2results about How to "High density storage" patented technology

The invention discloses an integrated air-ground deployment system and method for an unmanned cluster. The system comprises a carrier and an air-ground integrated release module, and the air-ground integrated release module is arranged above the carrier and comprises a cavity for containing an unmanned cluster, a ground release assembly and an air release assembly; wherein the ground release assembly can open and close the cavity and release the unmanned aerial vehicles deployed in the unmanned cluster in a ground mode when the ground release assembly is in an open state; the air release assembly can open and close the cavity and release the unmanned aerial vehicles deployed in an air mode in the unmanned cluster when the air release assembly is in an open state; a first envelope space body formed by switching on and off the ground release assembly and a second envelope space body formed by switching on and off the air release assembly do not overlap. According to the invention, efficient and flexible deployment of the unmanned cluster in a complex task scene can be realized.

The application relates to an abnormal transaction behavior identification method and device, and relates to the technical field of information security, and solves the problems of high delay, large energy consumption and cross-institution data island of a traditional pure software scheme. The method comprises the following steps: converting transaction relationship data into a graph structure, wherein the nodes of the graph structure represent transaction parties, and the edges of the graph structure represent transactions; inputting an adjacency matrix of the graph structure into a spin-orbit torque magnetic random access memory, wherein the spin-orbit torque magnetic random access memory stores the weights of a graph neural network model; reading simulation convolution results generated by the spin-orbit torque magnetic random access memory from the adjacency matrix to obtain graph neural network features extracted from the graph structure by the graph neural network model; and inputting the graph neural network features into an abnormal transaction behavior evaluation model to obtain an evaluation result.