13 results about "Formal specification" patented technology

The invention provides an end-to-end intelligent system development method and system based on an AI large model. The method comprises the following steps: S1, receiving a system demand described by a user through a natural language; s2, analyzing the requirements through an AI large model and converting the requirements into formalized specifications; s3, automatically generating a system architecture and dividing components; s4, generating each component code in a recursive manner; s5, dynamically detecting and repairing the generated code problem; s6, automatically integrating all components to form a complete system; and S7, continuously optimizing the system based on system feedback or user feedback. According to the method, work of multiple stages such as demand analysis, architecture design, module division, code writing and testing is automatically completed, distributed integration and smart contract are performed, distributed integration verification is performed through a block chain smart contract and a graph database, data consistency, interface matching and security among components are ensured, the integration process is optimized, and the integration efficiency is improved. Cross-domain cooperation is achieved, and the development efficiency is high.

The application discloses a structured image generation method, device, equipment and medium, and relates to the technical field of image generation. The method comprises the following steps: obtaining natural language input of a structured image to be generated; performing semantic analysis on the natural language input to obtain a formal specification and a constraint set; generating an intermediate symbolic representation in a constraint-guided manner according to the formal specification and the constraint set; obtaining constraint violation energy and error information through a symbolic verifier according to the intermediate symbolic representation and the constraint set; obtaining a legal intermediate symbolic representation according to the constraint violation energy and the error information; and obtaining a structured image through a deterministic rendering mapping according to the legal intermediate symbolic representation. The method can accurately generate a structured image.

This application discloses a method, apparatus, device, and storage medium for detecting smart contract vulnerabilities, relating to the blockchain field. The method includes: acquiring formal deployment information of the smart contract; wherein the formal deployment information includes a formal initial state and a list of formal behaviors; the list of formal behaviors includes the smart contract's initialization execution function and behavioral functions; based on the formal initial state, executing the initialization execution function and behavioral functions included in the list of formal behaviors to obtain the execution result of the smart contract; and detecting the execution result of the smart contract according to a formal specification library of the smart contract, to obtain a vulnerability detection result, wherein the formal specification library includes the formal specifications of the smart contract. This solves the problem of low detection accuracy in existing smart contract vulnerability detection methods.

Enterprise software relies on numerous types and instances of mathematical and logical calculations for proper functioning, which are formally specified in spreadsheets, known as Calculation Specification (CS) sheets, that provide illustrations of the inputs and outputs of the calculation, and are expressed in inputs and formulae applied on them to get values for outputs. The values for such inputs are retrieved by executing ad hoc queries on respective application's database. Present disclosure provides systems / methods to synthesize code using CS sheets by formulating a Programming By Example (PBE) problem for each input involved in the calculation. A query synthesis technique is then implemented that uses natural language processing and enumerative program synthesis techniques to infer queries corresponding to the PBE problem. These queries are filtered based on whether their output is consistent with expected output in PBE. Finally, the synthesized queries and calculation formulae are translated into a desired target programming language.

The application provides an AI large model-based end-to-end intelligent system development method and system, which comprises the following steps: S1, receiving a system requirement described by a user through a natural language; S2, analyzing the requirement through an AI large model and converting it into a formal specification; S3, automatically generating a system architecture and component division; S4, recursively generating component codes; S5, dynamically detecting and repairing the generated code problems; S6, automatically integrating all components to form a complete system; and S7, continuously optimizing the system based on system feedback or user feedback. The application automatically completes the work of requirement analysis, architecture design, module division, code writing and testing and the like, and realizes distributed integration and intelligent contract: distributed integration verification is realized through a blockchain intelligent contract and a graph database, data consistency, interface matching and safety among components are ensured, the integration process is optimized, cross-field cooperation is realized, and the development efficiency is high.

Systems and methods to publicly certify a specification and its corresponding software for a software project. A publicly certified specification and its software can consist of a verified software that comes with an interpretation of the formal specification written in some accessible language, in such a way that at least an individual with mathematical training can check that the translation from the formal specification to a human language is, up to some extent, correct. The systems and method provided herein generate and revise a technical specification, a formal specification, algorithmic code and formally verified code for compilation and execution as a formally verified program.

A system for converting natural language (NL) requirements of an aerospace system to formalize to control a landing gear system of an aircraft using a large language model (LLM) includes a processor and a memory including instructions that, when executed by the processor, convert the NL requirements into formalities to control the landing gear system of the aircraft. The system is caused to use at least the LLM to revise the received NL expressions associated with the requirements of the aerospace system. The LLM is further configured to replace at least one word in the revised NL expression with a lifting atomic entity to generate an underlying sentence structure and convert the underlying sentence structure into a lifting logic. The LLM is also used for basic improvement of the logical expression and conversion of the NL expression into formalized requirements of an aerospace system. The system also controls the aerospace system based on the formal demand.

The invention relates to the field of crime scheme generation, and particularly discloses a task scheme generation system based on situation assessment, which is characterized in that high-level task requirements and current situation key features are converted into formalized specification problems, and an integrated reasoning engine is combined to perform deep fusion and collaborative reasoning on a rule library and a case library, so that the task scheme generation efficiency is improved. The system can generate a scientific and feasible task scheme on the basis of fully understanding a complex battlefield environment. Compared with a traditional method, the scheme not only improves the intelligent level of task scheme generation, but also enhances the accuracy and adaptability of case matching through mechanisms such as semantic embedding coding and the like, improves the diversity and tactical value of the scheme, and is suitable for popularization and application. And the urgent demand of a commander on high-quality and multi-selection decision support in a complex and changeable battlefield environment is met, so that the scientificity, timeliness and reliability of task commanding are remarkably improved.

The invention discloses a method and device for automatically generating a function test case for enhancing a large language model, and the method comprises the steps: S1, carrying out the symbolic execution of a tested program, and generating a test case; s2, performing function division on the function demand of the natural language description of the tested program, and generating corresponding sub-function description and formalized specification; s3, matching the generated test case with the divided formalized protocol, if matching succeeds, automatically generating a function label for the test case, and if matching fails, turning to step S4; and S4, enhancing the target test case which is unsuccessfully matched by using a large language model to generate a function description and a formalized specification of a sub-function corresponding to the case, and enhancing the target formalized specification to generate a corresponding test case. According to the method, the compatibility and the adaptability between the protocols and the diversified test cases can be improved, and meanwhile, the automation degree and the test efficiency of the test are improved.

A computer-implemented method of generating a presentation digital file and associated software application includes generating a pitch digital file; evaluating the digital file to determine a vector score or value for the digital file; determining a next artificial intelligence (AI) software tool or agent to initiate, execute or deploy with respect to the pitch digital file; generating a formal specification file based at least in part on the pitch digital file; automatically reviewing the formal specification file to determine quality parameters associated with the formal specification file; determining a second AI software tool or agent for a build and deployment phase to perform operations on the formal specification file; and generating via the build and deployment stage of the readiness workflow process, the most viable product (MVP) digital file from the formal specification file.

The application discloses a formal specification generation and verification method for ESBMC, which reduces manual intervention by combining a large language model with an ESBMC tool, can significantly improve the verification efficiency and accuracy of complex programs, and can fully reflect the real behavior of the program when processing programs containing complex control structures. The automatically generated specification can fully reflect the real behavior of the program when processing programs containing complex control structures. By using a large language model to analyze and extract program information, the preconditions, postconditions and loop invariant formal specification are automatically generated, which are input into the ESBMC tool for verification to obtain the verification result. The verification result of ESBMC is fed back to the specification generation module, the generated specification is refined and repaired, and the generation strategy is dynamically adjusted to optimize different program behaviors, so that the generated formal specification is accurate and effective. Through supervised fine-tuning and reinforcement training, the ability of the large language model is continuously optimized, so that the model can automatically adapt to the characteristics of different programs and generate more accurate specifications.

The application discloses a program formalization specification generation and verification method and system based on a large language model, relates to the field of program code formalization verification, and has the powerful computing capacity of the large language model, can efficiently generate a large amount of formalization specifications in a short time, and significantly improves the efficiency of formalization specification generation. Meanwhile, the generated formalization specifications are verified by combining a static verification method and a fuzzy test method, the specifications that fail in static verification are divided into static verification error specifications and timeout specifications, the fuzzy test is further performed on the timeout specifications, the problem of insufficient formalization specification generation caused by error feedback of the to-be-verified specifications due to the capacity limitation of a single verification method is reduced, and the success rate of formalization specification verification is improved.