Parking lot recommendation method and device based on historical data and distributed system

• Main Authors: LI CAIBO, WANG XUN, AI RUFEI, QIN SHAOYANG, SHI TAOYUAN
• Format: Patent
• Language: Chinese; English
• Published: 27.10.2023
• Subjects: PHYSICS; SIGNALLING; TRAFFIC CONTROL SYSTEMS

The invention provides a parking lot recommendation method and device based on historical data and a distributed system, and relates to the technical field of data processing, and the method comprises the steps: building an initial model set in advance, and the initial model set comprises a plurality of initial models corresponding to each parking lot; acquiring historical data of each parking lot as training data, training the historical data of each parking lot to obtain a target model set, each target model being used for predicting departure time and departure probability of each vehicle in a target time period of the corresponding parking lot to determine a vehicle distribution state of the parking lot in the target time period; acquiring real-time data of each parking lot, and establishing a dynamically changing real-time parking database based on the target model set; establishing a parking scoring model, and scoring each target parking lot to perform parking lot recommendation on the target vehicle; t