Abstract: The present invention discloses a low signal-to-noise ratio (SNR) seismic event detection model based on a deep residual shrinkage network (DRSN). Considering the different noises contained in seismic records acquired by different seismic sensors, a DRSN based on a residual network was constructed to detect seismic events from low SNR seismic records. In the constructed network, a soft thresholding function (a shrinkage function) was inserted into the deep network structure as a nonlinear transform layer to effectively filter the impact of noise-related features, and an attention mechanism, together with an adaptive soft thresholding block, was also incorporated to automatically obtain the optimal denoising threshold for seismic signals, which ensures different signals are processed to the best effect. After training, the DRSN adaptively determines the denoising threshold so that each seismic signal has its own threshold set and seismic events can be accurately detected under strong background noise.

Abstract: Embodiments of this disclosure provide a data processing method, apparatus, and device, and a computer readable storage medium. In the embodiments of this disclosure, an unassigned order group of each of at least two distribution services is obtained; a status indicator of a distribution person is determined; a distribution indicator of the unassigned order group is determined; and the unassigned order group is assigned to a matched distribution person based on the distribution indicator and the status indicator. In this way, distribution orders of at least two distribution services can be jointly scheduled, thereby reducing distribution costs, saving distribution resources, and increasing a distribution resource utilization rate.

Abstract: Embodiments of the present invention provide a data object allocation method and apparatus and an electronic device. The method includes: pre-allocating a to-be-allocated data object to a first terminal, where the to-be-allocated data object is grouped into a data object group; simulating processing of the data object group by the first terminal and a second terminal associated with the data object group; and allocating the to-be-allocated data object to the first terminal if two simulation results meet a preset condition. According to the embodiments of the present invention, data object allocation efficiency is enhanced, and overall processing effect is optimized.