Dynamic response prediction for improved bot task processing
Systems and methods can be provided for predicting responses during communication sessions with network devices. In some implementations, systems and methods can facilitate predicting responses using machine learning techniques. Messages received through a platform can be stored in a repository. A machine learning model may be trained using the stored messages. When a terminal device is communicating with a network device in a communication session, the messages exchanged in the communication session and the machine learning model can be used to predict future responses in real-time. The predicted future responses can be presented at the terminal device. A predicted response can be selected at the terminal device. Upon selection, the selected predicted response is transmitted to the network device during the communication session.
1. A computer-implemented method comprising:
receiving a message during a communication session, wherein the message is associated with a user;
routing the message and additional messages of the communication session to a bot;
identifying an anchor in the communication session, wherein the anchor includes a string of text associated with a polarity, and wherein the polarity corresponds to a positive sentiment or a negative sentiment;
determining a message parameter using the anchor;
comparing in real-time the message parameter of the communication session to a threshold;
automatically transferring the communication session upon determining the message parameter satisfies the threshold, wherein when the message parameter satisfies the threshold, the communication session is transferred from the bot to an agent;
determining a parameter value associated with the message, wherein the parameter value includes the anchor;
predicting a response to the message by inputting the parameter value into a machine-learning model to determine a selected message, wherein the machine-learning model is trained using values of anchors associated with candidate messages; and
facilitating displaying the selected message, wherein when the selected message is selected by the agent, the selected message is automatically added to the communication session.
2. The computer-implemented method of claim 1 , wherein:
the parameter value includes a number of words, a number of messages exchanged, a number of characters, or a number of non-word characters.
3. The computer-implemented method of claim 1 , wherein the message parameter is a dynamic sentiment parameter.
4. The computer-implemented method of claim 1 , wherein the message parameter uses a characteristic of previous messages in previous communication sessions.
5. The computer-implemented method of claim 1 ,
wherein predicting the response to the message comprises grouping the candidate messages into a cluster, and
the method further includes determining a similarity between the message and the candidate messages in the cluster by executing a confidence algorithm to determine a confidence score.
6. The computer-implemented method of claim 1 , further comprising:
collecting a data set for training the machine-learning model, wherein collecting the data set includes storing previous messages included in previous communication sessions between network devices and terminal devices.
7. The computer-implemented method of claim 1 , further comprising:
collecting agent responses to messages in previous communication sessions between network devices and terminal devices.
8. The computer-implemented method of claim 1 , further comprising:
transmitting the selected message; and
updating one or more databases with training data associated with the message and the selected message.
9. The computer-implemented method of claim 1 , further comprising:
evaluating performance of the bot using the message parameter.
10. The computer-implemented method of claim 1 , further comprising:
reprogramming the bot to enhance future communication sessions.
11. The computer-implemented method of claim 1 , further comprising:
training the machine-learning model using the selected message and a feedback signal.
12. The computer-implemented method of claim 1 , further comprising:
determining a new parameter value associated with a new message, wherein the new parameter value includes a new anchor different from the anchor; and
predicting a new response to the new message by inputting the new parameter value into the machine-learning model to determine a second message, wherein the second message is different from the selected message.
13. A system comprising:
one or more data processors; and
a non-transitory computer-readable storage medium containing instructions which, when executed on the one or more data processors, cause the one or more data processors to perform a method including:
receiving a message during a communication session, wherein the message is associated with a user;
routing the message and additional messages of the communication session to a bot;
identifying an anchor in the communication session, wherein the anchor includes a string of text associated with a polarity, and wherein the polarity corresponds to a positive sentiment or a negative sentiment;
determining a message parameter using the anchor;
comparing in real-time the message parameter of the communication session to a threshold;
automatically transferring the communication session upon determining the message parameter satisfies the threshold, wherein when the message parameter satisfies the threshold, the communication session is transferred from the bot to an agent;
determining a parameter value associated with the message, wherein the parameter value includes the anchor;
predicting a response to the message by inputting the parameter value into a machine-learning model to determine a selected message, wherein the machine-learning model is trained using values of anchors associated with candidate messages; and
facilitating displaying the selected message, wherein when the selected message is selected by the agent, the selected message is automatically added to the communication session.
14. The system of claim 13 , wherein:
the parameter value includes a number of words, a number of messages exchanged, a number of characters, or a number of non-word characters.
15. The system of claim 13 , wherein the method further includes:
reprogramming the bot to enhance future communication sessions.
16. A computer-program product tangibly embodied in a non-transitory machine-readable storage medium, including instructions configured to cause a data processing apparatus to perform a method including:
receiving a message during a communication session, wherein the message is associated with a user;
routing the message and additional messages of the communication session to a bot;
identifying an anchor in the communication session, wherein the anchor includes a string of text associated with a polarity, and wherein the polarity corresponds to a positive sentiment or a negative sentiment;
determining a message parameter using the anchor;
comparing in real-time the message parameter of the communication session to a threshold;
automatically transferring the communication session upon determining the message parameter satisfies the threshold, wherein when the message parameter satisfies the threshold, the communication session is transferred from the bot to an agent;
determining a parameter value associated with the message, wherein the parameter value includes the anchor;
predicting a response to the message by inputting the parameter value into a machine-learning model to determine a selected message, wherein the machine-learning model is trained using values of anchors associated with candidate messages; and
facilitating displaying the selected message, wherein when the selected message is selected by the agent, the selected message is automatically added to the communication session.
17. The computer-program product of claim 16 , wherein the method further includes:
evaluating performance of the bot using the message parameter.
18. The computer-program product of claim 16 , wherein the method further includes:
reprogramming the bot to enhance future communication sessions.
19. The computer-program product of claim 16 , wherein the method further includes:
training the machine-learning model using the selected message and a feedback signal.
20. The system of claim 13 , wherein the method further includes:
determining a new parameter value associated with a new message, wherein the new parameter value includes a new anchor different from the anchor; and
predicting a new response to the new message by inputting the new parameter value into the machine-learning model to determine a second message, wherein the second message is different from the selected message.