Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

155 results about "Seed sample" patented technology

Semen cassiae authenticity identification method based on hyperspectral imaging

The invention relates to the technical field of detection and identification, in particular to a semen cassiae authenticity identification method based on hyperspectral imaging, which comprises the following steps: S1, acquiring a hyperspectral image of a semen cassiae sample by using hyperspectral imaging equipment; s2, correcting the spectral drift of the hyperspectral image by using a spectral baseline correction method; s3, segmenting the corrected spectral image, distinguishing a target region and a background region of the semen cassiae sample, and extracting an effective spectral region of the semen cassiae sample in combination with a segmentation result; s4, separating the key spectral features related to the chemical components of the semen cassiae from the redundant features influenced by interference; s5, training an authenticity identification model based on an LGBM algorithm; and S6, inputting the key spectral features of the cassia seed sample to be detected into the authenticity identification model, and outputting an authenticity identification result. According to the invention, interference factors such as ambient light change, equipment deviation, surface impurities and the like are effectively eliminated, so that high-quality input data are provided for true and false identification.
Owner:泰州学院

Classification method for enhancing multi-label intentions of large language model based on remote supervision algorithm

PendingCN119025679AImprove labeling efficiencyImplement multi-label intent classification capabilitiesBiological modelsText database clustering/classificationData setAlgorithm
The invention provides a classification method for enhancing multi-label intentions of a large language model based on a remote supervision algorithm, and the method comprises the steps: obtaining user input in vehicle machine voice burying point data, carrying out the data cleaning of an input text, randomly selecting a part of seed samples, and carrying out the manual pre-labeling, and forming a seed labeling data set; based on the data set, a rule template is separated out from the data set through a remote supervision algorithm, other unlabeled samples are automatically labeled based on the template, the labeled data set is expanded, and a large language model fine tuning training set is obtained; sending the training set into a large language model fine tuning interface according to a certain format, and performing fine tuning by using LoRA; constructing a cue word project, and filling the current user input into the cue word reserved slot position to form a multi-label intention classification cue word; and inputting cue words into the fine-tuned large language model for reasoning, and outputting a corresponding multi-label intention list. According to the method, the problem of high difficulty in acquisition and labeling of fine-tuning training data of a large language model is solved, and a vehicle owner multi-intention identification function is realized.
Owner:DONGFENG MOTOR GRP

Cistanche deserticola seed screening method based on infrared spectrum

The invention discloses a cistanche seed screening method based on an infrared spectrum, and relates to the technical field of seed screening. The method comprises the steps of seed grading data determination, infrared spectrum detection and data processing and analysis. The seed grading data determination specifically comprises the steps of clarity determination, thousand seed weight determination, seed vigor determination and moisture content determination. According to the method, different grades of cistanche seeds are obviously related to infrared spectrum characteristic peaks, and the characteristic peaks have relatively high positive correlation with thousand seed weight, seed activity and moisture content, so that the absorbance of a wave band corresponding to a cistanche seed sample is an important index capable of reflecting the quality of the seeds; the absorbance is remarkably related to the thousand seed weight and the seed activity, and the effectiveness and accuracy of the infrared spectrum technology in evaluating the quality, the activity and the thousand seed weight of the seeds are proved.
Owner:XINJIANG UYGUR AUTONOMOUS REGION INST OF TRADITIONAL CHINESE MEDICINE & ETHNIC MEDICINE

Seed vigor detection device and method based on polarization spectrum technology

The invention discloses a seed vigor detection device based on a polarization spectrum technology, which comprises a large-stroke electric control mobile platform, a black paperboard, a seed sample, a halogen light source, a polarizer, a lens, a hyperspectral sorter, an analyzer and a computer, and all the parts are arranged in a camera obscura; the light emitted by the halogen light source is reflected by the polarizer and the seed sample, reaches the lens and is captured by the hyperspectral sorter; the invention also provides a detection method which comprises the following steps: firstly, collecting spectral data; carrying out image analysis; preprocessing the polarization spectrum data, performing competitive adaptive reweighting algorithm dimension reduction, and selecting a characteristic wavelength; finally, establishing a seed vigor detection model, fusing ideal modeling methods by adopting Blending ensemble learning, and carrying out hybrid modeling on the grain seeds; the polarization hyperspectral technology is introduced into the field of seed vigor detection, the seed vigor detection precision is improved, and rapid and nondestructive detection of the soybean seed vigor is achieved.
Owner:NANJING AGRICULTURAL UNIVERSITY

A near-infrared spectroscopy prediction method for soybean seed vitality based on machine learning and deep learning algorithms

The present invention relates to the field of agricultural planting technology, and in particular to a soybean seed vitality near infrared spectrum prediction method based on machine learning and deep learning algorithms, comprising the following steps: S1, bean selection; S2, preparing soybean seed samples with different vitality levels by artificial aging method; S3, obtaining near infrared spectra of soybean seed samples; S4, obtaining the true value of seed vitality index of soybean seed samples; S5, abnormal spectrum removal; S6, spectrum preprocessing; S7, characteristic band extraction; S8, model construction and evaluation of the model; S9, obtaining a prediction model for soybean seed vitality. The present invention can not only predict the germination rate of soybean seeds with light and dark seed coats, but also predict the germination index, normal seedling rate, germination potential and bud length, and can more comprehensively predict the vitality of soybean seeds.
Owner:YUNNAN UNIV

Seed vigor prediction model construction method based on spectral index and detection system

The invention discloses a seed vigor prediction model construction method based on spectral indexes and a detection system, and relates to a method and a system for rapidly and nondestructively detecting seed vigor by using a visible-near infrared spectrum technology. The problem that in the prior art, the requirement for accurate and quantitative evaluation of seed vigor in modern agriculture cannot be met is solved. The method comprises the following steps: firstly, acquiring spectral data and actual germination rate data of a seed sample, and carrying out abnormal value elimination and pretreatment on the spectral data; then extracting one-dimensional, two-dimensional and three-dimensional spectral indexes from the preprocessed spectral data, and screening out an optimal spectral index by using a correlation matrix method; and finally, by taking the optimal spectral index as input and the actual germination rate as output, establishing a seed activity prediction model based on the optimal spectral index. The prediction model is embedded in the system, and seed vigor prediction is achieved. The method is suitable for the fields of seed quality detection and grading, precise sowing, agricultural production and the like.
Owner:JILIN AGRICULTURAL UNIV

Self-learning method of credible dialogue model

The invention discloses a self-learning method of a credit review dialogue model, and the method comprises the steps: constructing a seed sample which is used for marking a reasoning process and dialogue data of a question corresponding to the reasoning process; inputting the dialogue data in the seed sample into a current credit examination dialogue model, outputting a prediction problem and a reasoning process corresponding to a prediction question by the credit examination dialogue model, and forming a series of sample data by the dialogue data, the reasoning process and the corresponding prediction question; evaluating the quality of currently generated sample data, screening out high-quality sample data as seed samples, and putting the seed samples into a seed sample database; and training the trust dialogue model based on the seed samples in the seed sample database. By iterating a small amount of dialogue data of questions marked with the reasoning process, progressive self-optimization of the credit review dialogue model is realized, and the logical reasoning ability of the credit review dialogue model is improved.
Owner:CHERY HUIYIN MOTOR FINANCE SERVICE CO LTD

MCU firmware grey box fuzzy test method and device based on simulation and strategy selection

The invention discloses an MCU firmware grey box fuzzy test method and device based on simulation and strategy selection, and the method comprises the following steps: 1) loading an MCU firmware binary file to a Unicorn simulator, and starting to run from a firmware entry point; 2) intercepting all MMIO accesses generated during firmware running, and judging whether a corresponding MMIO access model exists or not; (3) the energy-saving fuzzifier selects a variation strategy with the maximum probability of generating a new path to perform variation on the seeds, and inputs the variation strategy into the simulator; (4) the simulator obtains the variation seeds, the processing mode of the seeds is selected according to the access model, and therefore peripheral input needed by firmware is generated, and simulation operation is recovered; 5) recording and feeding back execution conditions of the variant seeds to the exploration-utilization model, and simultaneously determining whether the variant seeds are discarded or added into the seed sample set; and 6) calculating the probabilities of different variation modes by the exploration-utilization model according to feedback information of a seed operation result for strategy selection in the step 3). According to the method, MCU firmware peripheral modeling and an energy-saving fuzzifier are combined, and vulnerability mining is carried out on full-simulation firmware by using input overhead judgment and abrupt change selection strategies. Through the input overhead judgment of the simulator and the exploration-utilization model of the fuzzer, the input overhead of peripheral modeling is reduced, the generation of redundant seeds is reduced, and the code coverage rate of fuzz testing is ensured.
Owner:ZHEJIANG UNIV OF TECH

Detection device for seeds and plant tissues

The utility model discloses a detection device for seeds and plant tissues. The detection device comprises a detection box and a seed sample feeder matched with the detection box, the detection box comprises a shell, a weighing module, a loading transparent plate, a camera module and a controller; an opening is formed in the top of the shell, the weighing module is fixed in the shell, the loading transparent plate is connected with the weighing module, the loading transparent plate is located at the opening in the top of the shell, the camera shooting module is located around the loading transparent plate, the camera shooting direction faces the loading transparent plate, and the camera shooting module and the weighing module are connected with the controller; the seed sample sending device comprises a loading plate, a sample sending plate and a partition plate, the loading plate comprises a plurality of seed hole sites, the seed hole sites are roughly the same as detected seeds in particle size and shape, the sample sending plate comprises a plurality of seed channels, and the seed hole sites correspond to the seed channels in position after the loading plate and the sample sending plate are stacked through a magnetic structure. A partition plate is inserted between the loading plate and the sample feeding plate. The seed metering device has the beneficial effects that the seed taking and metering processes are reduced, information such as weight, grain length, grain width and form can be obtained at one time, and the working efficiency is improved.
Owner:ZHONGKE HEFEI INTELLIGENT BREEDING ACCELERATOR INNOVATION RES INST CO LTD

Tripod type sample splitter

The utility model discloses a tripod type sample splitter which comprises three foot supports, the tops of the three foot supports are connected with the same outer fixing ring, the top of the outer fixing ring is sequentially communicated with a feeding hopper and a feeding hopper, a sample splitting assembly is arranged in the feeding hopper, and the sample splitting assembly is arranged in the feeding hopper. The sample separation assembly comprises an inner fixing ring, a lining, a first material guide groove and a second material guide groove, the outer ring of the inner fixing ring is fixed with the inner ring of the outer fixing ring, an inclined plane is arranged at the inner bottom of the inner fixing ring, the lining is arranged in the inner fixing ring, the top of the lining is conical, and the first material guide groove is communicated with the second material guide groove. The first material guiding grooves are formed between the lining and the inner fixing ring, and the multiple first material guiding grooves are distributed in an annular array mode relative to the lining. Through the arrangement, two parts of seed samples separated by the sample splitter are uniform as far as possible, so that the experimental requirements of sample splitting of the seed samples are met, and the practicability of the device is enhanced.
Owner:HANGZHOU FANGMAO PRECISION SHEET METAL CO LTD

Soybean grain single-band image classification method and system based on deep learning

The invention discloses a soybean grain single-band image classification method and system based on deep learning, and belongs to the technical field of hyperspectral application. The problem that in the hyperspectral data screening process, due to the fact that a hyperspectral image contains a large number of wave bands, once image noise is large or missing values exist, the classification accuracy class is low is solved. The method comprises the following steps: acquiring a soybean grain image and spectral data; carrying out black and white correction on the collected hyperspectral image to obtain a processed soybean grain image; selecting an optimal wave band according to SPA and KNN algorithms; carrying out image enhancement and threshold segmentation on the original data set and the new data set, and separating a soybean seed sample from a background by adopting a morphological method; the method comprises the following steps: training through an SENet-ResNet34-DCN model, and extracting a plurality of features of a test sample; and outputting a classification result. The method is suitable for soybean seed authenticity identification and quality analysis scenes.
Owner:CHANGCHUN UNIV OF SCI & TECH

Small seed precision sowing monitoring method and system

The invention relates to the technical field of agricultural machinery intellectualization, in particular to a small seed precision sowing monitoring method and system. The method comprises the following steps: setting a time window, and acquiring first signal data passing through a surface laser sensor and second signal data passing through an infrared sensor based on the time window; respectively correcting the first signal data and the second signal data to obtain first optimized data and second optimized data; performing matching degree calculation according to a preset seed sample database by utilizing the first optimization data and the second optimization data to obtain a fusion matching degree score; and calculating the actual pulse frequency of the time window according to the fusion matching degree score, and determining miss-seeding and reseeding by using the actual pulse frequency. According to the invention, the problem that reseeding and miss-seeding are difficult to monitor due to the fact that small seeds are difficult to identify during mechanical seeding in the prior art is solved, and the identification capability of the small seeds is greatly improved.
Owner:CHONGQING ACAD OF AGRI SCI

Rice seed cultivation device and use method thereof

The invention discloses a rice seed cultivation device and a use method thereof, relates to the technical field of seed cultivation devices, and provides the following scheme that the rice seed cultivation device comprises a machine body and further comprises a placement plate, a seed collection device and a seed collection device, the extracting mechanism is arranged in the machine body and is used for extracting the placing plate; the lifting mechanism is arranged in the machine body and is used for carrying out lifting adjustment on the placing plate; the soil loosening mechanism is arranged in the machine body. According to the device, rapid soil loosening, seedling pulling and spraying treatment can be carried out on a rice seed sample in cultivation, seed placement, soil loosening, seedling spraying and seedling pulling operation are completed through a mechanical structure and motor driving, the labor intensity of workers is reduced, especially, the stooping operation frequency of workers is reduced, the operation comfort is improved, and the working efficiency is improved. The soil loosening mechanism can not only break soil hardening but also reduce pulling damage to seedling root systems caused by traditional rigid soil loosening by achieving compound motion of reciprocating translation and rotary soil loosening.
Owner:HUBEI JIURUIKANG AGRI TECH CO LTD

Method for constructing large legal affair model, method for analyzing legal affair information, and computer device

The invention discloses a legal affair large model construction method, a legal affair information analysis method and a computer device. The legal affair large model construction method comprises the following steps: constructing a legal domain knowledge graph comprising a multi-level organization knowledge architecture, obtaining a preset amount of manually labeled seed samples, extracting structural features of the seed samples, and generating a target template; according to the legal domain knowledge graph pair, filling the target template, and generating diversified training samples; a multi-level sample generation strategy is configured according to training samples and requirements, a large language model is trained in a layered mode according to the strategy, and the trained large language model serves as a legal affair large model. According to the method, diversified high-quality legal training samples are automatically generated through a legal domain knowledge graph and a small number of seed samples, dependence on a large amount of annotation data and computing power resources is effectively reduced, model training is conducted through a multi-level sample generation strategy, it is ensured that complex legal knowledge and reasoning can be gradually mastered, and the method is high in practicability. And the utilization rate of data and the accuracy of model training are effectively improved.
Owner:BEIJING ELECTRONIC DIGITAL INTELLIGENCE TECHNOLOGY CO LTD

Grain grain storage duration prediction method and system

The invention belongs to the field of food grain storage quality detection, and particularly relates to a food grain storage duration prediction method and system. The method comprises the following steps: taking biophoton radiation data of to-be-predicted grain seeds as storage duration information of each iteration, and obtaining a prediction error, a state updating equation and a state vector corresponding to Kalman gain and a time updating equation corresponding to the prediction error through a Kalman filtering algorithm of a Kalman model of the storage duration information of the grain seeds; obtaining a state vector of the current iteration; updating the current number of iterations, then obtaining a state vector of the current iteration until a prediction error meets an iteration stop condition, and obtaining a predicted grain grain storage duration according to the state vector of the current iteration and the Kalman filtering state space model containing the state vector and storage duration information; the Kalman model identifies the coefficient of the Kalman filtering state space model by using the known storage duration information of the grain seed sample and the biophoton radiation data as the state vector to determine the Kalman filtering state space model.
Owner:HENAN UNIVERSITY OF TECHNOLOGY

High performance liquid chromatography characteristic chromatogram of Chinese hawthorn seed and determination method and application thereof

The invention belongs to the technical field of pharmaceutical analysis. The invention provides a method for determining the high performance liquid chromatography characteristic chromatogram of Chinese hawthorn seed, which comprises the following steps: crushing and sieving a Chinese hawthorn seed sample, adding an ethanol solution for extraction, then carrying out post-treatment, evaporating the supernatant to dryness, dissolving the residue with the ethanol solution, and filtering to obtain a Chinese hawthorn seed sample solution to be determined; dissolving vanillin with methanol to obtain a reference substance solution to be detected; and determining the to-be-detected solution of the hawthorn seed sample and the to-be-detected reference substance solution by adopting high performance liquid chromatography, and obtaining the high performance liquid chromatography characteristic spectrum of the hawthorn seeds according to the chromatogram. According to methodology verification, the method for measuring the hawthorn seed high performance liquid chromatography characteristic chromatogram is good in durability, high in specificity, good in precision, repeatability and stability, simple and convenient to operate and low in cost.
Owner:CHENGDE FOOD & DRUG INSPECTION & TESTING CENT

Crop seed sample crusher

The utility model relates to the field of crushers, and discloses a crop seed sample crusher which comprises a crushing shell, a bottom shell arranged at the bottom end of the crushing shell, a motor arranged in the bottom shell, an output shaft arranged at the output end of the motor, a crushing cavity and a powder cavity respectively arranged at the upper part and the lower part of the crushing shell, and a filter screen movably connected between the crushing cavity and the powder cavity, the output shaft penetrates through the powder cavity and penetrates into the crushing cavity, the part, located in the crushing cavity, of the output shaft is connected with a crushing roller, the bottom face of the filter screen is provided with a first vibration part, the output shaft is provided with a second vibration part, the output shaft in the powder cavity is connected with a scraper, a baffle is arranged in the powder cavity, and the movement track of the scraper intersects with the baffle. The powder filtering device has the advantages that the filter screen slides up and down in a reciprocating mode under the combined action of the first elastic piece, vibration of the filter screen is achieved, meanwhile, the output shaft drives the scraper to rotate, powder is brought out under the combined action of the baffle and the second elastic piece, and the powder filtering efficiency and the discharging efficiency are improved.
Owner:XIANGYANG XIANGZHOU GOLDEN SUN SEED TECH CO LTD

Layered sampling mechanism of grain seed sampler

The utility model provides a layered sampling mechanism of a grain seed sampler, and belongs to the technical field of grain seed sampling. Comprising a sampling assembly, the sampling assembly is arranged in a supporting column, the sampling assembly comprises a baffle fixed in the supporting column, a sliding plate is arranged in the baffle, a supporting plate is arranged in the supporting column, a sliding groove is formed in the inner wall of the supporting plate, and the sliding groove is communicated with the sliding plate; a fixing rod is arranged at the top of the supporting plate, a guide groove is formed in the fixing rod, the supporting column accommodates the sampling assembly and is inserted into a grain pile and the sampling assembly through a bottom drill bit, the baffle is matched with the sliding plate, and under the action of the contraction assembly, the sampling assembly can stretch out of the sliding plate. Sliding is achieved through the guide groove of the fixing rod and the sliding groove of the supporting plate, resetting is assisted through the elastic piece, and therefore opening and closing of the material receiving open groove in the supporting column are controlled, and the effects of sampling in a layered mode and preventing grain leakage are achieved.
Owner:HENAN BANGBANG SEED IND CO LTD

Method for extracting RNA (Ribonucleic Acid) of corn seeds

The invention discloses a corn seed RNA (Ribonucleic Acid) extraction method which comprises the following steps: adding a corn seed sample ground by liquid nitrogen into a sample tube, adding grinding beads and an extraction buffer solution preheated at 60-65 DEG C, and uniformly mixing by vortex; the extraction buffer solution is prepared from 90 to 100 mM of Tris-HCl, 20 to 25 mM of EDTA (Ethylene Diamine Tetraacetic Acid), 1 to 2 percent of CTAB (Cetyltrimethyl Ammonium Bromide), 0.5 to 1 M of NaCl and 1 to 2 percent of beta-mercaptoethanol; adding a phenol-chloroform mixed solution, vigorously shaking, centrifuging, taking an upper-layer solution into a centrifugal tube, adding isometric isopropanol, sufficiently and uniformly mixing, adding a magnetic bead mixed solution, performing magnetic bead purification, and extracting to obtain the corn seed RNA. Reagent consumables used in the method are simple and easy to obtain, and high-quality and high-purity corn seed RNA can be obtained in a short time. Meanwhile, the method utilizes magnetic bead purification and is combined with related equipment, so that the extraction flux can be greatly improved.
Owner:HANGZHOU LC BIOTECH

Small sample black box model fairness test method based on flow model domain adaptation

The invention relates to the technical field of artificial intelligence and software engineering, and discloses a small sample individual fairness testing method based on a domain adaptive flow model. Aiming at the problems of difficulty in obtaining target model training set data, low discrimination sample generation efficiency, insufficient sensitive attribute decoupling and the like in the existing black box fairness test, the invention provides the following technical scheme: firstly, constructing a gating residual domain adaptive flow model, and performing dynamic fusion on a frozen source domain projection matrix and a trainable low-rank adapter to obtain an adaptive flow model; domain adaptation of the flow model is realized under the condition of not depending on a target model training set; secondly, a two-stage anti-fact generation strategy is adopted, a seed sample set is constructed by utilizing a dynamic radius attenuation mechanism, and discriminated samples are efficiently expanded in combination with triple disturbance; finally, gradient orthogonal constraint is applied to the hidden space of the flow model, and decoupling control over the sensitive attributes and the semantic features is achieved. The black box fairness testing method can be used for black box fairness testing of classification models such as tables, texts and images, and has good practical significance and actual effect.
Owner:BEIJING INST OF TECH

Cotton seed quality online detection method, device, system and storage medium

The application provides a cotton seed quality online detection method, device, system and storage medium, comprising: in the case that the quality category of the to-be-detected cotton seed is not the first quality category, acquiring an air-coupled ultrasonic signal for detecting the quality of the to-be-detected cotton seed; generating a target image based on the air-coupled ultrasonic signal; inputting the target image into a trained cotton seed quality detection model to output a target quality category of the to-be-detected cotton seed; the trained cotton seed quality detection model is obtained after training according to a target image sample; the target image sample is obtained by acquiring a target image of a cotton seed sample of a second quality category and a target image of a cotton seed sample with an intact epidermis; the epidermis damage degree of the cotton seed of the first quality category is greater than that of the cotton seed of the second quality category. The application can effectively detect slightly damaged cotton seeds, effectively screen intact cotton seeds without damage, and greatly improve the efficiency of cotton seed online sorting.
Owner:INTELLIGENT EQUIPMENT RESEARCH CENTER BEIJING ACADEMY OF AGRICULTURE AND FORESTRY SCIENCES

Automatic fry measuring system for enhancement and release

The invention, which relates to the technical field of fishery proliferation, discloses an automatic fry measurement system for proliferation and releasing, comprising a weighing module for collecting net weight data of fry samples, an image acquisition module for acquiring RGB-D images of the fry samples at different angles, and a basic data module for acquiring the sampling time and place of the fry samples. The data collection module sends the net weight data, the sampling time and the sampling place to the record report generation module, and sends the image data to the data processing module; the data processing module obtains type data and body length data of the fry samples through the RGB-D images and sends the data to the record report generation module; and the record report generation module generates an enhancement release record report according to the collected data. By means of the system, sampling detection of the weight, the body length, the type and the sample number of the enhancement and release offspring seed samples and automatic generation of an enhancement and release record report are achieved, the current enhancement and release situation is accurately recorded, and a basis is provided for enhancement and release management and control.
Owner:FRESHWATER FISHERIES RES CENT OF CHINESE ACAD OF FISHERY SCI

Molecular marker for rapidly detecting high-purity fresh soybean germplasm

PendingCN122279097AVerify accurate identification capabilitiesEnsure purity testing errorBiotechnologyGermplasm
This invention discloses a molecular marker for rapid detection of highly homozygous fresh soybean germplasm. By carefully selecting specific editing sites, and then designing corresponding LAMP amplification primer sets and OSD probe sets based on these editing sites, the LAMP amplification primer sets and OSD probe sets designed in this invention can detect fresh soybean samples from different sources, verifying their specific recognition ability for autonomously edited improved germplasm. Wild-type OSD probes can also be used to detect seed samples from autonomous germplasm resources, verifying their accurate recognition ability for mixed wild-type seeds, ensuring that the seed purity detection error is ≤1%, meeting the requirements for production and planting.
Owner:SHUNFENG BIOTECHNOLOGY (HAINAN) CO LTD

Learning operating method based on federated distillation, learning operating server, and learning operating terminal

According to the present disclosure, disclosed are a learning operating method based on a federated distillation, a learning operating server, and a learning operating terminal which calculate a local average logit by collecting data samples by the terminal, transmit the local average logit and seed samples to an uplink of a server, perform distillation of a global model based on the seed sample and the local average logit by the server to solve the problems of the privacy and communication overhead generated in the distributed network.
Owner:IND ACADEMIC COOP FOUND YONSEI UNIV

Automated contamination-free seed sampler and methods of sampling, testing and bulking seeds

An automated seed sampler system for removing tissue from seeds includes an orientation system configured to orient seeds in a desired orientation, a sampling station configured to remove tissue from each of the oriented seeds, a sample collection subsystem configured to receive the tissue removed from each of the oriented seeds, and a seed collection subsystem configured to receive each of the seeds from which the tissue is removed. The sample collection subsystem and the seed collection subsystem are configured to facilitate a one-to-one correspondence between the seeds received at the seed collection subsystem and the tissue removed from the seeds and received at the sample collection subsystem.
Owner:MONSANTO TECHNOLOGY LLC

Sample separating and sampling device for crop seed detection

The invention relates to the technical field of seed sample splitting, in particular to a sample splitting and sampling device for crop seed detection, which comprises a sample splitter shell, a base, a top feeding unit, a plurality of collecting boxes and a plurality of shunting assemblies, each shunting assembly comprises two movable diffusion plates, an inclined conversion unit, a channel body, a channel sealing plate and a pressure sensor, different pressure threshold values can be set for a pressure sensor of each flow dividing assembly, after the threshold values reach a preset value, a gap between the two movable diffusion plates is closed through an inclined conversion unit, so that corn seeds cannot continue to fall, meanwhile, a channel sealing plate is rotated, corn crop seeds accurately collected on the pressure sensors fall, and the corn seeds are separated from the channel sealing plate. Storing and collecting by a collecting box; the seeds are respectively used for detecting the moisture, germination rate, cleanliness and authenticity of the seeds and storing backup samples, so that the channel bodies can be closed after the collection quantity meets the detection requirement, and the accurate collection of the corn seeds in each channel body is realized.
Owner:昭通市种子管理站

A method for identifying the origin of coix seed, a terminal device, and a storage medium

The application discloses a method for identifying the producing area of coix seed, a terminal device and a storage medium, and comprises the following steps: S1: collecting a plurality of coix seed samples of the producing area to be identified, and obtaining a three-dimensional data array of the excitation emission matrix (EEM) fluorescence spectrum of the coix seed; S2: converting the three-dimensional data array of the EEM fluorescence spectrum into a two-dimensional data array of the sample set; S3: obtaining a training set and a test set by using the two-dimensional data array of the sample set; S4: training a model constructed by using an improved random forest algorithm by using the training set, and obtaining a producing area identification model; and S5: evaluating the performance of the model by using the test set and a prediction set. The method for identifying the coix seed from different producing areas based on the fluorescence spectrum technology realizes the classification of the coix seed from different producing areas by using the model constructed by combining the improved random forest algorithm and the fluorescence spectrum.
Owner:HUNAN UNIV OF TECH

Amorpha fruticosa aerial seeding seed pelleting treatment method and equipment for improving germination rate

PendingCN121153410AAfforestationSeed immunisationAmorpha fruticosaAdhesive
The invention discloses an amorpha fruticosa aerial seeding seed pelleting treatment method and equipment for increasing the germination rate, and particularly relates to the field of forest tree seed treatment.The amorpha fruticosa aerial seeding seed pelleting treatment method.The amorpha fruticosa aerial seeding seed pelleting treatment method comprises the steps that S1, amorpha fruticosa seeds are cleaned, disinfected and soaked, washed with clear water after soaking is completed, and then naturally aired; s2, collecting a fresh koelreuteria paniculata seed sample to prepare an endophyte solution, preparing an adhesive, and uniformly stirring the adhesive to fully dissolve; s3, adding the amorpha fruticosa seeds and an adhesive into a stirrer, uniformly stirring, then adding the endophyte liquid, continuously stirring, then selecting medical stone and bentonite as carriers, and quickly and uniformly wrapping the seeds to obtain a mixture; and step S4, mixing the mixture, and then carrying out granulation treatment. Through the synergistic effect of multi-step pretreatment and the pelleting process, the germination rate and the survival rate of the amorpha fruticosa seeds are remarkably improved, the physical characteristics of the seeds are optimized through pelleting treatment, and the aerial seeding adaptability is greatly improved.
Owner:河南省林业资源监测院 +1

Computer implemented quantification of seed moisture content and / or thousand kernel weight based on color images of a seed sample

The invention relates to an easy-to-handle tool for non-invasive indirect measurement of seed parameter values based on acquisition and computer implemented analysis of an image of a small seed sample collected in the field. The solution can be implemented as portable device or as system comprising one or more portable image acquisition tools connected to a remote computer system for image analysis.
Owner:BAYER AG

Broccoli disease-resistant and disease-preventing pollination cultivation method

The invention relates to the field of broccoli cultivation, in particular to a broccoli disease-resistant disease-prevention pollination cultivation method which comprises the following steps: acquiring a seed sample, exposing the seed sample to the sun, soaking the seed sample in warm water, sterilizing the soaked seed sample, and mixing imidacloprid wettable powder with the seed sample to obtain pretreated seeds; sandy loam with good drainage is selected, the PH value of the sandy loam is adjusted and controlled within a standard range, a greenhouse of the sandy loam is built, an insect-proof net and an EVA film are selected and covered, and an experimental field where the pretreated seeds are planted is obtained; the handheld electric vibrator is used for pollination, operation is easy and convenient, and efficiency is high. Compared with natural pollination, the method is not limited by climate and pollination insects, can ensure sufficient scattering and uniform spreading of pollen, improves the pollination success rate, reduces the rate of deformed flower balls, increases the fruiting amount and commodity of broccoli, and brings higher economic benefits to farmer households.
Owner:ZHENJIANG XINYUANDA GARDENING SCI & TECH CO LTD