29 results about "Test data generation" patented technology

Disclosed herein is a training and deployment framework for a machine learning based recommendation system. In one aspect, a computer-implement method is provided for synthesizing training and testing data and using the training and testing data to generate a machine learning model. The computer-implement method includes deriving product ratings for products, the product ratings being stored in a user product score table in association with identifiers for users and the products, sampling the user product score table to generate a training and testing data set, training, using the training data set, machine learning models for a task of predicting product ratings, evaluating, using the testing data set, performance of the machine learning models, selecting one of the machine learning models for production use in predicting product ratings based on the evaluating, and predicting, using the selected machine learning model, new product ratings for the products.

The application discloses a thyristor control unit test system and method, and belongs to the field of power system testing. The method comprises the following steps: deciding test execution parameters of a debugging instrument based on acquired parameter information of a thyristor control unit; generating analog quantity input for thyristor control unit test through a program-controlled source based on the test execution parameters of the debugging instrument; and performing thyristor control unit test through the debugging instrument and a power load plug-in based on the analog quantity input; wherein the thyristor control unit test comprises forward normal trigger characteristic test and on-state protection and reverse recovery characteristic test; and when the thyristor control unit test is performed, test data of the thyristor control unit collected by the debugging instrument is used to generate a thyristor control unit test result. The application can realize automatic test of the thyristor control unit, and the test is efficient and convenient, and can be applied to in-plant single-plug production batch test.

This application discloses functional safety test circuits and methods, neural network processors, and storage media, relating to the field of functional safety technology. [Solution] The functional safety test circuit includes a configurator for generating and outputting configuration information for testing an integrated circuit under test; a plurality of test data generators for generating and outputting first test data corresponding to each of the plurality of test data generators based on the configuration information; an integrated circuit under test for processing the plurality of first test data and acquiring and outputting a plurality of second test data; and a first comparator for comparing the consistency of the plurality of second test data and acquiring a first test result of the integrated circuit under test.

The application provides a test image synthesis method for a slide scanner OCR function and application thereof, and belongs to the fields of medical image processing and computer vision. In view of the problems of low test data generation efficiency, high cost and incomplete complex scene coverage caused by the existing dependence on physical slide samples, the application receives a synthesis request containing a test strategy, extracts a target style template from a template library, and renders text into a base image; based on the strategy, a target disturbance model is selected from a pre-constructed disturbance model library specially simulating physical imaging defects of a slide label; the selected model is used for multi-layer mask fusion disturbance processing on the base image, a virtual test image is generated, and matched structured true value information is output. The application is mainly used for automatically and low-costly generating targeted high-fidelity test data in batches, so as to assist in directional evaluation and quality assurance of an embedded OCR function of a slide scanning software.

This application discloses an automated test data generation method and an automated testing method. The automated test data generation method includes: acquiring the requirements document and development document of the business system, and inputting the requirements document and development document into an AI analysis platform respectively; the AI ​​analysis platform outputs at least one target test object and business requirement information of the test object, wherein the at least one target test object includes a test object and a regression test object; inputting the business requirement information and each target test object into an AI data generation platform, the AI ​​data generation platform analyzes the business requirement information and each target test object, and generates test cases for each target test object, wherein functional test cases are output for the test object and regression test cases are output for the regression test object; and generating test data corresponding to each target test case according to the development document. Utilizing the embodiments of this application can reduce maintenance costs and improve testing flexibility.

The application discloses a kind of communication tunnel test data generation method and its device, electronic equipment, it is related to automatic test technical field, wherein, the test data generation method includes: determining initial configuration item;Based on target strategy dependency graph, configuration item extension is carried out to initial configuration item, obtains multiple target extension configuration items and at least one target extension configuration item value corresponding to each target extension configuration item, wherein, target strategy dependency graph is constructed by multiple configuration items and multiple constraint relations;Based on initial configuration item, all target extension configuration items and all target extension configuration item values, at least one combination test data for communication tunnel is generated.The present application solves the technical problem that different test data combinations are difficult to cover in related technologies, and there is a risk of missing measurement.

The application discloses a kind of test data generation method and device, it is related to software testing technical field.The specific embodiment of the method includes: receiving test data generation request;The target pipeline corresponding to the test data generation request is obtained, the target pipeline includes at least one target service interface, the target service interface is one-to-one corresponding with target processing element;The execution order of each target service interface in the target pipeline is obtained;According to the execution order, the target processing element corresponding to each target service interface is sequentially called to generate the test data corresponding to the test data generation request.The embodiment can reduce the time required to generate test data and is relatively efficient.

The application provides a wafer map generation method and system, the method comprising: obtaining test data of a target wafer, the test data comprising coordinate information and test result values of chips on the target wafer; generating a wafer map according to the test data, dividing the wafer map into a plurality of subunits along a horizontal direction or a vertical direction; obtaining attribute data of each subunit, the attribute data comprising coordinate positions, chip numbers and test data of the chips of the subunit; and independently storing the attribute data of each subunit of the wafer map. According to the technical scheme of the application, when data in the wafer map is called subsequently, the data in a certain region (subunit) in the wafer map can be called pertinently, the amount of data transmission is reduced, and the efficiency of calling wafer map data is improved.

This application discloses an AI-based test data generation system and method. The system includes: an atomic tool library storing N atomic tools; a tool invocation rule library storing the execution order and parameter passing dependencies of multiple atomic tools under various business scenarios; and a test data generation agent for performing the following processes: semantic parsing of test data generation requests to identify user intent and extract target parameters; querying the target business scenario corresponding to the user intent from the tool invocation rule library; constructing toolchain execution instances based on the target parameters and the tool invocation rules corresponding to the target business scenario; sequentially scheduling multiple atomic tools to execute test data generation tasks according to the toolchain execution instances, and passing the output results of upstream atomic tools to downstream atomic tools; and integrating the test parameters generated by multiple atomic tools to obtain test data. This application can improve the quality and efficiency of test data generation.

A testing method and system for electronic devices are provided. The testing method for electronic devices includes receiving multiple first test data for multiple first test cases and multiple second test data for multiple second test cases; generating multiple first local scores based on the multiple first test data; generating multiple second local scores based on the multiple second test data; generating a global score for a common test case of the multiple first test cases and the multiple second test cases; replacing at least some of the multiple first local scores with the global score to generate multiple first test scores; replacing at least some of the multiple second local scores with the global score to generate multiple second test scores; and performing a first mutation operation based on a first optimal test case corresponding to the highest score among the multiple first test scores to generate a first pre-test set.

The application discloses a cyclic code test data generation method based on deep learning fuzzy testing, comprising the following steps: guiding the selection of cyclic code seed data with high uncertainty by using the output uncertainty of cyclic code on a deep learning model; designing nine kinds of mutation rules to realize the mutation of cyclic code of different types; analyzing the correlation degree of each neuron and the error decision logic of the deep learning model; taking the maximum neuron coverage rate and the number of error behaviors as the joint optimization target, modeling the optimization target, taking the derivative of the target function as the gradient, selecting the mutation rule to mutate the seed, and using the gradient to iteratively mutate; realizing the mutation of the selected cyclic code seed data to complete the generation of cyclic code test data. The application uses the classification output probability of cyclic code on a deep learning model and related neuron information to design an optimization target, so as to effectively guide the mutation of cyclic code.

The application provides an AI deep learning-based semiconductor chip test management and control system, and belongs to the technical field of semiconductor manufacturing and intelligent management and control. The system comprises: a data acquisition and preprocessing module for acquiring and preprocessing multi-dimensional test data to generate a standardized data set; a real-time monitoring and early warning module for inputting the preprocessed first real-time data set into a full-dimensional yield difference analysis model, obtaining a real-time weighted average yield output by the model, and determining whether the difference between the yield and a benchmark yield exceeds a yield difference threshold; if it does, generating early warning information; a fault root cause analysis and decision module for, when a fault is identified, analyzing Fail information and fault scenario information in the fault data, inputting the information into a fault-spare intelligent matching model, obtaining a fault root cause and corresponding confidence and corresponding spare parts output by the model; a spare part recommendation and execution module for confirming the availability of the corresponding spare parts and generating a standardized replacement scheme.

The application discloses a physical condition guided image recognition test data generation method and device, belongs to the field of artificial intelligence testing, and mainly comprises the following steps: extracting physical characteristics and knowledge from natural language expressions given by a user, and constructing the physical characteristics and the knowledge into a structured physical knowledge dictionary; based on the obtained physical knowledge dictionary, constructing control conditions required for generating test images, including text conditions, data conditions and control graph conditions; generating test images according to the control conditions; and measuring the consistency between the generated test images and initial control conditions. The method utilizes a large language model and a condition-controllable image generation technology, fuses multi-dimensional physical knowledge, introduces specific controllable physical constraints in the image generation process, and can realize large-scale and high-efficiency generation of image recognition system test data conforming to physical reality.

The present disclosure provides a test data generation method and device and related equipment, relating to the technical field of artificial intelligence. The method comprises: obtaining test code; preprocessing the test code to obtain a vector sequence of the test code; inputting the vector sequence of the test code into a pre-trained test data generation model to output test data corresponding to the test code. The present disclosure can overcome the problem of tedious and time-consuming manual design of test data in related technologies to some extent.

The embodiment of the invention relates to the technical field of risk control rule testing, and provides a risk control rule testing method and device, and the method comprises the steps: carrying out the analysis of a to-be-tested risk control rule, extracting a control item of the to-be-tested risk control rule, and a calculation factor and a parameter value related to the control item; based on the control item, calling a corresponding historical test case template and a historical test data function in a pre-established rule index database; according to the calculation factor, the parameter value, a historical test case template and a historical test data function, obtaining or constructing test data meeting test requirements; generating a test message based on the test data; and testing the to-be-tested risk control rule based on the test message, and verifying the function correctness of the to-be-tested risk control rule. Therefore, low-cost, high-efficiency and high-quality testing of the risk control rule is realized.

The application provides a chip visual test method, system, device and storage medium. The method comprises: acquiring test data of a chip sensor; generating a visual mark according to the test data; and displaying the visual mark at a corresponding position of a chip layout according to a sensor coordinate mapping table, wherein the visual mark is located on a layer of the chip layout, and the visual mark coincides with a corresponding sensor in a physical coordinate of the chip layout. The application realizes real-time, dynamic and visual presentation of an alarm area by accurately mapping sensor alarm data and its physical coordinate in a chip layout.

The application discloses a low-code interface test case generation method, device and equipment and a storage medium, relates to the technical field of intelligent testing, and the low-code interface test case generation method comprises the following steps: receiving business category information, obtaining source code information according to the business category information; analyzing the source code information, extracting component information and focus order; obtaining component rules of the component information, generating first prompt information according to the component information and the component rules, sending the first prompt information to a large language model, and obtaining component test scene information; obtaining business scene knowledge, generating second prompt information according to the business scene knowledge, the focus order and the component test scene, sending the second prompt information to the large language model, and obtaining a flow test case; filling test data for data fields to be filled in the flow test case, and generating an interface automation test case. The application can improve the test case generation efficiency of the low-code interface.

The application discloses a path coverage test data generation method and system based on a reinforcement learning selection strategy, and relates to the technical field of software testing. The method solves the problems of long calculation time, low generation efficiency, unstable exploration process and redundant test data in the existing test data generation of large-scale path coverage or complex programs. The method comprises the following steps: acquiring all executable paths and numbers of a program to be tested; defining the executable paths as agent states and data selection as agent actions, and all states forming a whole state space; generating multiple groups of data according to an initial state obtained by an agent from initial data, and generating new data when the whole state space is not covered; selecting the data by a reinforcement learning selection strategy combining Q learning and a greedy method, defining an action reward function for the path coverage, and retaining the data with the maximum reward value as the new test data; and continuously updating until the test data covers the whole state space. The application is applied to the field of software product testing.

This invention discloses a method, apparatus, computing device, and storage medium for generating simulated road test data. The method includes: acquiring historical on-site road test data; determining the trend characteristics of signal indicator values ​​for any road segment based on the historical on-site road test data; acquiring MRO (Maintenance, Repair, and Overhaul) data for any user; determining the road segment matched to any user based on the MRO data and trend characteristics; determining the initial position of any MRO sampling point for any user based on the corresponding MRO data; acquiring the location information of the road segment matched to the user; calibrating the initial position of the user's MRO sampling point based on the road segment location information to obtain the calibration position of the MRO sampling point; and generating simulated road test data based on the calibration position of the MRO sampling point and the corresponding MRO data. Using this solution can improve the efficiency of road test data generation, reduce road test costs, and improve the accuracy of road test data.

A test device and a test method thereof are provided. The test device includes a plurality of connection lines, a plurality of first test circuits, and a plurality of second test circuits. The first test circuits respectively generate a plurality of detection signals according to a plurality of first test data, and transmit the detection signals to the connection lines respectively. The second test circuits receive the detection signals through the connection lines, and the second test circuits compare the second test data with the detection signals to generate a plurality of test results.

The application belongs to the technical field of domain models, and particularly relates to an interface test code generation system based on a domain model, which comprises a domain model management module, an interface contract analysis module, a domain-interface mapping module, a test case generation module, a test data generation module, an assertion generation module, a code generation module, an execution and feedback module. The application generates test cases and assertions by using domain rules, invariants and state machines, covers business correctness instead of only interface availability, improves the value of test cases, maps domain behaviors into multiple interface calling sequences, automatically generates pre-step, dependency graph and cleaning strategy, solves the problem of link arrangement difficulty, generates multiple types of test data according to domain constraints, is controllable and reproducible, realizes incremental update by comparing models and contract versions, reduces change maintenance cost, supports multi-language / cross-framework reuse, and reuses unified domain semantic assets.

This application provides a method, apparatus, device, medium, and program product for generating test data, which can be applied to the fields of big data, information security, and artificial intelligence. The method includes: sampling and querying a production database based on a target data volume to generate n original data entries; wherein each original data entry includes m fields, where m and n are integers greater than 1; based on each field in each original data entry, extracting sensitive information from each field to obtain sensitive information boundaries and sensitive types; performing data simulation on each field according to the sensitive types to generate simulation data; replacing each field based on the sensitive information boundaries and the simulation data to obtain test data corresponding to each field; and generating a test dataset based on the test data corresponding to the m fields in the n original data entries.

The application discloses a kind of test data generation method and device, it is related to program test technical field.The specific embodiment of the method includes: at least two data samples are generated using at least two pieces of data generated in production environment;Determine the product number segment information corresponding to production environment, and generate batch account information using product number segment information and the data sequence constructed;For each account information in batch account information, any data sample is combined with account information to form a piece of test data.The embodiment can effectively reduce the data leakage risk caused by test data.

This application discloses a method, apparatus, device, medium, and program product for generating software test data. The method includes: acquiring a test data generation request, the test data generation request including initial prompt text, the initial prompt text indicating the application system to be tested and the test scenario; performing at least one round of optimization on the initial prompt text using a Large Language Model (LLM) to obtain an optimized prompt set, the optimized prompt set including the optimized prompts obtained in each round of optimization; retrieving data constraint information related to each optimized prompt from a preset knowledge base, and embedding the data constraint information into the relevant optimized prompts to obtain a constrained prompt set; inputting the constrained prompt set into the LLM to obtain a data generation script set generated by the LLM; and generating test data corresponding to the test data generation request based on the data generation script set. According to the embodiments of this application, test data with high coverage and conforming to business logic can be automatically generated at a low cost.

The application provides a test data generation method and device, a storage medium and an electronic device. The method comprises: performing data preprocessing on a plurality of initial data information of each data object to obtain a plurality of target data information of each data object; performing clustering processing on the plurality of target data information of each data object to obtain a clustering result of each data object; determining rule generation indication data corresponding to each data object under each to-be-tested interface based on interface indication data of each to-be-tested interface and the clustering result of each data object; calling a target rule generation model to generate data generation rules corresponding to each to-be-tested interface based on the rule generation indication data corresponding to each data object under each to-be-tested interface, and the data generation rule corresponding to one to-be-tested interface is used to generate test data under the corresponding to-be-tested interface. The embodiment of the application can conveniently generate data generation rules to improve the effectiveness of test data.

This application discloses a method, apparatus, and electronic device for generating test data. Relating to the field of computers, the method includes: obtaining initial description content for describing a test data set; if a preset keyword exists in the initial description content, obtaining M first fields from the target sub-description content to which the preset keyword belongs; splitting the first sub-description content to which the first field belongs in the target sub-description content according to the first auxiliary fields under each first field, obtaining M sets of split sub-description content; replacing the target sub-description content in the initial description content with the split sub-description content corresponding to each first field, obtaining M sets of target description content; and obtaining the full test data of the test data set based on the M target description content. This application solves the problem in related technologies where the generated test data has strong randomness, leading to low efficiency and accuracy in generating full test data.

This application discloses a device testing method, apparatus, terminal device, and computer-readable storage medium. The method includes: acquiring historical user behavior data; analyzing the historical behavior data to determine key user usage scenarios; generating test data corresponding to the key usage scenarios; and testing the device based on the test data to obtain test results. The method of this application uses real historical user behavior data as the basis for generating test data, introducing key user usage scenarios between the historical user behavior data and the test data generation. These key usage scenarios serve as the basis for test data generation and device testing, reflecting representative operational characteristics and usage trajectories of users during real-world use, thus improving the authenticity and effectiveness of performance evaluation of the tested device.