Systems and methods for transferring messaging to automation
The present disclosure relates generally to facilitating routing of communications. More specifically, techniques are provided to dynamically transfer messaging between a network device and a terminal device to a type of bot based on intents identified from the messaging. Further, techniques are provided to track performance of the selected type of bot during automation.
1. A computer-implemented method comprising:
receiving a request for a conversation;
determining an intent for the conversation, wherein the intent is determined from the request;
identifying one or more types of bots based on the intent;
dynamically determining one or more options for facilitating a transfer of the conversation to a type of bot from a terminal device operated by an agent, wherein when an option is selected, a conversation with a selected type of bot is facilitated, and wherein the conversation with the selected type of bot is monitored at the terminal device by the agent;
dynamically determining feedback on the conversation, wherein the feedback is dynamically determined based on a real-time evaluation of responses exchanged during the conversation;
determining a polarity for the conversation based on the feedback, wherein the polarity is determined using the feedback as input to a model trained to determine polarities of conversations; and
applying the conversation, the intent, the polarity, and attributes of the selected type of bot to a second model to train the second model to determine a future intent for the one or more types of bots.
2. The computer-implemented method of claim 1 , further comprising:
displaying the conversation with the selected type of bot at the terminal device.
3. The computer-implemented method of claim 1 , further comprising:
calculating a sentiment score based on the conversation with the selected type of bot.
4. The computer-implemented method of claim 3 , further comprising:
determining that the sentiment score is below a threshold; and
transferring the conversation to the terminal device.
5. The computer-implemented method of claim 1 , wherein the request is in a natural language.
6. The computer-implemented method of claim 1 , wherein when the option is selected, the second model that is used to determine the future intent for the one or more types of bots is updated to provide the option when the future intent is determined.
7. The computer-implemented method of claim 1 , further comprising:
receiving additional feedback from the terminal device and a network device from which the request for the conversation was received; and
using the additional feedback as input to the model to determine a new polarity for the conversation.
8. 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 request for a conversation;
determining an intent for the conversation, wherein the intent is determined from the request;
identifying one or more types of bots based on the intent;
dynamically determining one or more options for facilitating a transfer of the conversation to a type of bot from a terminal device operated by an agent, wherein when an option is selected, a conversation with a selected type of bot is facilitated, and wherein the conversation with the selected type of bot is monitored at the terminal device by the agent;
dynamically determining feedback on the conversation, wherein the feedback is dynamically determined based on a real-time evaluation of responses exchanged during the conversation;
determining a polarity for the conversation based on the feedback, wherein the polarity is determined using the feedback as input to a model trained to determine polarities of conversations; and
applying the conversation, the intent, the polarity, and attributes of the selected type of bot to a second model to train the second model to determine a future intent for the one or more types of bots.
9. The computer-program product of claim 8 , wherein the operations further include:
displaying the conversation with the selected type of bot at the terminal device.
10. The computer-program product of claim 8 , wherein the operations further include:
calculating a sentiment score based on the conversation with the selected type of bot.
11. The computer-program product of claim 10 , wherein the operations further include:
determining that the sentiment score is below a threshold; and
transferring the conversation to the terminal device.
12. The computer-program product of claim 8 , wherein the request is in natural language.
13. The computer-program product of claim 8 , wherein when the option is selected, the second model that is used to determine the future intent for the one or more types of bots is updated to provide the option when the future intent is determined.
14. The computer-program product of claim 8 , wherein the operations further include:
receiving additional feedback from the terminal device and a network device from which the request for the conversation was received; and
using the additional feedback as input to the model to determine a new polarity for the conversation.
15. 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 request for a conversation;
determining an intent for the conversation, wherein the intent is determined from the request;
identifying one or more types of bots based on the intent;
dynamically determining one or more options for facilitating a transfer of the conversation to a type of bot from a terminal device operated by an agent, wherein when an option is selected, a conversation with a selected type of bot is facilitated, and wherein the conversation with the selected type of bot is monitored at the terminal device by the agent;
dynamically determining feedback on the conversation, wherein the feedback is dynamically determined based on a real-time evaluation of responses exchanged during the conversation;
determining a polarity for the conversation based on the feedback, wherein the polarity is determined using the feedback as input to a model trained to determine polarities of conversations; and
applying the conversation, the intent, the polarity, and attributes of the selected type of bot to a second model to train the second model to determine a future intent for the one or more types of bots.
16. The system of claim 15 , wherein the operations further include:
displaying the conversation with the selected type of bot at the terminal device.
17. The system of claim 15 , wherein the operations further include:
calculating a sentiment score based on the conversation with the selected type of bot.
18. The system of claim 17 , wherein the operations further include:
determining that the sentiment score is below a threshold; and
transferring the conversation to the terminal device.
19. The system of claim 15 , wherein the request is in natural language.
20. The system of claim 15 , wherein when the option is selected, the second model that is used to determine the future intent for the one or more types of bots is updated to provide the option when the future intent is determined.
21. The system of claim 15 , wherein the operations further include:
receiving additional feedback from the terminal device and a network device from which the request for the conversation was received; and
using the additional feedback as input to the model to determine a new polarity for the conversation.