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 is associated with an intent;
facilitating a communications session between the user and an automated bot, wherein when the communications session is facilitated, the automated bot automatically extracts the intent from the message;
training a machine learning model using a sample dataset, wherein the sample dataset includes sample messages and corresponding actions performable to address intents associated with the sample messages;
processing the intent and one or more messages exchanged during the communications session through the machine learning model to identify an action performable to address the intent; providing the action, wherein when the action is received at the automated bot, the automated bot autonomously executes the action to address the intent;
generating a ticket, wherein the ticket is used to track the one or more messages and the action as the one or more messages are exchanged and the action is performed; and
updating the machine learning model based on the intent and performance of the action.
2. The computer-implemented method of claim 1 , wherein the action includes routing the communications session to a terminal device associated with an agent.
3. The computer-implemented method of claim 1 , wherein the action is performed by the automated bot according to a set of rules without human intervention.
4. The computer-implemented method of claim 1 , further comprising:
analyzing textual or non-textual attributes associated with the one or more messages to determine a sentiment associated with the user, wherein the textual or non-textual attributes are analyzed as the one or more messages are exchanged; and
dynamically transferring the communications session from the automated bot to an agent based on the sentiment.
5. The computer-implemented method of claim 1 , further comprising:
processing the intent and the one or more messages through the machine learning model to generate one or more recommended responses to the one or more messages; and
providing the one or more recommended responses, wherein when the one or more recommended responses are received, the one or more recommended responses are communicated through the communications session.
6. The computer-implemented method of claim 1 , wherein the one or more messages are exchanged using a customer relationship management (CRM) format.
7. The computer-implemented method of claim 1 , further comprising:
storing information corresponding to the action; and
using the information and the machine learning model to determine a future action.
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 message associated with a user, wherein the message is associated with an intent;
facilitate a communications session between the user and an automated bot,
wherein when the communications session is facilitated,
the automated bot automatically extracts the intent from the message;
train a machine learning model using a sample dataset, wherein the sample dataset includes sample messages and corresponding actions performable to address intents associated with the sample messages;
process the intent and one or more messages exchanged during the communications session through the machine learning model to identify an action performable to address the intent;
provide the action, wherein when the action is received at the automated bot,
the automated bot autonomously executes the action to address the intent;
generate a ticket, wherein the ticket is used to track the one or more messages and the action as the one or more messages are exchanged and the action is performed; and
update the machine learning model based on the intent and performance of the action.
9. The system of claim 8 , wherein the action includes routing the communications session to a terminal device associated with an agent.
10. The system of claim 8 , wherein the action is performed by the automated bot according to a set of rules without human intervention.
11. The system of claim 8 , wherein the instructions further cause the system to:
analyze textual or non-textual attributes associated with the one or more messages to determine a sentiment associated with the user, wherein the textual or non-textual attributes are analyzed as the one or more messages are exchanged; and
dynamically transfer the communications session from the automated bot to an agent based on the sentiment.
12. The system of claim 8 , wherein the instructions further cause the system to:
process the intent and the one or more messages through the machine learning model to generate one or more recommended responses to the one or more messages; and
provide the one or more recommended responses, wherein when the one or more recommended responses are received, the one or more recommended responses are communicated through the communications session.
13. The system of claim 8 , wherein the one or more messages are exchanged using a customer relationship management (CRM) format.
14. The system of claim 8 , wherein the instructions further cause the system to:
store information corresponding to the action; and
use the information and the machine learning model to determine a future action.
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 message associated with a user, wherein the message is associated with an intent;
facilitate a communications session between the user and an automated bot, wherein when the communications session is facilitated, the automated bot automatically extracts the intent from the message;
train a machine learning model using a sample dataset, wherein the sample dataset includes sample messages and corresponding actions performable to address intents associated with the sample messages;
process the intent and one or more messages exchanged during the communications session through the machine learning model to identify an action performable to address the intent;
provide the action, wherein when the action is received at the automated bot, the automated bot autonomously executes the action to address the intent;
generate a ticket, wherein the ticket is used to track the one or more messages and the action as the one or more messages are exchanged and the action is performed; and
update the machine learning model based on the intent and performance of the action.
16. The non-transitory, computer-readable storage medium of claim 15 , wherein the action includes routing the communications session to a terminal device associated with an agent.
17. The non-transitory, computer-readable storage medium of claim 15 , wherein the action is performed by the automated bot according to a set of rules without human intervention.
18. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
analyze textual or non-textual attributes associated with the one or more messages to determine a sentiment associated with the user, wherein the textual or non-textual attributes are analyzed as the one or more messages are exchanged; and
dynamically transfer the communications session from the automated bot to an agent based on the sentiment.
19. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
process the intent and the one or more messages through the machine learning model to generate one or more recommended responses to the one or more messages; and
provide the one or more recommended responses, wherein when the one or more recommended responses are received, the one or more recommended responses are communicated through the communications session.
20. The non-transitory, computer-readable storage medium of claim 15 , wherein the one or more messages are exchanged using a customer relationship management (CRM) format.
21. The non-transitory, computer-readable storage medium of claim 15 , wherein the executable instructions further cause the computer system to:
store information corresponding to the action; and
use the information and the machine learning model to determine a future action.