Abstract: A device-cloud collaborative data mining method includes: A cloud determines a target text and a task configuration file based on a service requirement; encodes the target text by using a text encoder to obtain a text feature; and places the text feature in the task configuration file and delivers the task configuration file to a vehicle. The vehicle encodes image data by using a first picture encoder to obtain an image feature; calculates a value of a similarity between the text feature and the image feature; determines a target picture based on the value of the similarity and the task configuration file; and uploads the target picture to the cloud. The first picture encoder is obtained by compressing and tuning a second picture encoder, and the text encoder and the second picture encoder are two modules of a large image-text multimodal model.

Abstract: The embodiments of the present disclosure provide a system for calculating a regional crowd movement and a method thereof. The system is applied to a target monitoring environment, a plurality of key travel nodes are planned in the target monitoring environment, and the system includes radio frequency labels deployed on pedestrians, calculation apparatuses deployed at the key travel nodes and a plurality of directional antennas. The directional antenna is configured to, when driven by the calculation apparatus, send a read-write signal to the radio frequency label in a coverage region; the directional antenna is further configured to forward a radio frequency signal simultaneously reflected by the radio frequency label at the time of obtaining the read-write signal to the calculation apparatus; the calculation apparatus is configured to, based on a tempo-spatial distribution circumstance of the radio frequency signals in the region.