Abstract: 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.

Abstract: A method 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 can include receiving, via a computer network, a user interaction signal from a user device for a user. The method further can include after receiving the user interaction signal, determining, in real-time via a machine learning model, a plurality of user intent labels based at least in part on transaction data, interaction data, and incident data for the user. The machine learning model can include pre-trained based on historical input data and historical output data associated with multiple users comprising the user. The historical input data can comprise historical feature embedding vectors for historical transaction data, historical interaction data, and historical incident data associated with the multiple users.

Abstract: A method 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 can include receiving, via a computer network, an intent prediction request from a frontend system. The method further can include obtaining, from a database, one or more events in a lookback period associated with one or more items ordered by a user for the intent prediction request. The method also can include determining a time-based feature encoding for the one or more events for the user by: (a) determining a feature encoding for the one or more events; (b) determining a positional encoding for the one or more events; and (c) determining the time-based feature encoding based at least in part on the feature encoding, the positional encoding, and a decay function. The positional encoding can include one or more positional vectors associated with a temporal sequence of the one or more events.

Abstract: A method 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 can include receiving, via a computer network, a user interaction signal from a user device for a user. The method further can include after receiving the user interaction signal, determining, in real-time via a machine learning model, a plurality of user intent labels based at least in part on transaction data, interaction data, and incident data for the user. The machine learning model can include pre-trained based on historical input data and historical output data associated with multiple users comprising the user. The historical input data can comprise historical feature embedding vectors for historical transaction data, historical interaction data, and historical incident data associated with the multiple users.