668 results about "Intermediate language" patented technology

The invention relates to the technical field of metadata generation, and discloses a data platform metadata automatic generation method based on a large model, which comprises the following steps of: firstly, performing unified standardization and preliminary grammatical analysis on an original SQL (Structured Query Language) code to obtain a structured intermediate representation; on the basis, preliminary blood relationship analysis based on rules is carried out, and simple column references are quickly identified and processed. For complex expressions which are difficult to accurately analyze by a traditional method, code snippets and context information of the complex expressions are accurately extracted and submitted to a large language model for deep semantic understanding and complex blood relationship analysis. And finally, integrating the complex consanguinity analyzed by the large model with the initial consanguinity list to form a comprehensive and accurate field-level consanguinity, and further generating complete data platform metadata. In this way, the defect that a traditional analysis tool understands complex semantics is effectively overcome, and the accuracy and integrity of metadata generation are remarkably improved.

Provided is a process including: obtaining, with a computer system, access to a code base; decomposing, with the computer system, the code base into parts; classifying, with the computer system, the parts according to content type; selecting, with the computer system, processing templates based on the content types, with at least some different content types having different selected processing templates; and generating natural language documentation for the parts, with one or more generative language models, using the processing templates selected for the parts.

The invention belongs to the technical field of equipment knowledge engineering and natural language processing, and discloses an LLM-based constraint and self-repairing uniformization equipment knowledge graph automatic construction method. The method comprises the following steps: firstly, acquiring equipment related document data through network collection, document arrangement and database query; then, utilizing an equipment domain ontology and constraints as preposed soft and hard constraints, driving LLM to generate semantic intermediate representation, and obtaining candidate triples through structured compiling; then, a self-repairing closed loop is formed through semantic unit testing, logic consistency detection and evidence binding verification, and triples which violate constraints and have conflicts or illusions are automatically recognized and repaired; and finally, entity standard identification, cross-document duplicate removal combination and conflict resolution are realized through cross-segment unification and incremental alignment. According to the method, the fragile path that the LLM directly generates the triple and blindly stores the triple is avoided, the illusion and inconsistency problems are effectively inhibited, and the correctness, interpretability and maintainability of the equipment knowledge graph are remarkably improved.

Systems and methods for efficiently translating program code from a source language to a target language. Input source code is parsed, using a processor device, into an Intermediate Representation (IR). A structural and semantic model of the source code are established by applying static analysis to the IR, and a program skeleton of the target code is constructed from the IR, including generating context-aware placeholders. The IR is transformed into a Single Static Assignment (SSA) form, and a System Dependency Graph (SDG) is built from the SSA form. The SDG is traversed to order translation tasks, and ordered tasks are translated into the target language using a Large Language Model (LLM). A translated program is generated by integrating translated code segments into a coherent program structure in the target language.

The invention relates to the technical field of artificial intelligence and natural language processing, in particular to a cue word compiling and generating method and system for a large language model.The method comprises the steps that in response to a compiling calling request, a PDL protocol is received to serve as a compiling input text; performing lexical and grammatical analysis on the compiled input text, and constructing a corresponding abstract syntax tree AST as an intermediate representation according to a context-independent method; semantic verification and structure correction are carried out on the AST, and when semantics are effective, structure optimization is carried out to generate an optimized AST; and traversing the optimized AST, matching a cue word template in a cue word generation rule base, mapping semantic nodes into structured text fragments, splicing the structured text fragments to form a final cue word text, and outputting a compilation result consistent with PDL protocol semantics. By introducing a PDL-oriented compiling mechanism, automatic analysis, structure optimization and high-quality cue word generation of an input protocol are realized before cue words of a large language model are generated, and the development efficiency and the output quality of the cue words are improved.

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.

System and techniques to facilitate the translation of a sign language into another language are described herein. A modular architecture may be used in which the output of different classifiers may be used to produce intermediate representations, or final translations, of the sign language. These classifiers may be trained on different types of signs to enhance accuracy while reduce training time and complexity.

The invention relates to the technical field of artificial intelligence compilers, in particular to an AI compiler and compiling method based on a multi-level intermediate representation framework, and the compiler comprises a high-level semantic retention layer which converts models of different AI frameworks into Lalg-on-Tensor IR intermediate representations; the hardware perception optimization layer comprises a tensor packaging and propagation module which is used for performing block packaging, layout propagation and folding of redundant packaging / unpackaging operation on the input tensor; the dynamic partitioning module is used for automatically selecting the partitioning size based on the cache capacity and the core number of the target hardware; the microkernel fusion module is used for fusing matrix multiplication, bias addition and an activation function into a single composite operator; and the microkernel collaboration layer is in butt joint with the hardware acceleration library through the XSMM dialect to generate a target hardware code. The hardware perception optimization layer can perform optimization according to different hardware characteristics, so that codes generated by the compiler can better adapt to target hardware, and the hardware utilization rate is improved.

The invention provides a file uploading attack interception method based on semantic entropy enhancement, and aims at overcoming the defects of an existing file uploading security protection technology in the face of complex attacks. The method specifically comprises the steps that S1, file format analysis and content extraction are conducted, hidden scripts are mined through nested content recognition, and intermediate representation is generated through grammar cleaning and coding specifications; s2, constructing an abstract syntax tree and semantic entropy calculation, tracking a pollution chain, analyzing a high-risk function, identifying a high-entropy character string, modeling and controlling flow complexity, and generating a semantic entropy vector; s3, dynamic scoring and decision making are carried out, and accurate judgment is carried out in combination with white list perception, feature comparison, multi-modal model scoring, adaptive threshold and sandbox observation; and S4, carrying out real-time interception and feature synchronization, blocking malicious file landing, generating an attack log and synchronizing an attack fingerprint. The method takes the semantic entropy vector as a core, breaks through the limitation of static features, remarkably improves the recognition rate of complex attacks, reduces missed judgment, and guarantees the safety of Web applications.

The invention relates to a data query method and device based on a natural language and a medium, and belongs to the technical field of data analysis. Receiving a natural language query input by a user; constructing task planning guide information based on the natural language query, and inputting the task planning guide information into the large language model to identify a target task type corresponding to the natural language query; when the target task type is a data query type task, determining a query target index corresponding to the natural language query from an index library; on the basis of a DSL dimension normal form corresponding to the query target index, dimension fields related to semantics of the natural language query and matched enumeration values are recognized from the multiple dimension fields and enumeration value sets; and constructing a structured intermediate representation, generating an executable code corresponding to the natural language query, and executing the executable code to obtain a corresponding structured query result from a data source. According to the method and the device, the accuracy and the interpretability are considered, and meanwhile, the SQL generation flexibility is improved.

The invention discloses a software requirement modeling method and device based on a natural language, equipment and a medium, and relates to the field of software requirement modeling. According to the software demand modeling method and device based on the natural language, the equipment and the medium, through automatic demand analysis and model generation, the manual workload is greatly reduced, and meanwhile, errors caused by manual understanding deviation are reduced; close connection among the steps is ensured by sharing intermediate representation and a unified data model, output of the previous step provides structured information for input of the next step, and information loss or distortion is avoided; a demand provider is allowed to participate in a model confirmation process through an iterative demand acquisition and modeling framework of man-machine cooperation, and the quality of a demand model is continuously improved; by means of the model consistency analysis technology based on the data flow dependency relationship, the problem of inconsistency between the requirement specification and the software model can be automatically detected, and the software product quality is improved.

The invention discloses an AI-based low-code automatic development method and system and a medium, mainly relates to the technical field of image processing, and is used for solving the existing problems that the demand conversion efficiency is low, the code quality depends on manpower, and the complex scene support is insufficient. Comprising the steps of extracting a current functional entity corresponding to a code function core feature; based on the current functional entity and the historical functional entity, extracting an associated sub-graph containing the current functional entity and the historical functional entity from a preset knowledge graph corresponding to the demand technical field; dSL grammar corresponding to the demand technical field is obtained, entity nodes related to the associated sub-atlas, inter-node interaction logic rules and code function core features are input into the DSL grammar, and intermediate representation IR is obtained; and according to the intermediate representation IR, the code function core features and the current function entity, a model trained by a large-scale code library is utilized to generate a specific code.

Examples of the present disclosure describe systems and methods for providing control of input, output, and processing of an AI model. In examples, a request to execute an AI model implemented by a client device is received, where the AI model is associated with one or more licenses that specify a protection level that is applied to one or more portions of the AI model during the AI model runtime. In response to the request, the AI model is translated to a first set of commands in an intermediate language. The first set of commands is translated into a second set of commands for a hardware device of the client device. The second set of commands is translated into microcode that is executable by the hardware device. The hardware device then executes the microcode to generate an output in furtherance of the request.

The invention relates to code verification, in particular to a code and document consistency reasoning verification system based on a cross-modal logic atlas, which comprises an input layer for receiving source codes and software documents; the feature extraction layer is used for performing feature extraction on the source code and the software document; the abstraction layer is used for converting the extracted features into comparable intermediate representations; the unified modeling layer is used for mapping code logic and document semantics into a unified atlas structure and performing formalized representation by using description logic to obtain a cross-modal logic atlas; the reasoning verification layer is used for performing reasoning verification on the consistency of the code and the document according to the cross-modal logic graph; the result processing layer is used for judging a verification result according to the reasoning verification condition, starting a contradiction positioning mechanism when inconsistency is found, and carrying out contradiction positioning and report generation to obtain an interpretable report; according to the technical scheme provided by the invention, the defects that the consistency between the code and the document is difficult to accurately verify, and accurate contradiction positioning and an interpretable report are difficult to provide can be effectively overcome.

A software package is received and unpacked into multiple components comprising plural functions. Each function is lifted from machine code into static single-assignment intermediate representation and tokenized to produce semantics-preserving embeddings. Intermediate-representation data-flow features are extracted, including detection of constant static variables on a stack, stack reaching definitions, uninitialized variables, and intra-procedural aliases. For each component, the embeddings and features are input to a machine-learning model trained on semantic properties derived from a corpus of software packages to generate a software supply chain risk level. Data characterizing the risk level is provided to a consuming application. When the risk level satisfies a remediation criterion, a remediation action is initiated, including generation of a source-code patch recommendation for an identified root-cause function, insertion of a runtime guard into the component, or issuance of a security advisory for distribution to a security operations dashboard.

The invention discloses a compilation optimization pass combination optimization method based on deep reinforcement learning. The method comprises the following steps: 1) collecting a reference program data set for various general function tests; 2) constructing a deep reinforcement learning-based compilation optimization pass-combination optimization strategy model for a compilation optimization pass-combination optimization process, wherein the compilation optimization pass-combination optimization strategy model comprises agent D3QN construction and definition of a reward space, a state space and an action space; 3) introducing a composite program feature combined with basic features such as a control flow embedding vector extracted by the graph neural network, an instruction number, a basic block number and the like into the expression of the state space, enriching the expression ability of the state, optimizing the pass based on the state selection and acting on the intermediate expression by the D3QN, generating an award, and obtaining the state space; and repeating the loop of feature extraction-action selection-reward generation until the maximum action upper limit is reached, and generating an optimized pass combination adapted to the program features. The problem that in existing compiling optimization, the compiling optimization effect on part of programs is poor is solved.

The invention relates to the technical field of electrical digital data processing, in particular to an intelligent contract vulnerability detection method based on multi-modal selection state space fusion, and aims to solve the technical problem of low vulnerability detection accuracy in the prior art. The method comprises the following steps: firstly, fusing global and local features of a contract graph to obtain graph modal embedding features; performing feature alignment on the text context information of the intermediate representation text and the byte code text to obtain text modal embedding features; extracting spatial layout features from the color image and the grayscale image, and splicing the spatial layout features to obtain visual modal embedding features; thirdly, performing multiple rounds of feature cross processing on the graph modal embedding features, the text modal embedding features and the visual modal embedding features based on a selection state space to realize intra-modal and inter-modal information interaction, and then performing fusion to obtain multi-modal fusion features; and finally, performing feature normalization and regularization processing on the multi-modal fusion features, and performing classification processing to obtain a vulnerability detection result.

The invention relates to a public multi-mode cloud network resource software security enhancement method based on neural symbol fusion reasoning, which comprises the following steps: an intermediate representation generation stage: generating and optimizing an intermediate representation of a program through a fine-tuned large language model, and establishing semantic mapping from a source code to a structured logic representation; in the symbol language conversion stage, the intermediate representation generated by the large language model is converted into a domain-specific language fact set which can be recognized in the symbol logic reasoning stage, and formal and logic expression of program semantics is achieved; and a symbol logic reasoning stage: matching the fact set with the rule base through a symbol logic reasoning engine, performing detection and verification according to the safety rule, generating a structured report, and feeding back a result for optimization. The method is suitable for security enhancement of various core software systems in a public cloud network multi-modal network environment, high-precision security analysis is carried out on cross-modal and cross-subsystem fragmented codes in a compiling-free environment, and verifiable technical support is provided for public cloud network security control.

Data from manufacturing is highly uncontextualized and siloed, requiring expert knowledge of context and substantial data pre-processing to support meaningful queries and visualizations. To address this problem, data for a number of sources in a manufacturing context can be retrieved and converted into an intermediate representation in a natural language or near-natural language form, which can in turn be ingested by a generative AI engine, along with suitable prompts by the user to summarize, analyze, and make recommendations based on the data.

The invention belongs to the technical field of low-code development platforms, and particularly relates to a low-code platform model construction and dynamic execution method and system based on a hybrid DSL (Digital Subscriber Line), and the method comprises the steps: describing static model information in an application by using a structure DSL in a declarative grammar; defining a behavior DSL in a mounting mode under a corresponding element of the structure DSL; analyzing the structure DSL into a meta-model object tree in the platform, and converting the behavior DSL into an executable expression tree / intermediate representation; jointly driving the meta-model object tree and the expression tree / intermediate representation by utilizing a template engine, and automatically generating at least one application code in a front-end page, a back-end interface and a database script; a common structure DSL and a behavior DSL are combined and packaged into a scene template, and the scene template is stored in a template library so as to be reused by different service scenes, and modularization and templating of service modeling are realized. The complexity of the system is reduced, and the development efficiency and quality are improved.

The invention discloses a method for automatically capturing semantic information of a binary code block and a related device, and relates to the technical field of computers.The method comprises the following steps that code disassembling and instruction level analysis are conducted on the binary code block, and a binary stream original instruction sequence is generated; performing semantic intermediate representation conversion and vocabulary overflow standardization on the binary stream original instruction sequence to obtain a binary code standardized instruction sequence; obtaining an instruction data dependency relationship and an instruction control dependency relationship corresponding to the binary code block, and constructing a corresponding binary code program dependency graph; semantic code node embedding is carried out on the binary code program dependency graph to generate a binary code representation vector corresponding to context semantics; and performing automatic semantic capture reasoning on the binary code representation vector corresponding to the context semantics through a pre-trained semantic understanding model to obtain semantic information of the binary code block. According to the method, the semantic information of the binary code block can be efficiently and accurately captured.

The invention provides a large-model-oriented heterogeneous computing power adaptive compiling method, which comprises the following steps that: a user inputs a trained large model through a system interface, and a system front-end conversion module analyzes a computational graph of the model and converts the computational graph into an intermediate representation based on a unified operator description language (UDL); the system hardware sensing module automatically detects and extracts hardware feature fingerprints of at least one piece of target hardware; based on the unified operator description language UDL intermediate representation and the hardware feature fingerprint, automatically generating an optimization adaptation rule oriented to at least one piece of target hardware; wherein the basis of parameterized filling comprises specific parameters of hardware feature fingerprints and optimized attribute tags carried in an intermediate representation of a unified operator description language (UDL); and generating and deploying multiple back-end codes. The method has the beneficial effects that intelligent compiling based on hardware features can be realized, and the deployment efficiency and the operation performance of a large model in a complex heterogeneous computing power cluster are remarkably improved.

A method, computer system, and a computer program product for data-free knowledge amalgamation are provided. Multiple pre-trained teacher machine learning models are obtained. Each is trained on a respective different set of training data. Pseudo-data samples that mimic original training data of the teacher models are generated. A block-wise amalgamation with a self-regulative strategy to integrate knowledge from the multiple teacher models is implemented by inputting the pseudo-data samples into the teacher models and into a student machine learning model. The implementing also includes aligning intermediate representations of the student model with a unified representation capturing relevant features from the teacher models.

The invention relates to the technical field of computers, and discloses a method for generating a test program for testing a Solidiity smart contract compiler, which comprises the following steps of: defect directional triggering: inserting a Solidiity variable through an inline assembly block to expose an optimizer defect, and limiting a dynamic array / character string to be expanded to at most one element at a time; semantic consistency control: eliminating intermediate representation behavior differences by adopting a placeholder counter, and preventing border crossing through an array length check instruction; and resource conflict arbitration: managing EVM stack variables by using a block scope, and nesting hierarchies based on a depth threshold truncation function. Through triple innovative design of defect directional triggering, semantic consistency control and resource conflict arbitration, the fundamental contradiction among semantic ambiguity, low defect detection rate and resource constraint in the Solidity compiler test is systematically solved.

The invention discloses an SIMT architecture-oriented program branch compilation optimization system, which relates to the technical field of program branch compilation optimization, and comprises a compiler rear end which takes code intermediate representation as input, executes hardware-related optimization and code generation work, converts the intermediate representation into binary codes and stores the binary codes in a video memory; the SIMT execution unit is responsible for reading the binary code from the video memory and executing a corresponding instruction; the SIMT stack is responsible for storing an address and an active mask of a non-jump branch when the Split instruction is executed, and is responsible for loading the stored non-executed branch and executing or setting the active mask to perform branch reconvergence after the Join instruction is executed; the branch performance analysis module is responsible for recording distribution of active threads of different branch paths; and the branch optimization module is responsible for analyzing and optimizing the code intermediate representation according to the recorded information, and replacing the input of the rear end of the compiler by using the optimized code intermediate representation. The code execution efficiency can be improved.

The embodiment of the invention provides a code compiling method, electronic equipment and a storage medium. The code compiling method is used for compiling a code comprising at least one thread local storage variable, and comprises the following steps: in response to existence of a target thread local storage variable, allocating the at least one target thread local storage variable to a thread local memory based on an attribute of the at least one target thread local storage variable, obtaining a thread local memory address corresponding to each target thread local storage variable, wherein the target thread local storage variable is the thread local storage variable used by the first function; updating an intermediate representation corresponding to the code based on a thread local memory address corresponding to each target thread local storage variable; and generating a machine code corresponding to the code based on the updated intermediate representation. According to the code compiling method, thread local storage model support under a parallel computing architecture is provided, and the problem that traditional thread local storage implementation cannot be directly applied to a GPU architecture is solved.

The invention discloses a large language model jailbreak attack method based on alignment mechanism interference, and relates to the technical field of artificial intelligence. The method comprises the following steps: by constructing a consistency loss function, guiding an intermediate layer representation when a model generates a malicious request to approach an intermediate layer representation of a compliance request, thereby interfering a security alignment mechanism of the model and weakening the rejection capability of the model to malicious input. From the perspective of the internal representation space of the model, a jailbreak strategy which can interfere with the security cognitive path of the model is designed, and the model is disguised to the middle representation of malicious input as benign representation by optimizing prompt input, so that the jailbreak attack with higher concealment and stability is realized, the defense capability of the model to vulnerabilities is conveniently trained, and the security of the model is improved. The method can be widely applied to large model security mechanism research, alignment robustness test, red team evaluation and other scenes.

The invention provides an operator processing method and device based on MindSpore, and relates to the technical field of data processing.The method comprises the steps that graph nodes with explicit calculation semantics in a deep learning model are extracted and are abstracted into an independent operator type set in a unified mode; constructing a minimum executable network structure to verify whether the minimum executable network structure can be successfully identified and generate intermediate representation in a MindSore framework, further calling a graph compiler to judge whether back-end graph optimization can be completed, loading to a running environment to execute verification if the back-end graph optimization can be completed, and calculating an error based on forward output and gradient return results, and if the error is lower than the set tolerance, identifying the operator as a function effective operator. According to the method and the device, the problem that the MindSore framework supports the operator incompletely or is insufficient in performance in the large model training and reasoning process can be solved, and the function effectiveness and the execution consistency of the target operator in the stages of composition, compilation and operation are guaranteed.

The invention discloses a software source code security vulnerability detection method based on an artificial intelligence large model, and belongs to the technical field of information security and source code detection, and the method comprises the following steps: carrying out user registration and login, uploading a file, judging whether static analysis is carried out or not, judging whether dynamic analysis is carried out or not, introducing the AI large model, and generating a detection report; according to the method, through multi-level technology integration and a self-evolution mechanism, normal form innovation of vulnerability detection from a single view angle to global perspective is realized. According to the system, on the basis of unified intermediate representation, a closed-loop architecture of static rule screening, dynamic behavior verification and AI semantic reasoning is constructed, and the core contradiction of high false alarm rate, insufficient path coverage and semantic understanding deficiency of a traditional method is effectively solved.

The invention discloses an intelligent chart generation method and system suitable for multi-modal data and a storage medium, and the method comprises the steps: receiving and preprocessing the multi-modal data, and completing user intention type recognition and task routing; selecting an adaptive model according to a routing result, and constructing and generating a cue word; standardizing an initial graph code output by the model into an intermediate representation format containing a metadata field, converting the intermediate representation format into a graph code compatible with a target platform, and reserving node definition, a connection relation, layout constraint and metadata information; the method comprises the following steps: respectively completing chart type identification and layout strategy determination, node format size adjustment, overall layout alignment correction and partition adjustment, and connection line identifier optimization through four optimization components, and rendering and outputting a chart. The problem that due to the fact that an existing model lacks a special optimizing and processing mechanism for the structured chart, the effect is remarkably poor when a professional schematic chart needing an accurate logic structure and geometric constraints is generated is solved.