Message rerouting from an e-mail environment to a messaging environment
The present disclosure relates generally to facilitating routing of communications. More specifically, techniques are provided to dynamically reroute messages. For example, embodiments can redirect a communication from an e-mail environment to a messaging environment in order to perform services with one or more clients.
1. A computer-implemented method comprising:
receiving a request e-mail message addressed to an account associated with a client, wherein the request e-mail message specifies an intent to address an issue;
identifying a recipient for the request e-mail message, wherein the recipient is associated with the account;
training a machine learning model to perform a semantic analysis of e-mail messages to identify intents expressed in the e-mail messages, wherein the machine learning model is trained using a dataset of input e-mail messages and known intents included in the input e-mail messages;
using the request e-mail message as input to the machine learning model to identify the intent;
updating the machine learning model using the request e-mail message, the intent, feedback corresponding to identification of the intent from the request e-mail message, and the dataset of input e-mail messages and known intents;
transmitting the intent and additional information for identification of one or more resolutions for the intent, wherein the intent and the additional information is transmitted over a chat communication channel, and wherein when the intent and the additional information is received by the recipient, the recipient can determine a resolution from the one or more resolutions and respond using the chat communication channel;
receiving a response to the intent;
generating a response e-mail message, wherein the response e-mail message includes the response and a conversation history associated with the recipient and a sender of the request e-mail message; and
transmitting the response e-mail message.
2. The computer-implemented method of claim 1 , wherein the intent is transmitted to the recipient with the conversation history associated with the recipient and the sender of the request e-mail message, wherein the intent is incorporated into the conversation history.
3. The computer-implemented method of claim 1 , wherein:
the account is associated with a group of recipients; and
the computer-implemented method further comprises identifying the recipient from the group of recipients based on the intent.
4. The computer-implemented method of claim 1 , wherein:
the account associated with the client is further associated with a skill; and
the recipient is identified as a result of the recipient being assigned to the skill.
5. The computer-implemented method of claim 1 , further comprising inserting a header and footer into the response e-mail message, wherein the header and the footer are associated with the client.
6. The computer-implemented method of claim 1 , further comprising polling a client server to receive the request e-mail message.
7. The computer-implemented method of claim 1 , further comprising:
receiving another e-mail message;
determining that a conversation session corresponding to the request e-mail message is active; and
transmitting a response to the other e-mail message, wherein the response to the other e-mail message includes an instruction to utilize the conversation session corresponding to the request e-mail message.
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 request e-mail message addressed to an account associated with a client, wherein the request e-mail message specifies an intent to address an issue;
identify a recipient for the request e-mail message, wherein the recipient is associated with the account;
train a machine learning model to perform a semantic analysis of e-mail messages to identify intents expressed in the e-mail messages, wherein the machine learning model is trained using a dataset of input e-mail messages and known intents included in the input e-mail messages;
use the request e-mail message as input to the machine learning model to identify the intent;
update the machine learning model using the request e-mail message, the intent, feedback corresponding to identification of the intent from the request e-mail message, and the dataset of input e-mail messages and known intents
transmit the intent and additional information for identification of one or more resolutions for the intent, wherein the intent and the additional information is transmitted over a chat communication channel, and wherein when the intent and the additional information is received by the recipient, the recipient can determine a resolution from the one or more resolutions and respond using the chat communication channel;
receive a response to the intent;
generate a response e-mail message, wherein the response e-mail message includes the response and a conversation history associated with the recipient and a sender of the request e-mail message; and
transmit the response e-mail message.
9. The system of claim 8 , wherein:
the account associated with the client is further associated with a skill; and
the recipient is identified as a result of the recipient being assigned to the skill.
10. The system of claim 8 , wherein the instructions further cause the system to insert a header and footer into the response e-mail message, wherein the header and the footer are associated with the client.
11. The system of claim 8 , wherein the instructions further cause the system to poll a client server to receive the request e-mail message.
12. The system of claim 8 , wherein the instructions further cause the system to:
receive another e-mail message;
determine that a conversation session corresponding to the request e-mail message is active; and
transmit a response to the other e-mail message, wherein the response to the other e-mail message includes an instruction to utilize the conversation session corresponding to the request e-mail message.
13. 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 request e-mail message addressed to an account associated with a client, wherein the request e-mail message includes a body, and wherein the body specifies an intent to address an issue;
identify a recipient for the request e-mail message, wherein the recipient is associated with the account;
train a machine learning model to perform a semantic analysis of e-mail messages to identify intents expressed in the e-mail messages, wherein the machine learning model is trained using a dataset of input e-mail messages and known intents included in the input e-mail messages;
use the request e-mail message as input to the machine learning model to identify the intent;
update the machine learning model using the request e-mail message, the intent, feedback corresponding to identification of the intent from the request e-mail message, and the dataset of input e-mail messages and known intents;
transmit the intent and additional information for identification of one or more resolutions for the intent, wherein the intent and the additional information is transmitted over a chat communication channel, and wherein when the intent and the additional information is received by the recipient, the recipient can determine a resolution from the one or more resolutions and respond using the chat communication channel;
receive a response to the intent;
generate a response e-mail message, wherein the response e-mail message includes the response and a conversation history associated with the recipient and a sender of the request e-mail message; and
transmit the response e-mail message.
14. The non-transitory, computer-readable medium of claim 13 , wherein the intent is transmitted to the recipient with the conversation history associated with the recipient and the sender of the request e-mail message, wherein the intent is incorporated into the conversation history.
15. The non-transitory, computer-readable medium of claim 13 , wherein the executable instructions further cause the computer system to insert a header and footer into the response e-mail message, wherein the header and the footer are associated with the client.
16. The non-transitory, computer-readable medium of claim 13 , wherein the executable instructions further cause the computer system to poll a client server to receive the request e-mail message.
17. The non-transitory, computer-readable medium of claim 13 , wherein the executable instructions further cause the computer system to:
receive another e-mail message;
determine that a conversation session corresponding to the request e-mail message is active; and
transmit a response to the other e-mail message, wherein the response to the other e-mail message includes an instruction to utilize the conversation session corresponding to the request e-mail message.
18. The computer-implemented method of claim 1 , wherein the machine learning model is dynamically trained by soliciting the feedback corresponding to the identification of the intent from the request e-mail message.
19. The computer-implemented method of claim 1 , wherein the machine learning model is trained and updated in real-time as request e-mail messages are received.
20. The system of claim 8 , wherein the machine learning model is dynamically trained by soliciting the feedback corresponding to the identification of the intent from the request e-mail message.
21. The system of claim 8 , wherein the machine learning model is trained and updated in real-time as request e-mail messages are received.
22. The system of claim 8 , wherein:
the account is associated with a group of recipients; and
the instructions further cause the system to identify the recipient from the group of recipients based on the intent.
23. The system of claim 8 , wherein the intent is transmitted to the recipient with the conversation history associated with the recipient and the sender of the request e-mail message, wherein the intent is incorporated into the conversation history.
24. The non-transitory, computer-readable medium of claim 13 , wherein:
the account is associated with a group of recipients; and
the executable instructions further cause the computer system to identify the recipient from the group of recipients based on the intent.
25. The non-transitory, computer-readable medium of claim 13 , wherein:
the account associated with the client is further associated with a skill; and
the recipient is identified as a result of the recipient being assigned to the skill.
26. The non-transitory, computer-readable medium of claim 13 , wherein the machine learning model is dynamically trained by soliciting the feedback corresponding to the identification of the intent from the request e-mail message.
27. The non-transitory, computer-readable medium of claim 13 , wherein the machine learning model is trained and updated in real-time as request e-mail messages are received.