10 results about "Seed testing" patented technology

A diversified validation test suite application (DVTSA) for a generative AI powered tool or large language model (LLM) tool includes at least first, second, and third control logics. The first control logic receives a seed test input or user input, analyzes the seed test input or user input, and extracts key elements for variations. The second control logic performs a coverage measurement of outputs of the first control logic. The third control logic causes a human validator to evaluate outputs of the second control logic relative to predefined coverage metrics and selectively and continuously iterate to cause outputs of the second control logic to increase LLM tool input robustness and output robustness from a first level to a second level greater than the first level, in both production and pre-production LLM tool processes.

This invention discloses an IoT fuzzing method based on LLM-guided and FSM dynamic inference, belonging to the field of IoT network security and software testing technology. Addressing the problems of low coverage and inaccurate state machine inference in current IoT protocol fuzzing, this invention first constructs an initial FSM by combining IoT protocol specifications and captured traffic data. Then, it generates a large number of test cases through mutation of seed test cases for fuzzing testing. Features are extracted from device responses, and state identification is performed by calculating similarity. When a new state appears, the FSM and state fingerprint database are updated. When coverage becomes a bottleneck, LLM-guided path inference is used to generate extended sub-FSMs and test cases, which are then executed. The FSM is then corrected based on the test results. This invention enables high-precision automated construction of IoT protocol state FSMs, improving test coverage and enhancing the efficiency and accuracy of vulnerability discovery.

The application discloses a kind of fuzzy testing methods for continuous integration process, it is related to software collaborative development field.The application includes the following steps: in the project of applying continuous integration, difference analysis is carried out to two adjacent submissions, the difference information of both is obtained, and change point is obtained according to difference information, and is stored in change point set;In the process of building project, data flow analysis is carried out according to change point information, and data flow analysis result is obtained;Program is inserted into using data flow analysis result, and the measured program that has been inserted is obtained;The measured program is carried out fuzzy testing, the fitness of seed test case is calculated in the testing process, and corresponding test resource is allocated to it according to fitness.The application more specifically tests the place where change is generated in continuous integration process, and reduces the overhead brought by manual construction test case.

A diversified validation test suite application (DVTSA) for a generative artificial intelligence (AI) driven tool or a large language model (LLM) tool includes at least a first control logic, a second control logic, and a third control logic. The first control logic receives a seed test input or a user input, analyzes the seed test input or the user input, and extracts varying key elements. The second control logic performs an overlay measurement of the output of the first control logic. The third control logic causes the human verifier to evaluate an output of the second control logic with respect to a predefined coverage metric, and selectively and continuously iterating such that the output of the second control logic increases LLM tool input robustness and output robustness from a first level to a second level greater than the first level during production and pre-production LLM tools.

This invention discloses a method for correcting seed testing data of *Gnaphalium affine* based on transfer learning, belonging to the field of seed quality testing technology. This method collects benchmark data from standard equipment under standard conditions and target data from different testing equipment and environmental conditions to construct an equipment-environment error database and fit an error influence function. The benchmark data is set as the source domain, and the target data as the target domain. A transfer correction model is trained to correct the target domain data, and the classification threshold is dynamically updated. The corrected data is then mapped to a unified feature space to verify consistency, ultimately outputting standardized results and data traceability information applicable across laboratories. This method effectively eliminates systematic errors, standardizes testing data, improves correction accuracy and data reusability, ensures result reliability and traceability, and provides technical support for the standardization of seed testing.

This invention discloses an intelligent rice variety classification system and method based on image recognition, aiming to address the technical pain points of existing rice variety classification methods, such as reliance on manual experience, low efficiency, large errors, incomplete feature extraction, insufficient classification accuracy, and poor adaptability. The system includes a dual-optical-path controllable image acquisition module, a rice-specific preprocessing module, a dual-branch feature decoupling and fusion extraction module, a few-sample classification inference module, and a result output and verification module. The classification method sequentially performs image acquisition, preprocessing, feature extraction, variety identification, and result verification. Dual-path images of rice varieties are acquired through dual optical paths, and after preprocessing, the dual-branch module extracts fused features, which are then identified by the few-sample classification module. This invention achieves non-destructive, rapid, and accurate intelligent classification of rice varieties, improves the accuracy of distinguishing highly similar rice varieties, reduces usage and maintenance costs, adapts to multiple scenarios, and is applicable to fields such as agricultural seed testing and breeding research.

A diversified validation test suite application (DVTSA) for a generative AI-powered tool or a large language model (LLM) includes at least a first, a second, and a third control logic. The first control logic receives seed test input or user input, analyzes the seed test input or user input, and extracts key elements for variations. The second control logic performs a coverage measurement of the outputs of the first control logic. The third control logic prompts a human tester to evaluate the outputs of the second control logic against predefined coverage metrics and to iterate selectively and continuously to ensure that the outputs of the second control logic increase the LLM tool's input and output robustness from a first level to a second level that is higher than the first, in both production and pre-production LLM tool processes.

The utility model relates to a sampling device for multi-station seed detection. The sampling device comprises a barrel with a hollow structure, and a sampling assembly is arranged in the cylinder body. The sampling assembly comprises a sampling head close to one end of the barrel for sampling, a sampling rod connected with the sampling head and a pushing piece positioned at one end of the barrel far away from the sampling head. A connecting assembly is arranged on the circumferential side face of the barrel. According to the multi-station sampling device, multiple parts of multi-station samples can be obtained from equidistant positions of a seed pile at the same height through one-time sampling work, and the working efficiency is effectively improved. Moreover, the nesting design of the sampling assembly and the cylinder facilitates safe placement of the sampling device when the sampling device is idle, avoids possible damage caused by direct exposure of the sampling head to the outside, and avoids mutual collision damage among a plurality of sampling devices, so that subsequent multi-station seed sampling work is facilitated.

The application discloses an intelligent peanut seed testing method based on a neural network model, first constructs a seed testing network model and carries out training, tests peanut seeds based on the trained network model, calculates a breakage rate, identifies a seed category, and determines a hundred-grain weight and a length-width ratio of the peanut. The scheme constructs the seed testing network model, when clustering an initial anchor frame, solves the problem that convergence is seriously dependent on initialization of a cluster center, avoids the problem that a local optimal solution is tended to when clustering the initial anchor frame, uses 1-iou instead of Euclidean distance, can obtain an anchor frame with better precision and higher accuracy, a CBAM sub-module is redesigned, a feature extraction network based on Darknet in an original network is removed, deep separable convolution and an inverse residual structure are added, the running speed and accuracy of the neural network are effectively improved, and intelligent seed testing of the peanut is realized.

The invention discloses an automatic soybean seed testing instrument, and relates to the technical field of soybean seed testing, the automatic soybean seed testing instrument comprises a weighing assembly, a threshing assembly is arranged on the left side of the top of the weighing assembly, a stalk crushing assembly is nested in the middle of the right side of the weighing assembly, and a separation counting assembly is arranged on the top of an inner cavity of the weighing assembly; a phenotype data acquisition assembly is arranged at the bottom of the separation counting assembly, and a soybean particle distribution assembly is arranged below the phenotype data acquisition assembly; the soybean particle distribution assembly comprises a fixing frame fixedly arranged at the top of the base, a bearing disc is fixedly arranged at the top of the fixing frame, and a plurality of containing channels are evenly formed in the inner side of the bearing disc. Compared with traditional manual threshing, the threshing efficiency is higher, compared with threshing of traditional threshing equipment, after soybean threshing is completed, the steps of transferring threshed soybean particles and the like are not needed, the automation degree is higher, and the seed testing efficiency can be effectively improved.