Abstract
In response to a user’s request, a virtual assistant can direct the user to online resources that include relevant content. When the user follows a link to such a resource, the content shown to the user may include advertisements. However, the context of the user’s interaction with the virtual assistant is not incorporated when selecting the advertisements. This disclosure describes techniques to incorporate the details of prior user interactions with the virtual assistant as a factor in relevancy ranking of advertisements shown with recommended external content, such as videos, webpages, etc. The described techniques are implemented with specific user permission and users are provided with options to turn off use of interaction data for selection of advertisements.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Sharifi, Matthew and Carbune, Victor, "Ranking Advertisements Based On User Interactions With Virtual Assistant", Technical Disclosure Commons, (June 18, 2020)
https://www.tdcommons.org/dpubs_series/3347