claim 17 , wherein applying the machine learning model includes analyzing conversation tone from the ongoing messages.
22. The system of claim 15 , wherein the ongoing messages include two or more messages.
23. The system of claim 15 , wherein the one or more current actions include routing the ongoing messages to an agent.
24. The system of claim 17 , wherein analyzing the textual or the non-textual attributes of the ongoing messages includes determining a sentiment of the user based on the ongoing messages.