Abstract

Conversational artificial intelligence platforms can face challenges when integrating commercial content, as some advertising formats may disrupt a user's conversational experience. To address this, systems and methods are described for dynamically generating a synchronized, dual-payload response to a user query that has commercial intent. This response can comprise a natural language text component that maintains the conversational flow, alongside a structured, client-neutral data schema. This schema can define an interactive user interface widget, such as a personalized calculator or product configurator, that is rendered inline within a chat interface. A system can also use a personal authorization bridge for privacy-preserving personalization. This technique can enable the integration of sponsored content as a functional utility that may assist a user's decision-making process directly within the conversational context, potentially reducing a need for users to switch to external applications or websites.

Creative Commons License

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

Share

COinS