The latency of response from a virtual assistant to a user query is an important performance parameter. However, often it is the perception of latency that drives the user’s experience and thereby, adoption/use of a virtual assistant. Skeleton screens can be used for pre-answering a query, e.g., working out a partial answer based on a partial query. This disclosure describes techniques to predict the collection of intents associated with a partial user query and automatically rendering an appropriate skeleton screen substantially earlier during the user interaction with a virtual assistant or other user interface.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.