11 results about "Test graph" patented technology

The application relates to the technical field of software test automation, and provides a requirement-driven test case automatic generation method and system based on a semantic test graph, which comprises the following steps: performing multidimensional static analysis on source code, respectively constructing an abstract syntax tree, a control flow graph and a function call graph, and extracting function call relations and data flow dependency relations; constructing a semantic test graph by taking functions as nodes, taking function call relations as main edges and taking data flow dependency relations as auxiliary edges, and aggregating function nodes in the semantic test graph into several function modules; obtaining several test requirement nodes, calculating semantic similarity between the test requirement nodes and the function modules, establishing a mapping relationship from the test requirement nodes to the function modules, and forming a requirement-program structure association graph; and based on the requirement-program structure association graph, generating a test intention for each test requirement node, and converting the test intention into an executable test case. The highly corresponding relationship between the generated test case and the business requirement is ensured.

The invention provides a graph anomaly detection method and system based on self-evolution during testing, and the method comprises the steps: S1, extracting the node representation of a test graph through a pre-trained graph neural network, and dynamically generating a prompt vector matched with the node dimension through a lightweight prompt generator; s2, performing element-level addition fusion on the prompt vector and the node representation of the original test graph to generate a prompt enhancement graph; s3, energy values of all nodes in the original test graph and the prompt enhancement graph are calculated respectively, and potential abnormal nodes are identified based on the energy change ratio; and S4, constructing an energy preference optimization loss function, updating prompt generator parameters through back propagation iteration, taking the current prompt enhancement graph as a next round of iteration input, forming automatic closed-loop optimization until convergence, and outputting a final anomaly detection score. According to the method, on the premise that original training data does not need to be accessed, the detection capability of the graph neural network on the abnormal graph is effectively improved through a self-improved iterative optimization mechanism.

The invention discloses a condition query-oriented adaptive inductive knowledge graph reasoning method and system, and relates to the technical field of knowledge graph reasoning. Obtaining an induction test chart and a target query containing a head entity and a query relationship; performing full-graph pre-coding on the induction test graph, screening related initial entities to construct an initial sub-graph, and generating a node initial representation; building a query perception graph neural network, carrying out normalization weighting on tail entity edge grouping by combining a conditional query attention mechanism through multi-layer message passing, and dynamically updating node representation by an adaptive residual information fusion strategy; a relation sensing double decoder composed of a symmetric MLP decoder and an antisymmetric ComplEx decoder is adopted, and scoring results are fused through a relation-level gating mechanism; and sorting the candidate tail entities according to the scores and outputting a reasoning result. According to the method, the suitability of query conditions and structure evidences is enhanced, the over-smoothing problem is relieved, the complex relation modeling capacity is improved, and collaborative optimization of induction reasoning precision and calculation efficiency is achieved.

The application provides a hardware test method, device, equipment and storage medium. The method comprises the following steps: dividing a test graph into at least two sub test graphs, wherein each sub test graph comprises a×b regions, a and b are both integers equal to or greater than 2; generating a sub graph state array, wherein the sub graph state array is used for recording the test state of the regions in the sub test graph; performing the following processing on one or more sub test graphs in the at least two sub test graphs respectively to obtain a test result graph corresponding to the hardware to be tested: determining a target region from the sub test graph according to the sub graph state array; testing the hardware to be tested according to the test parameters corresponding to the target region, obtaining a test result, and updating the sub graph state array; performing filling processing on the target region of the test graph according to the test result; and initializing the sub graph state array after completing the test on each target region in the sub test graph. The method reduces the memory requirement during the test by reusing the sub graph state array.

This application provides an OPC model training method and an OPC model training device, relating to the field of model training technology. The method includes: cutting a chip design layout file to obtain multiple basic blocks; adding noise to the multiple basic blocks to obtain multiple noisy blocks; training a graph generator based on the multiple noisy blocks and corresponding real noise; using the graph generator to generate multiple test graphs based on multiple preset noise vectors; and training the model based on the multiple test graphs to obtain an OPC model. By training the graph generator based on the multiple noisy blocks and corresponding real noise, the graph generator implicitly learns the data distribution of the graphs, that is, it learns the rules of chip design. This results in multiple test graphs generated by the graph generator having more diverse forms and conforming to design rules. The OPC model trained based on these multiple test graphs is also more accurate and reliable.

The specification discloses a method for determining query parameters, a storage medium, an equipment and a program product. In the method, the number of edges of each vertex in a to-be-tested graph database belonging to different query dimensions and different value intervals is counted in advance as vertex statistical data and saved, so that when determining the query parameters needed for testing the to-be-tested graph database, the query cost value corresponding to the query statement obtained after configuring different query parameters for the query statement template can be determined according to the target value interval used in the query statement template and the vertex statistical data, and then a group of query parameters corresponding to the same query cost value can be selected from the query parameters as target query parameters according to the query cost value corresponding to the query statement obtained when each query parameter is configured into the query statement template, and the to-be-tested graph database is effectively tested according to the target query parameters.

The invention provides an unmanned aerial vehicle network intrusion detection multi-classification method based on knowledge distillation. The method comprises the following steps: firstly, obtaining a data set composed of multiple groups of unmanned aerial vehicle network traffic data containing normal samples and multiple attack samples; extracting communication features from the data set, constructing a directed multi-attribute graph G based on application layer protocol enhancement, and obtaining a training graph and a test graph; training a teacher model by using the training graph, and executing forward reasoning on the training graph and the test graph through the trained teacher model to obtain a training embedded vector and a test embedded vector; taking the training embedded vector as the input of a student model, realizing knowledge distillation through joint optimization of a hard tag loss function and a soft tag loss function, and obtaining a trained student model; and reasoning by using the trained student model, taking the test embedded vector as input, and outputting a prediction label. According to the method, effective expression can still be obtained under the condition that sample types are not labeled, and the reasoning cost is remarkably reduced under the condition that the detection performance is guaranteed.

This invention discloses a method and apparatus for evaluating medical language models based on dynamic cost graph matching and inference path logic review, belonging to the interdisciplinary field of artificial intelligence and medical informatics. The proposed technical solution includes: constructing a knowledge graph; receiving the output content of the medical language model under test and parsing it into a test graph; vectorizing and optimizing the node text information of the knowledge graph and the test graph; calculating the graph edit distance between the test graph and the knowledge graph based on a graph edit distance algorithm, using dynamically calculated node replacement costs, converting it into a similarity score, normalizing it, and then calculating the local and global similarity scores between the test graph and the knowledge graph; using a depth-first search algorithm to detect logical loops, or detecting semantic coherence by calculating the embedding vector similarity of adjacent nodes on the path; and finally generating an evaluation report. This invention achieves automated, multi-dimensional, and in-depth evaluation of the output content of medical language models.

The application discloses a graph data backdoor defense method and device based on spectral domain transformation and edge weight learning, equipment, medium and program product, relates to the technical field of network security, and includes: obtaining and constructing a feature vector matrix and an eigenvalue matrix of an original graph data set; mapping each feature vector matrix from a spatial domain to a spectral space through spectral transformation to obtain a plurality of spectral domain node features, so as to construct a normal data distribution of the original graph data set, and determine whether each to-be-tested graph data is abnormal graph data; if it is determined that the graph data is abnormal, learning abnormal node features and abnormal adjacency relationships of the to-be-tested graph data through a multilayer perceptron to obtain abnormal edge weights; based on the abnormal edge weights, performing adaptive clipping on abnormal spectral components in the abnormal graph data through a Gaussian mixture model to obtain modified spectral domain node features; and performing inverse spectral transformation on each modified spectral domain node feature to reconstruct a target graph data set. The application can effectively resist multiple types of graph backdoor attacks.

The application provides a UAV network intrusion detection multi-classification method based on knowledge distillation, first, a dataset composed of multiple groups of UAV network traffic data containing normal samples and multiple attack samples is acquired; communication features are extracted from the dataset, a directed multi-attribute graph G based on application layer protocol enhancement is constructed, a training graph and a test graph are obtained; the training graph is used to train a teacher model, forward reasoning is performed on the training graph and the test graph through the trained teacher model, training embedding vectors and test embedding vectors are obtained; the training embedding vectors are used as the input of a student model, knowledge distillation is realized through joint optimization of a hard label loss function and a soft label loss function, and a trained student model is obtained; the trained student model is used for reasoning, the test embedding vectors are used as the input, and prediction labels are output. The method can still obtain effective expression without labeled sample types, and significantly reduces reasoning cost under the condition of ensuring detection performance.

The application relates to the technical field of software test automation, and provides a requirement-driven test case automatic generation method and system based on a semantic test graph, which comprises the following steps: performing multidimensional static analysis on source code, respectively constructing an abstract syntax tree, a control flow graph and a function call graph, and extracting function call relations and data flow dependency relations; taking a function as a node, taking a function call relation as a main edge, and taking a data flow dependency relation as an auxiliary edge to construct a semantic test graph; aggregating function nodes in the semantic test graph into a plurality of function modules; obtaining a plurality of test requirement nodes, calculating semantic similarity between the test requirement nodes and the function modules, establishing a mapping relation from the test requirement nodes to the function modules, and forming a requirement-program structure association graph; based on the requirement-program structure association graph, generating a test intention for each test requirement node, and converting the test intention into an executable test case. The highly corresponding relation between the generated test case and the business requirement is ensured.