Abstract

The technology described in this paper relates to identifying relevant advertisements (“ads”) based on a textual conversation, e.g., chat, between a user and an agent and generating a text-based natural language advertisement that fits the context of the conversation. A natural language query is generated based on the conversation between the user and the agent to identify relevant ads. The query is transmitted to an advertising system that can identify the relevant ads based on the context of the conversation and/or additional signals. An artificial intelligence (“AI”) model, such as a large language model (“LLM”), converts the relevant ad into a custom, text-based, natural language ad that fits within the context of the conversation between the user and the agent.

Creative Commons License

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

Share

COinS