Enhanced digital messaging
Embodiments of the disclosure provide a method of processing messages received in an asynchronous communication system. In some embodiments, the method includes receiving a message from a customer communication device, determining that a conversation is already established in association with the customer communication device, including the message among a plurality of messages that are already assigned to the conversation, analyzing the message to determine a topic classification and a topic confidence score for the message, and based on the analysis of the message, determining whether the topic classification determined for the message corresponds to a continuation of a topic classification for the plurality of messages or whether the topic classification determined for the message corresponds to a different topic classification than the topic classification for the plurality of messages.
1. A method of processing messages received in an asynchronous communication system, the method comprising:
receiving a message from a customer communication device;
determining that a conversation is already established in association with the customer communication device;
including the message among a plurality of messages that are already assigned to the conversation;
analyzing the message to determine a topic classification and a topic confidence score for the message;
based on the analysis of the message, determining whether the topic classification determined for the message corresponds to a continuation of a topic classification for the plurality of messages or whether the topic classification determined for the message corresponds to a different topic classification than the topic classification for the plurality of messages;
determining that the topic confidence score exceeds a predetermined confidence threshold;
in response to determining that the topic confidence score exceeds the predetermined confidence threshold, comparing the topic classification determined for the message with the topic classification for the plurality of messages;
determining that a match exists between the topic classification determined for the message with the topic classification for the plurality of messages; and
in response to the topic confidence score exceeding the predetermined confidence threshold and in response to determining that the match exists between the topic classification determined for the message with the topic classification for the plurality of messages, providing an indication with the message that indicates a result of determining whether the topic classification determined for the message corresponds to the continuation of the topic classification for the plurality of messages or whether the topic classification determined for the message corresponds to the different topic classification than the topic classification for the plurality of messages, wherein the indication provided with the message indicates that the message corresponds to the continuation of the topic classification for the plurality of messages.
2. The method of claim 1 , wherein the indication comprises at least one of a visual and audible indication.
3. The method of claim 1 , further comprising:
receiving a second message from the customer communication device;
analyzing the second message to determine a second topic classification and a second topic confidence score for the second message;
determining that the second topic confidence score fails to meet or exceed the predetermined confidence threshold; and
in response to determining that the second topic confidence score fails to meet or exceed the predetermined confidence threshold, indicating that the second message corresponds to the continuation of the topic classification for the plurality of messages.
4. The method of claim 1 , further comprising:
receiving a second message from the customer communication device;
analyzing the second message to determine a second topic classification and a second topic confidence score for the second message;
determining that the second topic confidence score exceeds the predetermined confidence threshold;
in response to determining that the second topic confidence score exceeds the predetermined confidence threshold, comparing the second topic classification determined for the second message with the topic classification for the plurality of messages;
determining that a match does not exist between the second topic classification determined for the second message with the topic classification for the plurality of messages; and
in response to the second topic confidence score exceeding the predetermined confidence threshold and in response to determining that the match does not exist between the second topic classification determined for the second message with the topic classification for the plurality of messages, indicating that the second message corresponds to the different topic classification.
5. The method of claim 1 , further comprising:
determining an amount of time between receipt of the message and a most recent message from among the plurality of messages; and
considering the amount of time as part of determining whether the topic classification determined for the message corresponds to the continuation of the topic classification for the plurality of messages or whether the topic classification determined for the message corresponds to the different topic classification than the topic classification for the plurality of messages.
6. The method of claim 1 , wherein content of the message is analyzed by a natural language processing unit as part of analyzing the message.
7. The method of claim 1 , wherein metadata of the message is analyzed as part of analyzing the message.
8. The method of claim 1 , wherein the message comprises a digital message received over a first communication channel and wherein at least one message from the plurality of messages is received over a second communication channel that is different from the first communication channel.
9. A communication system, comprising:
a processor; and
computer memory storing data thereon that enables the processor to:
receive a message from a customer communication device;
determine that a conversation is already established in association with the customer communication device;
analyze the message to determine a topic classification and a topic confidence score for the message;
determine an amount of time between receipt of the message and a most recent message from among a plurality of messages;
based on the analysis of the message, determine whether the topic classification determined for the message corresponds to a continuation of a topic classification for the plurality of messages already assigned to the conversation or whether the topic classification determined for the message corresponds to a different topic classification than the topic classification for the plurality of messages, wherein the amount of time is considered as part of determining whether the topic classification determined for the message corresponds to the continuation of the topic classification for the plurality of messages or whether the topic classification determined for the message corresponds to the different topic classification than the topic classification for the plurality of messages; and
indicate a result of determining whether the topic classification determined for the message corresponds to the continuation of the topic classification for the plurality of messages or whether the topic classification determined for the message corresponds to the different topic classification than the topic classification for the plurality of messages.
10. The communication system of claim 9 , wherein the data stored on the computer memory further enables the processor to:
determine that the topic confidence score exceeds a predetermined confidence threshold;
in response to determining that the topic confidence score exceeds the predetermined confidence threshold, compare the topic classification determined for the message with the topic classification for the plurality of messages;
determine that a match exists between the topic classification determined for the message with the topic classification for the plurality of messages; and
in response to the topic confidence score exceeding the predetermined confidence threshold and in response to determining that the match exists between the topic classification determined for the message with the topic classification for the plurality of messages, indicate that the message corresponds to the continuation of the topic classification for the plurality of messages.
11. The communication system of claim 9 , wherein the data stored on the computer memory further enables the processor to:
determine that the topic confidence score fails to meet or exceed a predetermined confidence threshold; and
in response to determining that the topic confidence score fails to meet or exceed the predetermined confidence threshold, indicate that the message corresponds to the continuation of the topic classification for the plurality of messages.
12. The communication system of claim 9 , wherein the data stored on the computer memory further enables the processor to:
determine that the topic confidence score exceeds a predetermined confidence threshold;
in response to determining that the topic confidence score exceeds the predetermined confidence threshold, compare the topic classification determined for the message with the topic classification for the plurality of messages;
determine that a match does not exist between the topic classification determined for the message with the topic classification for the plurality of messages; and
in response to the topic confidence score exceeding the predetermined confidence threshold and in response to determining that the match does not exists between the topic classification determined for the message with the topic classification for the plurality of messages, indicate that the message corresponds to the different topic classification.
13. The communication system of claim 9 , wherein the indication comprises at least one of a visual and audible indication.
14. The communication system of claim 9 , wherein content of the message is analyzed with a neural network as part of analyzing the message.
15. The communication system of claim 9 , wherein metadata of the message is analyzed as part of analyzing the message.
16. A contact center, comprising:
a server comprising a processor and a chatbot engine that is executable by the processor and that enables the processor to:
receive a message from a customer;
determine that a conversation is already established in association with the customer;
analyze the message to determine a topic classification and a topic confidence score for the message;
based on the analysis of the message, determine that the topic confidence score fails to meet or exceed a predetermined confidence threshold; and
in response to determining that the topic confidence score fails to meet or exceed the predetermined confidence threshold, indicate that the topic classification determined for the message corresponds to a continuation of a topic classification for a plurality of messages already assigned to the conversation.
17. The contact center of claim 16 , wherein the chatbot engine further enables the processor to:
receive a second message from the customer;
analyze the second message to determine a second topic classification and a second topic confidence score for the second message;
determine that the second topic confidence score exceeds the predetermined confidence threshold;
in response to determining that the second topic confidence score exceeds the predetermined confidence threshold, compare the second topic classification determined for the second message with the topic classification for the plurality of messages;
determine that a match exists between the second topic classification determined for the second message with the topic classification for the plurality of messages; and
in response to the second topic confidence score exceeds the predetermined confidence threshold and in response to determining that the match exists between the second topic classification determined for the second message with the topic classification for the plurality of messages, indicate that the second message corresponds to the continuation of the topic classification for the plurality of messages.
18. The contact center of claim 16 , wherein the processor analyzes the message with a natural language processing unit.
19. The contact center of claim 16 , wherein the chatbot engine further enables the processor to:
receive a second message from the customer;
analyze the second message to determine a second topic classification and a second topic confidence score for the second message;
determine that the second topic confidence score exceeds the predetermined confidence threshold;
in response to determining that the second topic confidence score exceeds the predetermined confidence threshold, compare the second topic classification determined for the second message with the topic classification for the plurality of messages;
determine that a match does not exist between the second topic classification determined for the second message with the topic classification for the plurality of messages; and
in response to the second topic confidence score exceeding the predetermined confidence threshold and in response to determining that the match does not exist between the second topic classification determined for the second message with the topic classification for the plurality of messages, indicate that the second message corresponds to a different topic classification.
20. The contact center of claim 16 , wherein the chatbot engine further enables the processor to:
determine an amount of time between receipt of the message and a most recent message from among the plurality of messages; and
consider the amount of time as part of determining that the topic classification determined for the message corresponds to the continuation of the topic classification for the plurality of messages.