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 ticket, wherein the ticket is submitted through a ticketing system, and wherein the ticket is associated with an intent;
facilitating a communications session between the ticketing system and an automated bot, wherein the automated bot automatically receives one or more messages between a user and the ticketing system in real-time through the communications session as the one or more messages are exchanged, and wherein the user is associated with the ticket;
training a machine learning model using a sample dataset, wherein the sample dataset includes sample tickets, messages associated with sample tickets, and corresponding actions performable to address intents associated with the sample tickets and the messages;
applying the ticket and the one or more messages to the machine learning model to identify one or more actions performable to address the intent;
providing the one or more actions, wherein when the one or more actions are received, the automated bot autonomously executes the one or more actions to address the intent; and
updating the machine learning model based on the intent and performance of the one or more actions.
2. The computer-implemented method of claim 1 , further comprising:
generating a dynamic sentiment parameter corresponding to the communications session, wherein the dynamic sentiment parameter represents a sentiment associated with the one or more messages, and wherein the one or more actions are identified according to the sentiment.
3. The computer-implemented method of claim 1 , wherein the one or more actions include transferring the communications session from the automated bot to a terminal device associated with a live agent.
4. The computer-implemented method of claim 1 , further comprising:
applying the ticket and the one or more messages to the machine learning model to generate recommended responses to the ticket and the one or more messages; and
providing the recommended responses, wherein when the recommended responses are received, the recommended responses are displayed to assist in the communications session.
5. The computer-implemented method of claim 1 , wherein the one or more actions are executed within the communications session.
6. The computer-implemented method of claim 1 , further comprising:
converting the one or more messages in real-time as the one or more messages are exchanged into a format usable as input to the machine learning model.
7. The computer-implemented method of claim 1 , wherein the ticket and the one or more messages are applied to the machine learning model subject to a set of rules, and wherein the set of rules define one or more parameters for selecting different actions performable based on corresponding intents.
8. A system, comprising:
one or more processors; and
memory storing thereon instructions that, as a result of being executed by the one or more processors, cause the system to:
receive a ticket, wherein the ticket is submitted through a ticketing system, and wherein the ticket is associated with an intent;
facilitate a communications session between the ticketing system and an automated bot, wherein the automated bot automatically receives one or more messages between a user and the ticketing system in real-time through the communications session as the one or more messages are exchanged, and wherein the user is associated with the ticket;
train a machine learning model using a sample dataset, wherein the sample dataset includes sample tickets, messages associated with sample tickets, and corresponding actions performable to address intents associated with the sample tickets and the messages;
apply the ticket and the one or more messages to the machine learning model to identify one or more actions performable to address the intent;
provide the one or more actions, wherein when the one or more actions are received, the automated bot autonomously executes the one or more actions to address the intent; and
update the machine learning model based on the intent and performance of the one or more actions.
9. The system of claim 8 , wherein the instructions further cause the system to:
generate a dynamic sentiment parameter corresponding to the communications session, wherein the dynamic sentiment parameter represents a sentiment associated with the one or more messages, and wherein the one or more actions are identified according to the sentiment.
10. The system of claim 8 , wherein the one or more actions include transferring the communications session from the automated bot to a terminal device associated with a live agent.
11. The system of claim 8 , wherein the instructions further cause the system to:
apply the ticket and the one or more messages to the machine learning model to generate recommended responses to the ticket and the one or more messages; and
provide the recommended responses, wherein when the recommended responses are received, the recommended responses are displayed to assist in the communications session.
12. The system of claim 8 , wherein the one or more actions are executed within the communications session.
13. The system of claim 8 , wherein the instructions further cause the system to:
convert the one or more messages in real-time as the one or more messages are exchanged into a format usable as input to the machine learning model.
14. The system of claim 8 , wherein the ticket and the one or more messages are applied to the machine learning model subject to a set of rules, and wherein the set of rules define one or more parameters for selecting different actions performable based on corresponding intents.
15. A non-transitory, computer-readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to:
receive a ticket, wherein the ticket is submitted through a ticketing system, and wherein the ticket is associated with an intent;
facilitate a communications session between the ticketing system and an automated bot, wherein the automated bot automatically receives one or more messages between a user and the ticketing system in real-time through the communications session as the one or more messages are exchanged, and wherein the user is associated with the ticket;
train a machine learning model using a sample dataset, wherein the sample dataset includes sample tickets, messages associated with sample tickets, and corresponding actions performable to address intents associated with the sample tickets and the messages;
apply the ticket and the one or more messages to the machine learning model to identify one or more actions performable to address the intent;
provide the one or more actions, wherein when the one or more actions are received, the automated bot autonomously executes the one or more actions to address the intent; and
update the machine learning model based on the intent and performance of the one or more actions.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
generate a dynamic sentiment parameter corresponding to the communications session, wherein the dynamic sentiment parameter represents a sentiment associated with the one or more messages, and wherein the one or more actions are identified according to the sentiment.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein the one or more actions include transferring the communications session from the automated bot to a terminal device associated with a live agent.
18. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
apply the ticket and the one or more messages to the machine learning model to generate recommended responses to the ticket and the one or more messages; and
provide the recommended responses, wherein when the recommended responses are received, the recommended responses are displayed to assist in the communications session.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the one or more actions are executed within the communications session.
20. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
convert the one or more messages in real-time as the one or more messages are exchanged into a format usable as input to the machine learning model.
21. The non-transitory, computer-readable storage medium of claim 15 , wherein the ticket and the one or more messages are applied to the machine learning model subject to a set of rules, and wherein the set of rules define one or more parameters for selecting different actions performable based on corresponding intents.