251 results about "Unit testing" patented technology

The invention particularly relates to a unit test case rapid generation method based on an AI large model. According to the unit test case rapid generation method based on the AI large model, structure information is extracted through a static AST, an execution path is tracked through dynamic instrumentation, and code analysis is achieved; an analysis result is converted into cue words through AI, a multi-scene use case is generated through reasoning, and the multi-scene use case is matched with a language framework; counting row / branch / path coverage, identifying gaps and optimizing loop logic; hot spots and paths are displayed through a visual report, IDE one-key repair and manual correction of a feedback model are supported, intelligent retrieval and reuse of historical cases are realized by relying on FAISS, and the generation accuracy is continuously improved. According to the unit test case rapid generation method based on the AI large model, high-coverage-rate test case generation is achieved through the AI large model, the test case generation efficiency is remarkably improved, the test period is shortened, the software quality is improved, the workload of manually compiling and maintaining the test case is reduced, and the development cost is reduced.

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.

The invention discloses a full-process automatic unit testing method, device and equipment for an AI chip operator, a medium and a product. The method comprises the following steps: generating an engineering directory and a test framework design document through an architect agent according to operator interface information and a DSL operator design document knowledge base; the method comprises the following steps of: generating a test code for unit test by a software engineer agent according to a test framework design document and a domain knowledge base, and storing the test code in an engineering directory; multiple rounds of interaction are carried out through a software engineer agent and a test engineer agent, a test code is gradually corrected into a target test code which can be successfully compiled, a generated test case can be successfully executed and the generated test case meets the code coverage rate requirement, and a target operator code passing a unit test is obtained; and submitting the target operator code and the target test code which pass the normativity check to a code warehouse through a code auditing engineer agent so as to automatically realize the whole-process unit test of the AI chip operator.

The invention discloses a method and device for automatically generating a Java method unit test case based on AI, and the method comprises the steps: building a structured annotation specification, carrying out the automatic traversal and intelligent analysis of a Java project, extracting a method signature, a parameter type and a parameter constraint condition, constructing a test data generation model, and carrying out the automatic generation of the test case. The model is transmitted to an AI service to analyze business logic and boundary conditions, test case codes are generated, test cases are optimized and integrated to a project test directory, finally, code areas with insufficient coverage are identified through coverage rate analysis, a test completion strategy is generated, and iterative perfection of the test cases is completed. The technical problems that in the prior art, project-level automatic test case generation cannot be achieved, the generated test case cannot fully cover business logic and boundary conditions, and context relation understanding is lacked are solved, full-automatic project-level test generation is achieved, and the test efficiency and quality are improved.

The invention discloses a code generation method and device based on a large model, equipment, a medium and a product, and the method comprises the steps: carrying out the code generation through a first code large model according to target code demand data, and obtaining an initial code; according to the first code snippet, generating a test code through a second code large model to obtain a unit test code; according to the unit test code and the initial code, code repair based on editing distance regularization is conducted through a third code large model, and a to-be-analyzed code is obtained; performing iterative optimization on the to-be-analyzed code and the unit test code to obtain a target code corresponding to the target code demand data; according to the method, code generation, unit test generation and code repair are carried out in a multi-model cooperation mode, the reliability and accuracy of code generation can be effectively improved, software security vulnerabilities are reduced, and therefore the stability and security of a software system are improved.

The invention relates to the technical field of vehicle software testing, and discloses a vehicle unit test code generation method and device, equipment, a medium and a product. The method comprises the steps of obtaining a tested code; the tested code and the intention prompt word are input into a large language model to be analyzed, a test intention is generated through the large language model, and the test intention is used for indicating the process needed for testing the tested code; inputting the test intention, the tested code and the template cue word into a large language model for analysis so as to generate a test strategy through the large language model, and recommending a code template and a parameter value required by the test from a template library; and integrating the recommended code templates according to the test strategy, and filling the parameter values into the code templates to obtain test codes. The AI illusion is reduced, and the accuracy of generating the test code is improved.

The invention belongs to the technical field of software engineering, and particularly relates to a unit test method for generating a discrimination model based on retrieval. Searching a to-be-tested function, namely a test case pair, and establishing a code library; constructing an efficient code retriever based on code embedding and mixed feature extraction; constructing a multi-input matching discriminator network, preparing an own data set, and training the network; integrating the code library, the retriever and the discriminator into a local knowledge base, and performing fine adjustment on the large model based on the local knowledge base to obtain a retrieval generation discrimination model; and generating a test case based on the retrieval generation discrimination model, and testing. According to the method, the discrimination model is generated by using retrieval, corresponding change is automatically carried out according to the previous test case, and the test with higher coverage rate and quicker speed can be realized.

The invention provides a code analysis method, system and equipment based on a multi-programming language sandbox and a medium, and belongs to the technical field of code analysis and detection.The method specifically comprises the steps that an input code and a corresponding unit test sample are obtained, and a programming language type specified by the code is determined; sending the code and the unit test sample to a sub sandbox environment of a corresponding language for execution; a compiler in the sub sandbox reports a missing library according to a code compiling result and prompts a user to install the missing library; calling an analysis tool of a code analysis module to analyze the code; compiler feedback of the sub sandboxes and various analysis results generated by the code analysis module are integrated into a large language model; inputting the integration result into a large language model through a preset template; and analyzing and evaluating the code case based on the user instruction. Through multi-language sandbox isolation, automatic analysis tool integration and large language model enhancement, the security, efficiency and quality of a code processing flow are improved.

A large language model, trained on source code and natural language text generates a unit test for a change to a file in a pull request of a code repository. An ordered sequence of prompts is created and each is applied serially to the large language model to perform an individual task that leads to the generation of the unit test. The unit test may be added to an existing file or generated as a newly-created file. Each prompt includes the data from a previously-issued prompt of the ordered sequence in order for the model to retain contextual knowledge learned previously. The model generates the unit test as update commands when the unit test is added to an existing file.

The invention discloses a high-precision multi-interface collaborative FTU dynamic function test system and method. The system comprises a protection unit, a test bearing unit, a core test unit and a control system, the protection unit is composed of an acrylic transparent protection cover and a metal plate box body, and a test space is formed. The test bearing unit comprises a quickly replaceable carrier plate, an access structure and a positioning assembly, and the positioning assembly comprises a positioning pin and a guide block; the core test unit comprises a pressing plate structure, an endoscope and a test module; the test module is integrated with a key, a short circuit bolt, a network port, a DB9 and an aviation plug test module; the safety detection unit comprises a safety grating, an anti-pinch device and a pre-feeding induction mechanism, and the safety grating is arranged at the inlet of the test space; and the control system controls starting, execution and result uploading of the test process. The method is used for solving the technical problems of insufficient positioning precision, poor interface test collaboration, low safety protection reliability and limited automation and intelligence level in the existing FTU test.

The invention belongs to the technical field of software engineering, and particularly relates to software testing, in particular to a unit testing method based on a large model. Reading a source code from the tested unit; the code features are enhanced through an enhancement method; performing endpoint labeling and segmentation on the code by using a multi-dimensional code correlation comprehensive evaluation analysis method; inputting the segmented code into a code task unit test thinking chain template and generating a corresponding unit test; the segmented unit test is sent to coverage rate detection and coverage information analysis, and a unit test report is automatically generated according to a test report model; the uncovered information is fed back to the thinking chain to be repaired, and a repaired unit test case is generated and moved backwards. According to the method, the unit test case generated by the segmented feedback thinking is used, so that the test with higher coverage rate can be realized on the whole under the condition that a local high coverage effect is achieved.

A method of generating a code output in response to a natural language problem description. The method includes: receiving the natural language problem description; generating, by a neural network based language model, a first candidate code snippet based on a first input prompt combining the natural language problem description and a first instruction; executing, at a code execution environment, the first candidate code snippet based on a unit test thereby producing a first feedback reflecting a correctness of the first candidate code snippet; generating, by the neural network based language model, a second candidate code snippet based on a second input prompt combining the natural language problem description, the first candidate code snippet, and the first feedback; and executing, at the code execution environment, the second candidate code snippet based on a runtime test thereby producing a second feedback reflecting a runtime efficiency of the second candidate code snippet.

The invention discloses a unit test code generation method, system and device and a medium, which are applied to the technical field of code generation, and comprise the following steps: performing program structure interface analysis and abstract syntax tree analysis on a target engineering code to obtain a structured meta-information set and a source code syntax structure model; generating a structured context feature vector based on the structured meta-information set and the source code grammar structure model, and retrieving a historical test case sample set from a historical test case database, wherein the global line coverage rate weighted similarity of the historical test case sample set and the structured context feature vector meets a matching condition; after Prompt template filling of different test subtasks is performed based on a historical test case sample set and structured context data through an Agent agent, different modular test codes are generated by adopting different test code generation models, and closed-loop verification is performed after the different modular test codes are integrated into unit test codes. Therefore, the code quality, practicability and adaptability are improved.

An assert statement generator employs a neural transformer model with attention to generate candidate assert statements for a unit test method that tests a focal method. The neural transformer model is pre-trained with source code programs and natural language text and fine-tuned with test-assert triplets. A test-assert triplet includes a source code snippet that includes: (1) a unit test method with an assert placeholder; (2) the focal method; and (3) a corresponding assert statement. In this manner, the neural transformer model is trained to learn the semantics and statistical properties of a natural language, the syntax of a programming language, and the relationships between the code elements of the programming language and the syntax of an assert statement.

The invention relates to the technical field of computers, in particular to a code sample optimization method and system based on a language large model, and the method comprises the steps: firstly, obtaining a source code sample, determining a code sample boundary, and generating a mark sequence; then, based on a compiling result, a static analysis result and a unit test result, a quality label is generated, and a training sample set is formed; then, taking a Transform neural network model of bidirectional context coding as an encoder, and carrying out training under the supervision of quality annotation to obtain a quality evaluation model; and finally, screening according to a preset quality score threshold to obtain a high-quality code sample set. According to the technical scheme, by combining the deep grammar analysis and context understanding of the code samples, the accuracy and efficiency of automatic screening are improved, manual intervention is reduced, and the method can adapt to automatic evaluation of a large-scale code library.

The invention discloses a method for realizing a redundant function memory chip test, which relates to the technical field of memory chip test, and comprises the following steps: calculating hyperedge coupling strength based on a hypergraph fault model, and generating a test vector sequence and a memory unit test instruction by adopting a weighted flipping mode according to the hyperedge coupling strength; injecting the test vector sequence into a tested memory chip, executing memory unit test instructions one by one, and capturing a failure unit coordinate and a failure mode category at the same time; constructing a Hall triad based on the failure unit coordinates and the failure mode category, executing theorem proving on the Hall triad by using a theorem proving device to verify the test completeness, generating an increment test vector when the verification fails, executing theorem proving again, and recording the result of the test completeness; according to the method, the hypergraph fault model is established, so that the coverage rate of non-independent faults is increased, the number of redundant test instructions is reduced, the test time and resource consumption are reduced, and the defect detection efficiency is improved.

The invention relates to the technical field of artificial intelligence, can be applied to the medical field and the financial field, and discloses a software unit testing method and device, computer equipment and a storage medium. The method comprises the steps that an original version and an updated version of a production code are received, and the code difference between the original version and the updated version is analyzed based on a large language model; identifying an affected target element; calling a code analysis tool to obtain a context definition corresponding to the target element; constructing a structured prompt in combination with the code difference and the context definition, and generating an initial version of the updated unit test based on the structured prompt; and performing a verification correction loop test on the initial version of the unit test until a preset termination condition is met or the maximum number of iterations is reached, and outputting a corresponding test result. The method can solve the problems that the context is not fully acquired, only can be repaired but cannot be enhanced, the accuracy is low due to lack of verification and correction of a closed loop, task processing is not specialized due to single architecture, and the like.

The invention discloses a unit test coverage rate intelligent optimization method guided by using a control flow. The method comprises the following steps: S1, obtaining and preprocessing a to-be-tested code; s2, a cycle generation stage: calling a predefined tool by using a large generative model to dynamically obtain a code to be tested, and generating a unit test code; s3, repairing the unit test codes which fail to compile or run; s4, acquiring the coverage rate and coverage information of the unit test code; performing control flow analysis on the to-be-detected code according to the coverage information and the coverage rate, and outputting a control flow information set; and uncovered control flow information is fed back to the generation cycle stage as output. According to the method, the automation degree of unit test generation based on the large model is high, the effectiveness of the codes generated by the large model is effectively improved, the coverage rate of the unit test codes generated by the large model is obviously improved, and the problems that the effectiveness of the codes generated by other unit test automatic generation tools based on the large model is low and the coverage rate in a complex scene is low are solved.

The embodiment of the invention relates to a test code generation method, device and equipment and a readable storage medium, test codes are iteratively generated through an LLM model, coverage rate improvement is automatically verified, a compilation failure rollback mechanism and environment adaptation are combined, automatic closed-loop control of test code generation and coverage rate improvement is achieved, and the test code generation efficiency is improved. And the manual writing and debugging cost is effectively reduced. And the generated test code is subjected to multiple rounds of compilation verification, so that the grammar correctness and the execution feasibility are ensured. The generation direction is continuously optimized through a dynamic feedback mechanism, and the coverage range of unit testing on target codes is systematically improved. And finally, automatically terminating the process when a preset quality index is reached, and outputting an effective test code set which is fully verified.

The invention relates to a code generation method and device, electronic equipment and a storage medium. Comprising the steps of obtaining a programming problem data set and a code generated by a target model, and obtaining a data set with rewards; based on an MSE regression training strategy and a comparison loss training strategy, training a reward model by using the data set with the reward to obtain a code reward model; and obtaining programming problem training data, sorting the programming problem training data by using the code reward model to obtain sorted training data, and obtaining a final reward according to the sorted training data, a reward model score output by the code reward model and a preset unit test score, and reinforcement learning training is carried out on a preset language model to obtain a code generation model, so that codes meeting preset performance requirements are generated through the code generation model. Therefore, the problems that in the prior art, the model reasoning cost is high, and it is difficult to capture the intermediate state and partial correctness in the code execution process to evaluate the code quality in a fine-grained mode are solved.

In a first use case, a description of source code to be created is validated and used to form a prompt for a large language model (LLM). The prompt is provided to the LLM to generate an output. The output from the LLM is post-processed to generate the source code. In a second use case, a source code file is processed and provided, along with instructions, to an LLM. The LLM provides a list of the methods in the source code file. The LLM is requested to provide a unit test for each of the listed methods. The output from the LLM is post-processed to generate unit tests for the methods in the identified source code file. In a third use case, the LLM is used to generate unit tests for new methods added to the source code file after unit tests were generated.

The invention relates to the technical field of board card testing, in particular to a board card automatic testing system and method and a storage medium, and the system comprises an upper computer which comprises a processor, a memory, a human-computer interaction interface and a communication interface; the tool body comprises a test bottom plate, a board card clamp and a pneumatic execution unit which are arranged in the tool case, and the test bottom plate is connected with the power supply module and is provided with an instruction analysis and drive circuit; the instruction analysis and drive circuit is connected with a communication interface of the upper computer and is in control connection with the pneumatic execution unit; the pneumatic execution unit is provided with a needle bed, and the needle bed is provided with a test needle. The board card control unit comprises a communication interface circuit which is electrically connected with the microcontroller and is connected with a communication interface of the upper computer; the detection end of the function detection sensor is electrically connected with the test needle; the signal processing module is electrically connected with the function detection sensor; and the microcontroller is electrically connected with the function detection sensor and the signal processing module. According to the invention, efficient, accurate and full-automatic board card testing can be realized.

One or more unit-test cases are generated from a monolingual code corpus and the generated unit-test cases are filtered to generate a corpus of unit-test cases which have acceptability scores exceeding one or more predefined thresholds. One or more of the code samples of the monolingual code corpus are translated from a source language to a target language using a pretrained Large Language Model and the generated unit-test cases are translated from the source language to the target language. The LLM-translated code samples are validated using the translated unit-test cases and a parallel-data training corpus comprising the LLM-translated code samples that pass the validation is created. The pretrained large language model (LLM) is fine-tuned using the parallel-data training corpus, a given code segment is translated using the fine-tuned large language model (LLM), the translated given code segment is tested and the tested given code segment is deployed.

A method of generating a code output in response to a natural language problem description. The method includes: receiving the natural language problem description; generating, by a neural network based language model, a first candidate code snippet based on a first input prompt combining the natural language problem description and a first instruction; executing, at a code execution environment, the first candidate code snippet based on a unit test thereby producing a first feedback reflecting a correctness of the first candidate code snippet; generating, by the neural network based language model, a second candidate code snippet based on a second input prompt combining the natural language problem description, the first candidate code snippet, and the first feedback; and executing, at the code execution environment, the second candidate code snippet based on a runtime test thereby producing a second feedback reflecting a runtime efficiency of the second candidate code snippet.

Techniques for fast smart contract processing and validation. A C3N smart contract may be written in a high-level programming language such as Go rather than a domain-specific language (DSL) for smart contracts that is difficult to learn and utilize correctly. The smart contract may support a predefined list of C3N libraries, including APIs for accessing components within a C3N containerized environment. The smart contract may natively support access to oracles and data external to the C3N blockchain. The C3N smart contact may be deployed as source code or executable code for one or more target architectures. Such executable code may be run directly on the target architectures without additional compilation or interpretation. Validator nodes can verify correct execution of C3N smart contracts through unit tests.

The invention discloses a method and equipment for testing an AUTOSAR AP application program. According to the method, a calling instruction containing a module, an interface and a parameter data type is obtained by analyzing an ARXML file, a corresponding function template is matched according to the module and the interface in the instruction, the parameter data type is written into the template to generate adaptive stub functions, and finally unit testing of the application program is completed based on the stub functions. According to the method, automation of stub function generation is achieved, manual writing and adjustment are not needed, and the error rate and workload caused by manual operation are greatly reduced; through accurate matching of the parameter data type and the function template, the consistency of the stub function and the application program interface is ensured, and the accuracy of unit testing is improved; the whole process adapts to the standardization characteristic of the AUTOSAR AP, and the efficiency and reliability of application program unit testing are remarkably improved.

The invention discloses a whole-process intelligent unit testing method driven by a large language model, belongs to the technical field of software testing, and aims to solve the problems of poor testing quality, difficulty in effective understanding of testing intentions and low coverage rate of testing codes in existing unit testing. The method comprises the following steps: intelligently analyzing a to-be-tested code driven by a large language model; automatically generating a test code driven by the large language model; testing code intelligent verification driven by the large language model; error codes driven by the large language model are automatically repaired; and automatic construction of a test suite and intelligent evaluation driven by a large language model. According to the method, the advantages of the large language model in the aspects of natural language understanding and code generation are fully played, so that the large language model can more accurately grasp the test intention and the function requirement, the generation quality and the coverage range of the test code are remarkably improved, and a brand new solution is provided for realizing efficient, intelligent and whole-process automatic unit test generation.

The invention relates to the technical field of software testing, and discloses a unit test code generation method, which comprises the following steps: analyzing a source code of software to be tested through a PSI framework, and generating a template code corresponding to a unit test; filling the source code and the template code through a preset prompt word to obtain a filling source code and a filling template code; generating an initial code according to the filling source code and the filling template code through a preset generation model; performing static detection on the initial code through a PSI framework to obtain a static detection result; and when the static detection result represents that the initial code does not have an error, executing automatic verification on the initial code, and when the automatic verification result represents that the initial code does not have error reporting information, determining the initial code as a target code. Through static detection of the PSI framework and dynamic detection of automatic verification, detection of code accuracy is achieved, the accuracy of the target code and the generation efficiency of the code are improved, and then the coverage rate of service logic is increased.

The invention relates to the technical field of software testing, in particular to a test item generation system based on large model and retrieval enhancement generation, which comprises a test item knowledge base construction module and a test item generation module which work cooperatively, the test item knowledge base construction module comprises a document analysis unit, a table extraction unit, a table standardization processing unit and a vectorization unit which are in cascade connection, and is used for analyzing a test outline document and constructing a test item vector database supporting semantic retrieval; the test item generation module comprises a double-document analysis unit, a large model cleaning unit, a test demand alignment unit and a retrieval enhancement generation unit which are connected in sequence, and is used for performing joint semantic analysis on a demand document and a task book, and retrieving a data volume library based on a test item to generate an optimized test item; according to the method, the understanding capability of a large model on task books and demand documents is effectively enhanced, the reuse rate of historical test items is improved, and the completeness and accuracy of test item generation are improved.

The invention relates to an OCamml unit test system, which adopts a layered architecture design and comprises a test driving layer, a test case regulation layer and a test suite function layer. The test driving layer automatically manages compiling, execution and result archiving of OCAML test codes through Makefile scripts; the test case regulation layer defines and organizes test cases based on a standardized template, and each test case annotates and declarates information such as a unique identifier and an airworthiness demand number through structured metadata; the test suite function layer comprises an assertion module, a report generation module, a data conversion module and a test auxiliary module. Through the layered architecture design, standardized management and automatic execution of the test process are realized, the standardization and traceability of the test activity are ensured, a complete demand-test-verification traceability evidence chain is provided for airworthiness certification, and the strict requirement of the high-security field for unit test is met.