The invention relates to the technical field of
big data analysis, in particular to an order matching method based on a
knowledge graph. Obtaining order data to be processed, performing multi-
modal feature extraction on the order data to obtain order
feature data, and mapping in the
knowledge graph to generate cargo entity nodes; calling a vehicle model node in the
knowledge graph, and executing multi-dimensional matching
verification based on the cargo entity node and the vehicle model node, including verifying geometric suitability based on a cargo
voxel set and an effective loading
voxel module, verifying operation
operability based on an operation entry vector and a loading and unloading port vector set, and verifying the operation
operability based on the cargo
voxel set and the effective loading voxel module. Carrying out transportation
suitability analysis based on historical portrait data driving; the vehicles passing the
verification are screened to generate a
single vehicle scheme; meanwhile, a load
decomposition algorithm is executed to disassemble cargo entity nodes into subtasks, a vehicle combination is retrieved, behavior consistency
verification is carried out based on historical tracks and speed collaborative entropy, and a multi-vehicle collaborative scheme is generated; and outputting a candidate scheme set including the single-vehicle scheme and the multi-vehicle cooperation scheme.