6 results about "Structure chart" patented technology

The invention provides an information detection method, device and equipment, a medium and a program product, which can be applied to the technical field of artificial intelligence. The information detection method comprises the following steps: acquiring a social network structure chart and to-be-detected information; performing feature extraction on the to-be-detected information to obtain a semantic feature vector; constructing multiple groups of cue words based on the to-be-detected information and the social network structure chart, and performing propagation graph simulation based on the multiple groups of cue words to obtain a propagation graph representing a propagation path of the to-be-detected information; feature extraction is carried out on the propagation graph to obtain a propagation graph feature vector, and the propagation graph feature vector represents structure information of the propagation graph and behavior information of the user nodes; and inputting the semantic feature vector and the propagation graph feature vector into a trained prediction neural network to obtain a detection result of the to-be-detected information.

The invention provides an intelligent manufacturing digital twinning whole process management and control method and platform based on a swan gap system, and the method comprises the steps: constructing a process structure chart according to a manufacturing process, and collecting operation parameters through a state collection port; and constructing a current state vector of each node according to the operation parameters, and obtaining an operability mark of each node according to the precursor node set, the current state vector and a state linkage rule. The node of the operable mark is defined as a target node. And generating a plurality of candidate control strategies of each target node according to the strategy parameter template, the current state vector and the current equipment margin. And obtaining a cost evaluation value of each candidate control strategy according to the cost function. The candidate control strategy corresponding to the minimum cost evaluation value is defined as a target control strategy. And sending the target control strategy to a controller for execution. The whole-process modeling capability with the process dependency relationship as the framework is achieved, and when the production line rhythm or the equipment load changes, the scheduling logic can also be automatically adapted accordingly.

The invention relates to a circuit layout method and device, equipment, a storage medium and a program product. The circuit layout method comprises the following steps: searching a repetitive unit group with the same topological structure as that of a layout template in a circuit topological structure chart, wherein the repetitive unit group comprises a plurality of circuit units; multiple repetitive unit groups corresponding to the same layout template are aggregated into independent layout units, and the multiple repetitive unit groups corresponding to the same layout template have the same relative position relation between circuit units after layout; and carrying out layout on the independent layout units. The layout design efficiency is remarkably improved, layout errors caused by manual operation are avoided, and the layout design accuracy is improved.

The application discloses a kind of ship structure standardization design data analysis methods based on AI, comprising the following steps: using unlabeled data to carry out bimodal self-supervised pre-training to HGT, through geometric attribute cover prediction and edge existence prediction, loss is optimized jointly;Obtain the labeled ship structure chart data;Parallelly embed error transmission module in pre-training model, obtain final cumulative error;The labeled data is input into the HGT after embedding error transmission module, calculate size prediction loss, assembly constraint loss, and obtain fine-tuning model by optimizing jointly;Target structure chart data is input into fine-tuning model, and each node design size prediction value and tolerance band are output;Standardized design data is generated.The application realizes the efficient reuse and construction process cooperation of ship structure design data, and improves the design standardization degree and engineering adaptability.

The invention belongs to the technical field of computers, and discloses a software development project management method and system based on an incremental model, and the method comprises the steps: receiving external change data, mapping the external change data into a target node in a structure chart based on the structure chart of a preset software system, and calculating the structural stability parameter of the target node, judging whether a preset structure change threshold value is reached or not, if so, marking the node as a fission trigger node, and outputting an identifier and adjacency information; fission trigger nodes and adjacency information are received, based on the structure diagram, a structure splitting function is used for executing sub-diagram cutting operation on the affected area, different structure sub-diagrams are constructed, and a structure sub-diagram set and corresponding sub-diagram function information are output; mapping the sub-graph function information to a unified function expression space through a preset function semantic mapping rule, and outputting a unified function expression vector group and a corresponding cooperative relationship matrix; and the overall execution efficiency of the project and the resource use efficiency are improved.

The invention relates to the technical field of software engineering, in particular to a source code fault positioning method based on heterogeneous decoupling and gating fusion, which comprises the following steps of: establishing a unified coverage graph based on a to-be-tested program code, a test code and a result of performing automatic test by utilizing the test code; decoupling the unified coverage graph to obtain a code structure graph and a test coverage graph; encoding the test coverage graph and the code structure graph by adopting a heterogeneous graph neural network, and performing dynamic test embedding and static structure embedding on each node; dynamic test embedding and static structure embedding of the nodes are spliced, and final comprehensive embedding of the code nodes is obtained through gating information spreading; performing full-connection linear layer processing on the final comprehensive embedding of each code node, and outputting a suspicious degree score; the suspicious degree scores of all the nodes are arranged in a descending order to serve as a fault positioning result; the method can improve the fault positioning effect of the graph neural network.