34 results about "Seed testing" patented technology

The invention relates to the technical field of soybean seed testing, in particular to an improved soybean seed testing system and method based on YOLO v8, and the system comprises a pod recognition network and a pod image restoration network. The pod identification network adopts an improved YOLO v8 network combined with a mixed attention module in a detection head to carry out pod and stem identification to obtain a stem image in a pod image and an independent image of each pod in the pod image; the pod image restoration network adopts an adversarial neural network to restore the pod independent image; according to the method, the attention mechanism for extracting local and global features is introduced, so that the target frame can be more accurately positioned to the target area, and the detection precision is improved; in the method, a loss function combined with ShapeIoU loss is used, the loss is calculated by paying attention to the shape and the scale of a bounding box, so that bounding box regression is more accurate, and high-precision soybean seed testing is completed by combining calculation and statistics of independent image characters of bean pods.

The invention relates to the technical field of soybean seed testing, in particular to a soybean stalk seed testing device and portable seed testing equipment, which comprises a scanning bin, a chuck, a Y-axis movement unit, a 3D scanning unit, an electric turntable, an electric control unit and a display, the Y-axis movement unit can move in the height direction; the 3D scanning unit performs imaging scanning on the stalks; the electric rotary table drives the stalks to rotate by 360 degrees; the electric control unit controls scanning; according to the device, the electric control unit controls the electric rotary table and the Y-axis movement unit, the 3D scanning unit is matched, all-directional imaging scanning of soybean stalks is achieved, appearance and internal feature information is accurately obtained, and phenotype analysis accuracy is improved; according to the automatic seed testing process, manual intervention is reduced, seed testing time is shortened, efficiency is improved, and the problems that a traditional seed testing method is low in efficiency and prone to being interfered by subjective factors, and the requirements of precision agriculture for high throughput and multi-dimensional data cannot be met are solved.

The invention discloses a multi-coverage-rate-guided voice intelligent model test data generation method and system. The method comprises the steps that a to-be-tested voice intelligent model and a seed test data set are input; the coverage rate of the voice intelligent model to be tested under different neural network coverage rate indexes is analyzed; randomly selecting one or more variation strategies to perform variation on the seed test data; defining a strong variation number constraint condition, preliminarily filtering variation data, calculating four neural network coverage rates of the voice intelligent model to be tested by using the filtered variation data, and selecting variation data of which the coverage rate of the model to be tested is improved compared with that before variation to form variation data sets corresponding to different neural network coverage rate criteria; and outputting a coverage rate calculation result of the to-be-tested voice intelligent model on the seed test data set and the selected variation test data set. The diversity of test data is improved, and the sufficiency of voice intelligent model test is ensured.

The invention discloses a method for accurately identifying sweet-waxy corn germplasm, and particularly relates to a method for identifying sweet-waxy corn germplasm, which comprises a first tracking process: a process from F3-generation seed budding to F4-generation seed maturation, including sweet-waxy gene DNA tracking marking after seed budding; sampling once 28 days after pollination, and measuring the thickness of soluble sugar, amylose, amylopectin and pericarp; extracting DNA (deoxyribonucleic acid) and RNA (ribonucleic acid) of F3-generation plants in a After the F4-generation seeds are mature and picked, determining sweet-waxy gene DNA, determining amylose and amylopectin, and determining single-plant grain weight, hundred-grain weight and endosperm / embryo dry weight; a second tracking process: a process from germination of the F4-generation seeds to bearing of fresh sweet-waxy corn, including observation and recording of a field corn plant growth process; measuring the thickness of soluble sugar, amylopectin, amylose and pericarp 15 days after pollination; determining and analyzing the traits of the indoor test species; data analysis and germplasm scoring: comparing and analyzing the data obtained in the second tracking process, scoring the F4-generation seeds, and determining the germplasm quality of the F4-generation seeds.

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.

1. Name of the product in this design: Rice Seed Testing Machine. 2. Purpose of this design: for high-precision intelligent seed testing of single rice panicles. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key features: the front view.

The invention relates to the technical field of soybean seed testing, in particular to a bean pod and seed testing device which comprises a bean pod discharging opening, a bean pod shell discharging opening and a soybean discharging opening which are formed in the outer portion of a device body, and a bean pod feeding unit, a bean pod imaging unit, a soybean shelling unit and a soybean imaging unit which are arranged in the device body. Bean pod conveying, bean pod image acquisition, hulling separation and soybean image acquisition are realized; the device is also provided with a control button and a display for operation and data display. According to the technical scheme, the full-automatic process from pod feeding, image acquisition, shelling to soybean seed detection is achieved, manual intervention is reduced, the seed testing time is remarkably shortened, and the seed testing efficiency is improved; the problems that a traditional test method is low in efficiency and prone to being interfered by subjective factors, and accuracy and consistency of data are difficult to guarantee are solved.

The invention relates to the technical field of seed testing equipment, in particular to a beet pelletized seed wear resistance testing device, which comprises a roller provided with a testing cavity; the driving assembly is used for driving the roller to rotate; the collision assembly comprises a protruding mechanism and a fixing mechanism; the cleaning assembly comprises an impact gas storage mechanism, an energy storage mechanism, a storage mechanism, an injection mechanism and a dust collection mechanism; according to the collision assembly, through direct collision between the protruding mechanism and the pelletized seeds, the requirement for testing the wear resistance of the seeds is accurately simulated; through linkage of the collision air storage mechanism and the injection mechanism, seed collision kinetic energy is reasonably utilized, collision energy is recycled and converted into compressed air and electric energy, the stored energy can be utilized to clean the inner wall of the roller through the cleaning assembly after a test is finished, energy recycling is achieved, and the subsequent test precision is effectively improved.

This invention relates to the field of soybean seed testing technology, and more particularly to a device for soybean seed testing. The device includes a pod feeding port, a pod shell discharge port, and a soybean discharge port located outside the left side of the main body of the device. Inside, there are pod feeding, imaging, soybean shelling, and soybean imaging units, enabling pod conveying, pod image acquisition, shelling separation, and soybean image acquisition. A straw scanning chamber is located outside the right side of the main body of the device, containing a Y-axis motion unit, an electrical control unit, an electric turntable, a chuck, and a 3D scanning unit. The electric turntable and 3D scanning unit can scan the straw in all directions. The device also includes control buttons and a display for operation and data display. This technical solution solves the problems of low efficiency, subjective data, and lack of comprehensive analysis of key traits of pods and straw in manual seed testing, making it impossible to achieve a comprehensive, efficient, and accurate evaluation of soybean traits.

The utility model relates to the technical field of seed testing devices, and discloses a tetraploid rice seed testing device which comprises a machine body and a feeding cylinder fixedly connected to the machine body, the top of the feeding cylinder is fixedly connected with a feeding hopper, the top of the inner wall of the feeding cylinder is slidably connected with a vibration frame, one side of the feeding cylinder is provided with a through groove matched with the vibration frame, and the through groove is communicated with the feeding hopper. A vibrating assembly for vibrating the vibrating frame is fixedly connected to one side of the feeding cylinder and located below the through groove, and a mounting groove is formed in the top of the vibrating frame; according to the tetraploid rice seed testing device, after rice sample seeds fall onto the filter plate through the feeding hopper, the filter plate can vibrate through the operation of the vibration assembly, so that the screening efficiency of the filter plate on the rice sample seeds is improved, impurities can be discharged through the discharging groove after the rice sample seeds are screened by the filter plate, and the screening efficiency is improved. A worker does not need to frequently clean impurities on the filter plate, so that the device is more convenient to use, and the rice seed testing efficiency of the device is effectively improved.

The invention provides a test method and system based on artificial intelligence. According to the method, the position of a given source code is set as a first target; the source code is compiled for the first time to obtain a function call graph and a control flow graph, the function call graph is used for representing the relation between functions, and the control flow graph is used for representing the relation between basic blocks; obtaining distance values between all the basic blocks and the first target according to the first target, the function call graph and the control flow graph; compiling the source code for the second time so as to carry out instrumentation on the basic block, and taking the distance value as a distance used during instrumentation; when the coverage rate of the test is smaller than a first threshold value, a first variation strategy is used for testing the source code, and when the coverage rate is larger than or equal to the first threshold value, a second variation strategy is used for testing the source code; the first variation strategy comprises the use of a decision model based on deep learning; the second variation strategy comprises the step of selecting the seed test case with the maximum use energy value.

The invention discloses a corn seed testing machine and a corn seed testing method, and relates to the technical field of seed testing, the corn seed testing machine comprises a tray, a weighing device, a centering clamp, a self-tapping screw, a cutter, a first area-array camera, a line scanning camera, a second area-array camera and a corn retreating baffle; the first area-array camera can photograph the outer side surface of the corn on the tray; the weighing device can weigh the corn on the tray; the centering clamp can center, clamp and fix a corn, the self-tapping screw can be drilled into a corn cob of the corn clamped by the centering clamp, and the line scanning camera can scan and photograph the outer side face of the corn connected to the self-tapping screw by a circle; the cutter can cut off the corn connected to the self-tapping screw, and the second area-array camera can photograph the cross section of the corn connected to the self-tapping screw; according to the invention, the image of the corn can be accurately, conveniently and comprehensively obtained.

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.

The present invention relates to the technical field of soybean seed testing, and in particular to a soybean seed testing system and method improved based on YOLO v8. The system comprises a pod recognition network and a pod image restoration network. The pod recognition network adopts an improved YOLO v8 network combined with a hybrid attention module in a detection head to identify pods and stems, thereby obtaining a stem image in a pod image and an independent image of each pod in the pod image. The pod image restoration network adopts an adversarial neural network to restore the independent pod image. The present invention introduces an attention mechanism for extracting local and global features, so that a target frame is more accurately positioned in a target area, thereby improving detection accuracy. The method uses a loss function combined with ShapeIoU loss, calculates the loss by focusing on the shape and scale of the bounding box itself, thereby making the bounding box regression more accurate, and combines the calculation and statistics of the characteristics of the independent pod image to complete high-precision soybean seed testing.

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.

The utility model aims to provide a water-replenishing-free simple germination box device for seed inspection, and relates to the technical field of seed inspection, a water storage tank is rotatably arranged on a base, a plurality of germination boxes are arranged on the outer circumference of the water storage tank in an array mode, and outer boxes of the germination boxes are communicated with the water storage tank through upper pipelines and lower pipelines; water in the water storage tank is supplemented into the outer tank through the lower pipeline, and the liquid level in the outer tank is kept at a certain height through the upper pipeline, so that the sponge in the inner tank is always soaked in the water, the humidity of seeds in the inner tank is kept, regular manual watering is not needed, and the workload is reduced; the moving part is arranged on the outer box in a sliding mode, during use, the distance between the inner box and the bottom of the outer box is controlled by sliding the moving part, the soaking depth of sponge at the bottom of the inner box in water is controlled, and therefore the humidity of seeds is controlled; the sliding of the moving part is limited through the cooperation of the limiting columns and the limiting holes in the outer box.

The invention relates to the technical field of soybean seed testing, in particular to an improved soybean seed testing system and method based on Transform-faster-Rcnn. In the system, a pod recognition network based on a Swin-Transform structure is used for accurately recognizing pods and stems in a natural form mature state; the problem of mutual shielding between pods is solved through a pod image restoration network of an adversarial neural network structure. The phenotype recognition efficiency and accuracy in a complex scene are remarkably improved by optimizing a network structure; in the method, an identification loss function combined with FocalLoss loss is adopted, so that the loss contribution of easy-to-classify samples is reduced, the model pays more attention to difficult-to-classify samples, the problem of class imbalance is solved, and the robustness of the model is improved.

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.

1. The name of the product of this design: Automatic phenotypic testing analyzer. 2. Purpose of this product with the design: This product with the design is used for accurate seed testing of various crop seeds and rapid detection and analysis of seed testing information. 3. The key point of the design of this product lies in its shape. 4. The picture or photo that best illustrates the design points: three-dimensional picture.

The present invention relates to the field of soybean seed testing technology, and in particular to a repair system and method for pod occlusion during seed testing, as well as a pod trait extraction method. The system includes a pod repair generator with an improved U-Net structure and a pod repair discriminator based on PatchGAN. The pod repair generator processes defective input pod images to obtain corresponding pod repair images. The present invention provides a multi-level residual convolution module and a self-attention module in the pod repair generator to perform multi-scale feature extraction and feature fusion to improve the pod image repair effect; the pod repair discriminator calculates the difference between the complete image corresponding to the input pod image and the corresponding pod repair image. The present invention repairs the pod image based on the repair system and completes the acquisition of trait information for each pod through a trait extraction method, thereby improving the statistical accuracy and efficiency of soybean pod phenotypic traits and avoiding the subjective errors caused by traditional manual statistics.

The present invention relates to the field of soybean seed testing technology, and more particularly to a soybean seed testing system and method based on an improved Faster-R-CNN. In this system, a pod recognition network accurately identifies pods and stems in their naturally mature state, while a pod image restoration network addresses the issue of mutual occlusion between pods. By optimizing the network structure, the efficiency and accuracy of phenotypic recognition in complex scenarios are significantly improved. The method utilizes a recognition loss function combined with Focal_Loss loss to reduce the loss contribution of easily classified samples, allowing the model to focus more on difficult-to-classify samples, thereby helping to address class imbalance and improving model robustness.

The present invention relates to the field of soybean seed testing technology, and in particular to a soybean seed testing system and method based on an improved Transformer-faster-RCNN. In this system, a pod recognition network based on a Swin-Transform structure accurately identifies pods and stems in their naturally mature state. A pod image restoration network with an adversarial neural network structure addresses the problem of mutual occlusion between pods. By optimizing the network structure, the efficiency and accuracy of phenotypic recognition in complex scenarios are significantly improved. The method uses a recognition loss function combined with Focal_Loss loss to reduce the loss contribution of easily classified samples, allowing the model to focus more on difficult-to-classify samples, thereby helping to address the problem of class imbalance and improving the robustness of the model.

The invention relates to the field of seed testing instruments, and discloses a seed testing instrument integrating screening, counting and weighing, a device body comprises a supporting cylinder and a U-shaped base, insertion holes are symmetrically formed in the base, rubber sleeves are embedded in the insertion holes, a hollow supporting frame is vertically fixed to the front side of the middle of the supporting cylinder, and the lower end of the supporting cylinder is connected with the base in an inserted mode through a U-shaped insertion frame; the inner wall of the supporting cylinder is sleeved with three sets of arc-shaped baffles capable of being spliced, the baffles are connected through spiral springs to form a dynamic screen cylinder, the inner surfaces of the baffles are covered with nylon friction layers and are made of transparent acrylic materials, a rotating cylinder is coaxially arranged in the supporting cylinder, and a screening blocking net is installed at the rear end of the rotating cylinder; the front end is rigidly connected with the rotating wheel in the center of the supporting frame through a connecting rod. The screening, counting and weighing device integrates screening, counting and weighing into a whole and adopts a mechanical mode, the situation that a traditional screening and counting mode is affected by the environment is avoided, and screening, counting and weighing of seeds are completed.

This invention relates to the field of soybean seed testing technology, and more particularly to a seed testing device for soybean pods and seeds. The device includes a pod feeding port, a pod shell discharge port, and a soybean discharge port located outside the main body of the device, and a pod feeding unit, a pod imaging unit, a soybean dehulling unit, and a soybean imaging unit located inside the device. This enables pod conveying, pod image acquisition, dehulling separation, and soybean image acquisition. The device also includes control buttons and a display for operation and data display. Through the above technical solution, a fully automated process is achieved from pod feeding, image acquisition, dehulling to soybean seed detection, reducing manual intervention, significantly shortening the seed testing time, and improving seed testing efficiency. It solves the problems of low efficiency and susceptibility to subjective factors in traditional seed testing methods, making it difficult to guarantee the accuracy and consistency of data.

The invention provides a method, a device and equipment for generating a test case. The method for generating the test case comprises the following steps: acquiring a to-be-tested code unit; variable information of variables in the code units is determined, wherein the variable information comprises variable names and variable reference values; wherein the variable reference value is derived from historical business data of the variable. Filling the variable information into a preset cue word template to obtain cue words used for being input into a large language model; the cue word contains task information used for indicating the large language model to output contents conforming to the business semantic features reflected by the variable reference value. And calling a large language model based on the cue word to obtain first seed test data, taking the variable reference value as a reference, of the variable. And constructing a seed test case based on the first seed test data. And performing iterative variation on the seed test case by adopting a genetic search algorithm to obtain a test case for testing the code unit.

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 utility model discloses constant temperature equipment for seed detection, which belongs to the technical field of seed detection and comprises a constant temperature water bath kettle, a constant temperature heating device, a constant temperature control device and a constant temperature control device, and is characterized in that the top end of the constant temperature water bath kettle is connected with a kettle cover; the rotating motor is fixedly connected to the top end of the pot cover, an output shaft of the rotating motor penetrates through the pot cover and is connected with a rotating rod, the periphery of the rotating rod is detachably connected with a plurality of limiting ring plates arranged side by side, and blocking ring plates are arranged on the peripheries of the limiting ring plates; a supporting net for supporting seeds and a supporting rod for improving the stability are fixedly connected between the limiting ring plate and the blocking ring plate; a plurality of vertical supporting plates which are arranged in an annular array mode are connected to the bottom end of the pot cover, a draught fan is installed on the side face of each vertical supporting plate, the top end of each draught fan is communicated with a ventilation hopper, and each ventilation hopper is communicated with an inverted-U-shaped ventilation pipe. According to the constant temperature equipment for seed detection, the efficiency of temperature uniformization can be improved, and filtering, cleaning and collecting can be carried out.