3results about How to "Improve deliverability" patented technology

The application discloses a reservoir intelligent inversion method and related device, relates to the technical field of reservoir intelligent inversion, and comprises the following steps: obtaining multi-source heterogeneous data of a target area and preprocessing; constructing an initial geological model generator based on a conditional diffusion model, and optimizing hidden space parameters in a manner of seismic wave forward simulation; constructing a reservoir knowledge graph and adaptively pretraining and migrating the model online; performing task demand analysis, task decomposition and dynamic collaborative execution on a reservoir modeling task based on a thinking chain technology and a language large model technology, and obtaining iteratively optimized hidden space parameters; inputting the iteratively optimized hidden space parameters into the optimized geological model generator, outputting a three-dimensional distribution model, and extracting a confidence interval feature; incrementally updating the reservoir knowledge graph, determining a reservoir model conforming to a geological mode feature and matching a seismic waveform, and realizing reservoir intelligent inversion. The application can improve the accuracy and efficiency of reservoir inversion.

The present application relates to the technical field of underground engineering seepage inversion, in order to improve the accuracy of the generation of the permeation tensor field, a three-dimensional seepage field inversion analysis method suitable for anisotropic rock mass is provided, the drilling lithology, the occurrence of structural plane, the segmented water pressure, the water level monitoring, the excavation surface groundwater inflow, the recharge boundary and the excavation surface data are mapped to the three-dimensional unit to form the permeation tensor generation condition; the reserved parameters and the parameters to be updated are divided in the condition normalization flow affine coupling layer, the conduction relationship graph is constructed based on the reserved parameters, the random walk absorption probability and the direction change amount are calculated, and the scale parameter and the translation parameter generation link are embedded to update the tensor parameters; the three-dimensional anisotropic permeation tensor field and the directed connected state are output by matching the water level and the inflow response, and the accuracy of the generation of the permeation tensor field is improved.

The invention discloses an electric power infrastructure project risk assessment method based on a multi-factor dynamic weighting algorithm, and belongs to the technical field of project management, and the method comprises the steps: carrying out the noise filtering of original business flow data, and carrying out the normalization compression of a filtered data field, and obtaining a standardized data set; performing factor stripping on the standardized data set to obtain an original risk factor pedigree; performing weight assignment on the original risk factor pedigree to obtain an initial weight assignment factor set; calling a weight correction coefficient matrix in a preset benchmark item database, and performing dynamic iteration calibration on the initial weight value to obtain a stage weight vector; performing empowerment reconstruction on the initial empowerment factor set to obtain a risk feature vector; performing fuzzy membership degree matching on the risk feature vector to obtain an evaluation conclusion; and carrying out standardized packaging on the assessment conclusion, the risk feature vector and the stage weight vector to obtain a risk assessment data message. According to the invention, the accuracy and efficiency of risk assessment of the power infrastructure project can be improved.