Personalizing user interface displays in real-time
A method can include receiving a signal from a user device of a user. The method can further include processing, via a machine learning model, user intent labels, wherein: the machine learning model is pre-trained based on historical input data and historical output data associated with multiple users comprising the user, the historical input data comprise historical feature embedding vectors associated with the multiple users, and the historical output data comprise historical intent labels based at least in part on uttered intents of the multiple users. The method can also include processing one or more user intent candidates of the user intent labels. The method can further include processing one or more user interface components for the one or more user intent candidates. Additionally, the method can include transmitting the one or more user interface components to be presented on a user interface executed on the user device of the user. Other embodiments are described.
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform:
receiving a signal from a user device of a user;
processing, via a machine learning model, user intent labels, wherein:
the machine learning model is pre-trained based on historical input data and historical output data associated with multiple users comprising the user;
the historical input data comprise historical feature embedding vectors associated with the multiple users; and
the historical output data comprise historical intent labels based at least in part on uttered intents of the multiple users;
processing one or more user intent candidates of the user intent labels;
processing one or more user interface components for the one or more user intent candidates; and
transmitting the one or more user interface components to be presented on a user interface executed on the user device of the user.
2. The system of claim 1 , wherein the historical feature embedding vectors generated based on historical transaction data, historical interaction data, and historical incident data associated with the multiple users.
3. The system in claim 2 , wherein:
the historical transaction data comprises one or more transactions for the user within a transaction time window.
4. The system in claim 2 , wherein:
the historical interaction data comprises one or more interactions for the user occurring within an interaction time window.
5. The system in claim 2 , wherein:
the historical incident data comprises one or more incidents handled by agents for the user within an incident time window.
6. The system in claim 2 , wherein:
the historical feature embedding vectors are further generated based on historical conversation data associated with the multiple users.
7. The system in claim 2 , wherein:
the historical intent labels are further based at least in part on historical intent categories provided by agents for the historical incident data.
8. The system in claim 1 , wherein:
the machine learning model is further pre-trained to process the uttered intents of the multiple users.
9. The system in claim 1 , wherein:
the machine learning model is further pre-trained to process the user intent labels by a classification algorithm.
10. The system in claim 1 , wherein:
processing the one or more user intent candidates further comprises processing the one or more user intent candidates based on a candidate count threshold.
11. A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
receiving a signal from a user device of a user;
processing, via a machine learning model, user intent labels, wherein:
the machine learning model is pre-trained based on historical input data and historical output data associated with multiple users comprising the user;
the historical input data comprise historical feature embedding vectors associated with the multiple users; and
the historical output data comprise historical intent labels based at least in part on uttered intents of the multiple users;
processing one or more user intent candidates of the user intent labels;
processing one or more user interface components for the one or more user intent candidates; and
transmitting the one or more user interface components to be presented on a user interface executed on the user device of the user.
12. The method of claim 11 , wherein the historical feature embedding vectors generated based on historical transaction data, historical interaction data, and historical incident data associated with the multiple users.
13. The method in claim 12 , wherein:
the historical transaction data comprises one or more transactions for the user within a transaction time window.
14. The method in claim 12 , wherein:
the historical interaction data comprises one or more interactions for the user occurring within an interaction time window.
15. The method in claim 12 , wherein:
the historical incident data comprises one or more incidents handled by agents within an incident time window.
16. The method in claim 12 , wherein:
the historical feature embedding vectors are further generated based on historical conversation data associated with the multiple users.
17. The method in claim 12 , wherein:
the historical intent labels are further based at least in part on historical intent categories provided by agents for the historical incident data.
18. The method in claim 11 , wherein:
the machine learning model is further pre-trained to process the uttered intents of the multiple users.
19. The method in claim 12 , wherein:
the machine learning model is further pre-trained to process the user intent labels by a classification algorithm.
20. The method in claim 11 , wherein:
processing the one or more user intent candidates further comprises processing the one or more user intent candidates based on a candidate count threshold.