400 results about "Control flow graph" patented technology

The invention discloses a variation test method and device based on an intelligent automation script. The method comprises the following steps: extracting a statement execution sequence and a branch dependency relationship in an original source code by using a context-aware syntax tree, and generating a control flow diagram and a data flow diagram; performing code semantic analysis on the multi-dimensional code features by using a large language model, identifying potential defect types and variation rules, predicting the test efficiency of variants in combination with a deep Q learning model, and generating to-be-processed variants; performing grammar check and equivalence analysis on the to-be-processed variants to obtain effective variants, and testing the effective variants; variation test indexes are calculated, code weak points are positioned, and test blind areas are identified according to survival variants, so that a visual analysis report is generated; and iteratively generating a new test case according to the current survival variant and the visual analysis report, and testing the current survival variant by using the new test case. According to the invention, the variation test efficiency can be improved.

The invention relates to the technical field of vulnerability detection, and provides a fine-grained vulnerability detection method and system based on semantic perception sparse attention, and the method comprises the steps: analyzing a to-be-detected source code, and generating an abstract syntax tree, a control flow graph and a program dependency graph; carrying out weighted fusion on graph representations of the abstract syntax tree, the control flow graph and the program dependency graph, and integrating into a code attribute graph; for the code attribute graph, processing the code attribute graph by adopting a semantic perception sparse attention method combined with sparse attention, a learnable Token pruning method and Top-k interaction frequency to obtain a Token attention score; and based on the obtained Token attention scores, accumulating the attention score of each Token in each row of the code, and detecting and determining a statement where the vulnerability code is located. According to the detection method disclosed by the invention, the capability of modeling code semantic information and capturing a structured dependency relationship can be effectively improved, and meanwhile, the calculation complexity is remarkably reduced.

The invention belongs to but is not limited to the technical field of software development, and particularly relates to a multi-round reasoning and feedback optimization method and system for industrial software codes, and the method comprises the steps: S1, vector code library establishment: the establishment of a vector code library is composed of three parts of feedback establishment, vector database establishment and format summarization; s2, code reasoning optimization: the code reasoning optimization mainly comprises four aspects: control flow graph analysis, multi-query generation and reciprocal ranking fusion retrieval, reasoning generation subtask and code chain submodule generation, and code combination completion; and S3, feedback optimization: the feedback optimization is composed of score feedback optimization and log feedback optimization. According to the method, an automatic verification mechanism is introduced, logic consistency check and performance evaluation are carried out on the generated and optimized codes, and the correctness and execution efficiency of the codes are ensured. The verification mechanism can find and correct errors in real time in each stage of generation, so that the cost of manual verification is reduced, and the development efficiency is improved.

The invention discloses a cross-chain smart contract vulnerability detection method and system based on multi-feature fusion learning. The method comprises the following steps: collecting a cross-chain smart contract vulnerability data set for cleaning and labeling; feature extraction is carried out from the source code and the byte code, an abstract syntax tree (AST) is extracted from the cleaned source code, a basic control flow graph (CFG) is extracted from the byte code, and a cross-chain control flow graph (xCFG) is constructed; carrying out feature representation on AST and xCFG, generating a graph vector through a graph neural network (GNN), generating a semantic vector through CodeBert, and fusing the semantic vector into a feature fusion vector; performing model training and detection, taking the generated vectors as training data and test data, obtaining a cross-chain smart contract vulnerability detection model by adopting Transform-FC model training data, and finally evaluating model performance through accuracy, recall rate, precision rate and F1 value. According to the method, the structural features and semantic features of the codes can be effectively fused, potential vulnerability information in the codes can be fully mined, the recognition capability of the model for cross-chain vulnerabilities can be enhanced, and the accuracy and reliability of the cross-chain vulnerability detection model can be improved, so that the security of a block chain system can be more efficiently guaranteed.

The invention provides a malicious code gene information recessive association mining method based on meta-learning, which comprises the following steps of: generating a function call graph (FCG) to obtain an attribute function call graph; training the feature extraction model based on the sequence-to-sequence mechanism by adopting meta-learning, and obtaining a key sub-graph of the function call graph from the generated attribute function call graph through the trained feature extraction model based on the sequence-to-sequence mechanism; generating a control flow graph (CFG), and obtaining an attribute control flow graph; using the optimized gene feature extraction model based on the graph structure for the generated attribute control flow graph to obtain a key sub-graph of the control flow graph; and a fine-tuning corpus is obtained through the key sub-graph of the function call graph and the key sub-graph of the control flow graph, and hidden association mining of malicious code gene information is carried out by using the fine-tuned large language model. According to the method, the recessive association of the malicious code gene information can be accurately mined, and the malicious code analysis precision and efficiency are remarkably improved.

The invention relates to the field of intelligent contract vulnerability detection, in particular to an intelligent contract vulnerability detection method based on code graph fusion analysis and a graph matching network. The method comprises the steps of constructing an intelligent contract source code data set; through static analysis, extracting three different code feature information including a control flow diagram, a data flow diagram and an abstract syntax tree from the source code of the smart contract; carrying out information integration on the three extracted code features, and constructing a code graph covering wider features; on the basis of the generated code graph, a GraphCodeBerT model is used for pre-training; vectorizing a code graph which is output by the pre-training model and contains structural and semantic features through a graph embedding network; and learning the feature representation of the contract pair by using a cross-graph attention mechanism of a graph matching network to realize specific vulnerability detection of the smart contract source code. According to the invention, potential vulnerabilities can be accurately identified.

The invention discloses an intelligent contract vulnerability detection method based on a heterogeneous graph attention network. According to the method, firstly, the source code of the intelligent contract is preprocessed, the SCIR of the code of the intelligent contract is constructed, the complexity of the code of the contract is reduced, and vulnerability features are enriched; and constructing an intelligent contract code attribute graph SCPG based on SCIR, integrating various code graph structures such as an abstract syntax tree and a control flow graph, and comprehensively describing syntax and semantic features of the contract. And then constructing an intelligent contract code heterogeneous graph SCHG on the basis of the SCPG, optimizing code graph structure representation, and realizing high-quality modeling of node features. And finally, detecting the vulnerability of the smart contract by using a customized multi-layer heterogeneous graph attention network model MHGAN. The intelligent contract vulnerability detection method based on deep learning makes up for the defects of an existing intelligent contract vulnerability detection method based on deep learning, effectively improves the accuracy of intelligent contract vulnerability detection, and is excellent in the interpretability of the detection result.

The present invention provides a cross-modal pre-training model-based smart contract similarity detection method, comprising: constructing a control flow graph of a smart contract; extracting comment information from the smart contract, and enabling the control flow graph to correspond to the comment information so as to acquire a corresponding graph; inputting information of the corresponding graph into a preset cross-modal pre-training model so as to acquire a feature representation vector of the contract; and, on the basis of the feature representation vector, determining a contract similarity by means of a threshold value. The present invention can implement high-precision smart contract semantic similarity detection.

A smart contract fine-grained vulnerability detection method based on expert knowledge comprises the following steps: S1, constructing cue words by using a large language model, analyzing smart contract source codes, and labeling a smart contract data set; the method comprises the following steps: statically analyzing an intelligent contract source code statement, representing a source code element as a vector to obtain a source code fine-grained feature preliminary representation, and merging abstract syntax tree sub-trees into a code graph of a control flow graph node to obtain a graph representation of a source code; s2, acquiring heterogeneous code features and source code fine-grained features of the same smart contract, inputting the heterogeneous code features and the source code fine-grained features into a BGSCVul model for iterative fusion, and constructing a deep learning classifier; s3, by constructing an expert knowledge classifier, making a decision for specific expert knowledge; and S4, fusing the output of each sub-classifier by using a stack pressing method, and outputting final prediction.

The invention discloses a static and dynamic analysis-combined source code vulnerability detection method, which comprises the following steps of: performing static scanning on an input source code, and preliminarily positioning potential vulnerabilities according to a preset vulnerability rule base; executing program slicing based on the control flow diagram and the data flow diagram, and extracting a precise code subset related to the vulnerability; a large language model based on a Transform structure is utilized, and a dynamic verification attack case is automatically generated according to the vulnerability type and the slice code; executing the test case in a sandbox environment, monitoring program abnormal behaviors in real time, and confirming actual availability of vulnerabilities; and finally, synthesizing static and dynamic results to generate a multi-level vulnerability detection report. According to the method, the accuracy and coverage rate of vulnerability detection can be effectively improved, the false report and missing report rate is reduced, high automation and intelligence of the source code vulnerability detection process are realized, and the method has good applicability and popularization value.

The invention relates to an EOSIO smart contract vulnerability detection method based on an adaptive multi-channel graph convolutional network. The method comprises the following steps: S1, generating a control flow graph CFG and a data flow graph DFG of a smart contract function to be detected; s2, learning contents in a control flow graph CFG and a control flow graph DFG by adopting an adaptive multi-channel graph convolutional network EAM-GCN; s3, after a feature vector splicing process in a learning control flow graph (CFG) and a data flow graph (DFG) of the adaptive multi-channel graph convolutional network EAM-GCN, fusing semantic features extracted from the control flow graph (CFG) and the data flow graph (DFG) of the source code by using a global fusion attention mechanism, classifying the obtained global code features by using a classifier, and extracting the feature vectors in the data flow graph (DFG) of the source code; and identifying the existence of the EOSIO smart contract vulnerability to be detected. According to the method, the problem that deep learning cannot be applied to EOSIO smart contract vulnerability detection at present is solved.

The invention relates to the technical field of automatic testing, and discloses an automatic testing scheme generation method and device and a medium, and the method comprises the steps: matching a demand action in a test demand with a code entry name corresponding to a code segment, and determining a code risk level of a current demand code block; analyzing the code change frequency and the code dependency degree of the current demand code block according to historical test records in the test domain knowledge base, and determining the test dynamic priority of the current demand code block; constructing a control flow diagram and a data flow diagram of the current demand code block, and detecting risk nodes in the control flow diagram and the data flow diagram; generating a test scene of the current demand code block according to the risk node, and generating a boundary value test rule according to a key constraint condition in the data flow diagram; and querying an environment simulation rule of the current demand code block, and packaging the test scene, the boundary value test rule and the environment simulation rule into an automatic test scheme. According to the invention, the code coverage when the test scheme is generated can be improved.

The invention discloses a cross-language application program vulnerability mining method based on static analysis, which adopts a nested cross-programming language pointer analysis method and a micro-service cross-programming language taint tracking method to effectively solve the limitation of processing nested cross-language control flow and micro-service cross-language data flow. A nested language semantic boundary is accurately positioned by constructing a nested byte code, and a data stream is completely tracked by utilizing an interface relay technology, so that the detection precision is improved. According to the method, part of multi-end data streams and complex control streams of cross-programming language applications can be uniformly processed, and the analysis process in a cross-programming language environment is simplified; by nesting cross-programming language control flow diagram construction and double-end / multi-end data flow diagram construction, a unified analysis framework is constructed, seamless cooperation of static analysis among different languages is achieved, the analysis cost is reduced, the analysis efficiency is improved, efficient and accurate vulnerability mining is achieved in a complex cross-programming language application program, and the method is suitable for application and popularization. And the reliability of cross-language vulnerability detection is improved.

The invention discloses a test generation and defect prediction method and system based on a heterogeneous program diagram, and the method comprises the steps: constructing a heterogeneous dynamic program dependency diagram: extracting an abstract syntax tree, a control flow diagram and a program dependency diagram of a source code through static analysis, capturing an execution track during operation in combination with dynamic instrumentation, and integrating version evolution information, forming a heterogeneous dynamic program dependency graph containing various types of nodes and edges; heterogeneous graph neural network modeling: designing a four-layer eight-header heterogeneous graph neural network model based on the heterogeneous dynamic program dependency graph, and outputting a function level defect probability and a test case sequence by adopting a type awareness attention mechanism and time coding injection; and multi-task joint training and reasoning: adopting an end-to-end training strategy, jointly optimizing defect prediction loss and test generation loss, preferentially screening high-risk functions during reasoning, and generating a coverage test case. According to the method, the defect detection accuracy is remarkably improved, the test coverage rate is increased, and the method is suitable for enterprise-level complex software systems.

The invention relates to the technical field of vulnerability repair, in particular to a source code vulnerability repair method, electronic equipment and a storage medium, and the method comprises the following steps: obtaining an abstract syntax tree and a control flow graph according to a source code containing a vulnerability, and generating a vulnerability context feature vector by using a graph neural network model in combination with vulnerability position information, determining a historical vulnerability repair case corresponding to the vulnerability context feature vector from a vulnerability-repair knowledge base, inputting the vulnerability context feature vector and the corresponding historical vulnerability repair case into a code generation model, outputting a candidate repair code set corresponding to the source code, evaluating each candidate repair code, and determining the vulnerability-repair knowledge base according to the candidate repair code set. Screening out an optimal repair code to automatically repair the source code vulnerability; according to the method, deep semantic analysis is performed on the vulnerability context, and intelligent reasoning is performed, so that the repair code with correct grammar and adaptive context can be generated, and the automation level and accuracy of vulnerability repair are remarkably improved.

The invention provides an intelligent contract vulnerability detection method based on code slices and a neural network, and relates to the technical field of contract vulnerability detection, and the method specifically comprises the following steps: carrying out the static analysis of an intelligent contract code; checking a program execution path through depth-first traversal of the control flow diagram, detecting timestamp dependent vulnerabilities and unchecked external call vulnerabilities, and positioning vulnerability paths in the control flow diagram according to nodes corresponding to vulnerability statements; normalizing the smart contract code, removing smart contract code annotations, unifying variables and function naming, not renaming related state information related variables, converting a smart contract code statement into vector representation, and training and updating a vector; constructing a multilayer graph convolutional neural network as a neural network model for training and detecting vulnerabilities; and outputting a detection result by the multilayer graph convolutional neural network. According to the technical scheme, the problem that the intelligent contract vulnerability cannot be accurately and effectively detected in the prior art is solved.

The invention discloses a graph neural network-based intelligent contract bytecode similarity detection method, which comprises the following steps of: performing disassembling operation on Ethereum virtual machine bytecodes, and performing data flow analysis and control flow analysis on disassembling results to obtain a data flow graph and a control flow graph corresponding to the bytecodes; combining the data flow diagram and the control flow diagram of each external function into a byte code characteristic diagram; a large number of intelligent contracts with similar labels are adopted to train a graph neural network, vectorization operation is performed on the byte code feature graph in the training process, and feature vectors are obtained; and taking the problem contract as a reference smart contract, respectively inputting the bytecode feature maps of the reference smart contract and the to-be-detected smart contract into the trained graph neural network to respectively obtain corresponding feature vectors, comparing the Euclidean distance of the two feature vectors, and measuring to obtain the similarity of the bytecode of the two smart contracts. Compared with a traditional method, the method has higher accuracy, problem contracts can be effectively recognized, and the safety of a block chain system is enhanced.

The invention discloses an instruction-level code optimization method and device based on template matching, a medium and equipment. According to the method, instruction-level codes serve as input, the input instruction-level codes are firstly constructed into corresponding control flow diagrams, then value ranges of active variables and register quantities are initialized based on the control flow diagrams, then variable assignment instructions and related instructions are found out from instruction sequences of basic blocks to form instruction segments to be optimized, and the instruction segments to be optimized are optimized. The method comprises the following steps of: optimizing an instruction fragment, obtaining an optimized instruction fragment through template matching, performing SMT equivalence verification on the instruction fragment before and after optimization based on an active variable and a value range of a register quantity, and finally optimizing an input instruction-level code in a manner of replacing the instruction fragment before optimization with the optimized instruction fragment which is verified to be equivalent. And finally, the optimized instruction-level code is obtained.

The invention discloses a multi-language code generation method based on self-supervised pre-training, which comprises the following steps: acquiring and cleaning multi-language code data to form a training corpus; the method comprises the following steps: representing code data as an abstract syntax tree, extracting a control flow diagram and a data flow diagram of the code data, and obtaining unified semantic representation through combination of a diagram encoder and a sequence encoder; designing a self-supervised pre-training task, and pre-training the semantic representation based on the training corpus; constructing a multi-language pre-training model based on the structure-improved recurrent neural tensor network and the multi-language embedding matrix; when a user inputs a natural language, generating a target language code by using the multi-language pre-training model; and target language code correction is carried out through conventional function testing and grammar checking. According to the method, multi-channel recursive combination and a hierarchical recursive expansion mechanism are combined with self-supervised pre-training, so that accurate generation and performability improvement of cross-language codes are realized.

The present invention discloses a program static analysis method and system based on LLVM, belonging to the technical field of computer program analysis. The technical problem to be solved is that the existing program analysis technologies have low accuracy, low efficiency and limited application scope in estimating program performance characteristics and memory reuse distance distribution. The method includes: converting a source file into an LLVM IR file with source-level debugging information; traversing modules, functions, basic blocks and instructions in the LLVM IR file to obtain static trace information of a target function; constructing a basic block-level control flow graph of the LLVM IR file and annotating relevant information; identifying and annotating loop information when traversing paths to obtain an execution path with loop annotations, replacing basic blocks in the execution path with corresponding memory access information, and generating a static memory trace with loop annotations; calculating the memory access reuse distance distribution through a recursive algorithm based on the static memory trace with loop annotations.

The invention relates to an application user tracking detection method and device based on a dynamic and static combination technology, and the method comprises the steps: obtaining a first interprocess control flow diagram associated with a device identifier according to an application package of a target application and a configuration file containing a predefined device identifier; according to a program behavior of a target application in a running state, determining a function associated with an application programming interface of the equipment identifier and an application programming interface of network data transmission, and obtaining a second interprocess control flow diagram of data leakage according to the function; integrating the first interprocess control flow diagram and the second interprocess control flow diagram to obtain a third interprocess control flow diagram; and obtaining a leakage path of the target application to the user data according to the third interprocess control flow diagram. By adopting the method, the problems of narrow detection coverage and low detection accuracy in the aspect of tracking the user by using the device identifier through the APP can be solved.

The invention discloses a cross-modal adaptive fine tuning method and system based on a double-branch network architecture, and realizes cross-modal knowledge fusion and migration by combining the modeling capability of a graph neural network on code graph structures such as an abstract syntax tree, a control flow graph and the like and the powerful semantic understanding and generation capability of a large language model. A double-branch architecture is adopted, a graph structure and text input are coded respectively, and feature interaction is achieved through heterogeneous adaptation, structural decoupling and a mask attention mechanism. In a fine tuning stage, three-stage strategies are provided: basic fine tuning of structure perception, efficient parameter migration by combining Adapter, Prefix Tuning and LoRA, and language generation quality and robustness are optimized based on an unsupervised text reconstruction task. The training stage relates to structure sensing tasks such as node prediction, edge reconstruction and subgraph comparison, and the stability and generalization ability are improved in combination with course learning. The method is widely applicable to tasks such as code completion, question and answer and vulnerability detection, and has the advantages of strong structure perception, efficient cross-modal fusion, low training cost and the like.

The invention provides a computer network security software debugging method and system, and the method comprises the steps: setting a plurality of test nodes of a source program in target network security software, and positioning a key test node based on the execution state of each test node; constructing a target search domain when the source program is tested through the program context information of the key test node; determining a plurality of abnormal program slices in the source program based on the static control flow diagram and the dynamic control flow diagram of the program code in the target search domain; determining the test overhead of each program slice according to the test coverage information of each program slice and the path complexity when the source program executes the test data; determining the constraint level of each program slice according to all the test overhead and the membership relationship among the program slices; and debugging each program slice through the constraint level of each program slice. According to the scheme, on the basis of the constraint level of each program slice, the problem code line can be accurately pointed in the network security software debugging process.

The invention discloses an automatic code defect repairing method based on a code attribute graph and a large model, which comprises the following steps: collecting a code sample, analyzing a source code, generating the code attribute graph fusing an abstract syntax tree, a control flow graph and a data flow graph, and then carrying out dynamic pruning according to node importance calculated based on node degrees, PageRank and data propagation dependency, so as to obtain a large model; key nodes are reserved to improve the graph learning efficiency; extracting features of the optimized graph through GAT, introducing multi-scale coding, and generating a graph embedding vector; in combination with node importance, high-value Tokens are screened, semantic embedding of structure perception is carried out, and more accurate text representation is obtained; generating a comprehensive feature by fusing the image and the text vector, and then inserting a mask at a position with weak dependence or high risk; performing fine tuning optimization on the mask position; and inputting the comprehensive features and the mask source codes into a pre-training language model to generate patches, performing multi-task evaluation and reordering, and selecting an optimal patch to complete repair.

The invention discloses a flow chart image analysis and structured reconstruction method and device and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: carrying out the element background separation of an input image through a pre-trained convolutional neural network, and obtaining a flow chart image, the elements including text elements and graphic elements; extracting rectangular frame information, arrow information, text information and position coordinates thereof in the preprocessed flow chart image; determining the node type of each node in the flow chart image based on the rectangular frame information and the text information, and determining the connection relationship of each node based on the arrow information in combination with the position coordinates; analyzing the node type and the connection relationship of each node, modeling the logic relationship of each node, and generating a control flow diagram of the flow diagram image; and converting the control flow diagram into structured data, and rendering to generate an interactively editable flow diagram visual interface. According to the method and the device, the technical effect of reconstructing the structured flow chart by identifying the control logic structure of the flow chart is realized.

The invention relates to the technical field of software engineering, and discloses a path coverage test data generation method based on an SA-BKA hybrid optimization mechanism, and the method comprises the steps: generating a control flow diagram through a program, recognizing each decision node through the control flow diagram, and deducing a set of all possible execution path sets as a target path set according to the decision nodes; the paths are grouped through path similarity, different optimization strategies are selected for the paths with different similarities, a simulated annealing algorithm is adopted for the groups with high path similarity, and an adaptive disturbance strategy is introduced, so that the algorithm diversity is enhanced; for low-similarity groups, a BKA algorithm is adopted, Levy flight and a dynamic step length adjustment strategy are fused, and meanwhile balance of the search process is achieved through dynamic step length adjustment. Compared with the prior art, the method has higher search efficiency under the condition of different population scales, and verifies the validity in path coverage test data generation.

The invention relates to the technical field of block chains, in particular to a smart contract vulnerability detection method and system based on a multi-modal large language model.The detection method comprises the steps that S1, the system receives source code input of a smart contract; s2, executing semantic branches and graph structure branches in parallel; executing semantic branch processing, calling an annotation agent, and generating an annotation from the source code of the smart contract; calling a vectorization agent, coding the annotation and the source code, and converting the annotation and the source code into a high-dimensional vector; executing graph structure branch processing, compiling a source code into a byte code by the system, and generating a control flow graph; the vectorization agent generates high-dimensional embedded representation of the nodes based on the control flow graph; and S3, integrating features extracted from the semantic branches and the graph structure branches through a multi-modal feature fusion strategy, and inputting the integrated features into a classifier to detect vulnerabilities. The method is based on a multi-modal large language model agent, and potential vulnerabilities in the smart contract are comprehensively analyzed by integrating high-level semantic information and low-level structured data.

The invention relates to the technical field of kernel fuzz testing, and provides a fuzz test input generation method based on characteristic unification and related equipment, the method comprises the following steps: generating a function call graph and a plurality of control flow graphs of a target system, and integrating the function call graph and all the control flow graphs to obtain an inter-program control flow graph; constructing a kernel code calling chain based on the inter-program control flow diagram; carrying out characteristic unified representation modeling based on the kernel configuration file and the kernel code call chain of the target system, and generating a configuration code relation mapping table; extracting related information of the characteristic related interface function according to the kernel code call chain, and performing grammar conversion based on the related information to generate a system call test protocol template of the characteristic related interface function; and generating fuzzy test input of the target system based on the system call test protocol template and the configuration code relation mapping table. According to the method provided by the invention, the correlation between kernel characteristic configuration and fuzzy test input can be improved.

The invention discloses a code embedding method based on a semantic embedding vector generation model, which belongs to the technical field of computers, and comprises the following steps of: obtaining a binary code block, and performing disassembling processing and code structure analysis based on different granularities to obtain a basic block corresponding to the binary code block and a control flow diagram structure feature; performing assembly instruction linear conversion and cross-instruction-set semantic embedding conversion on the basis of the basic blocks corresponding to the binary code blocks and the structural features of the control flow graph to generate a unified binary code semantic embedding vector space corresponding to a cross-instruction-set architecture; obtaining a known vulnerability sample, and performing semantic vulnerability characterization analysis and candidate vulnerability retrieval positioning to generate a candidate vulnerability code block set; and carrying out dynamic analysis verification on the candidate vulnerability code block set and identifying a corresponding vulnerability repair state so as to output a corresponding binary vulnerability code block detection report. According to the method, high-precision semantic embedding of binary codes can be realized.

The invention provides a memory allocation method and device, electronic equipment, a storage medium and a chip. The method comprises the following steps: extracting tensor data of each tensor in a kernel program; constructing a control flow diagram according to the kernel program; allocating first address information in a static random access memory for each piece of tensor data; determining an active path of each tensor according to the control flow graph, the active path comprising a first node involving the tensor; an interferogram of the tensors is constructed according to the active path, each second node in the interferogram represents a different tensor, and edges between the second nodes represent an interference relation between the tensors; the first address information of each piece of tensor data is adjusted according to the interferogram, the second address information of each piece of tensor data is obtained, and in different steps of the kernel program, if no interference relation exists between the two tensors, the storage areas of the two pieces of tensor data are reused. According to the invention, the memory reuse rate can be improved.