Abstract: The disclosure relates to a method, apparatus, system, medium and electronic device for graph neural network generation. The method includes: obtaining a subgraph structure, the subgraph structure being configured to reflect a graph structure of a corresponding subgraph, and the subgraph comprising a plurality of nodes and edges between the plurality of nodes; obtaining, based on the subgraph structure and according to a predetermined priority, node features of the plurality of nodes and edge features of the edges from a plurality of memories; the predetermined priority being obtained by sorting the plurality of memories in accordance with memory size in an ascending order; fusing, based on the subgraph structure, the node features of the plurality of nodes and the edge features of the edges to obtain subgraph data; and training, based on the subgraph data, the graph neural network.

Abstract: Disclosed are a method for processing neural network feature map using a plurality of accelerators. The method includes: reading first feature data about the neural network feature map from first shift register array in first accelerator among a plurality of neural network accelerators, and first weight data corresponding to the first feature data from first buffer; performing preset operation on the first feature data and first weight data using the first accelerator, to obtain a first operation result; shifting, according to preset shift rule, first overlapping feature data in the first feature data and required by a second accelerator to a second shift register array of the second accelerator; and performing a preset operation on the second feature data from the second shift register array including the first overlapping feature data and the read second weight data using the second accelerator, to obtain a second operation result.

Abstract: Embodiments of the present disclosure provide method and apparatus for changing radio access technology. A method performed by a network device comprises obtaining channel estimation information of a terminal device; determining an uplink power value according to the channel estimation information and a number of antennas to be used; and transmitting the uplink power value to the terminal device periodically.

Abstract: An antimicrobial detergent composition includes the following components by mass percent: 0.1-10% of a polyester-polyether polymer, 0.01-2% of an antimicrobial agent with a halogenated phenol structure, 10-50% of a surfactant and a solvent. A 1% deionized water solution of the detergent composition has a pH value of 7.0-9.0. In the present invention, by introducing the polyester-polyether polymer into the composition, the deposition efficiency of the antimicrobial agent with the halogenated phenol structure on a fabric can be improved, a solubilization effect of the surfactant in a detergent can be reduced, and therefore, a antimicrobial effect is achieved.