Computer-implemented methods for searching over the internet, databases, methods of producing such databases, and related systems and computer program products
A machine learning model predicts when to stop polling early in travel searches, optimizing energy usage and response time in internet search processes.
Patent Information
- Application Number
- PCT/GB2024/053037
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-09-18
- Filing Date
- 2024-12-05
- Publication Date
- 2025-12-18
AI Technical Summary
The increasing energy consumption associated with internet search activities and the desire for quicker, more pertinent results necessitate the development of methods to optimize search processes.
A computer-implemented method using a trained machine learning model to predict when to stop polling early in travel searches by determining a cumulative number of distinct responses, converting these into model travel search parameters, and generating an output indicator to stop polling before a predetermined time, allowing continued searches in the backend for future training.
This approach reduces energy consumption and delivers processed distinct responses sooner to the user terminal while maintaining efficient search functionality.