Current mechanisms to discover sightseeing routes in a given location or plan a multi-destination trip do not take into account all factors and constraints that are important to users. Users find it difficult to find routing that can optimally combine time, cost, and other constraints for multi-destination trips. This disclosure describes techniques for finding optimal routing that balances a number of relevant factors and constraints, such as distances, travel times, costs, traffic, travel modes, weather, scenery, crowd, noise, opening hours, etc. Users can seek optimal routing by providing a list of destinations or issuing a natural language query that can be processed via a large language model (LLM). For example, the LLM can generate a list of destinations based on a natural language query provided by the user. If users permit, the routing can be personalized by using a trained machine learning model that can consider a user’s individual preferences and context. The route can be augmented with personalized advertisements recommending relevant opportunities along the route.

Creative Commons License

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