35results about How to "Representative" patented technology

The invention belongs to the technical field of water quality remote sensing monitoring, and particularly relates to a sky-ground remote sensing integrated lake and reservoir water quality parameter quantitative inversion method. Qualitative inversion is carried out on water quality parameters through medium-high resolution satellite remote sensing images, and ground sampling points are reasonably arranged. And carrying out ground and air collaborative operation, including on-site water body sampling and unmanned aerial vehicle flight, so as to ensure the consistency of sampled water quality parameters and unmanned aerial vehicle image spectral characteristics. The sampling point water body sample is sent to a laboratory to be tested, and measured data are obtained. An unmanned aerial vehicle image is subjected to preprocessing including splicing and radiation correction, and a reflectivity image map is obtained. Water vector data are extracted by using an unmanned aerial vehicle image, a remote sensing quantitative inversion model of water quality parameters is established, and the model is analyzed and optimized through an optimal wave band combination. And in combination with the unmanned aerial vehicle image, the inversion model and the water body vector data, obtaining a water quality parameter quantitative inversion result and spatial distribution characteristics in the lake and reservoir range. The method can improve ground sampling rationality and time coordination of lake and reservoir water quality monitoring, and supports long-term high-precision dynamic monitoring.

The invention discloses an automatic driving simulation test scene generalization evaluation method and system, and belongs to the technical field of intelligent network connection automobiles. Comprising the steps of obtaining real vehicle operation data and performing preprocessing to obtain scene generalization basic data; fitting the scene generalization basic data through a Gaussian mixture model to obtain a joint probability density function among scene parameters; on the basis of a joint probability density function between scene parameters, generalization scene parameter sampling is carried out through a Hamilton Monte Carlo method, and a generalization scene parameter set is generated; generalization scene evaluation is performed based on the scene generalization basic data and the generalization scene parameter set, and the coverage degree of the generalization scene parameter set is acquired in combination with the complexity of the generalization scene; initialized parameters of the Gaussian mixture model are generated through a K-means + + algorithm. The convergence speed and accuracy of generalization scene construction can be improved, and effective evaluation of generalization scene coverage is realized. The problem that comprehensive and effective evaluation of the generalization scene cannot be realized in the prior art is solved.

The application discloses a hyperspectral image target intelligent detection method, and belongs to the field of remote sensing image processing. The method comprises the following steps: selecting background training samples based on density clustering and spectral angle mapping; generating sufficient target training samples by using a random spectral band zero masking method; inputting the background training samples, a prior target and the target training samples into upper, middle and lower branches of a spectral aggregation and separation network respectively for training, and using a triple soft loss function to promote the network training to separate the background samples, the prior target and the target samples; inputting a pixel to be detected and a prior target into the upper and lower branches and the middle branch of the trained network for target detection, and outputting the network to form a final detection result. By using the application, the difference and similarity of the background and target pixels in the hyperspectral image and a prior target can be simultaneously discriminated, so that the detection result of highlighting the target and suppressing the background can be obtained.

The application discloses a life evaluation method and device of a speed reducer and a storage medium, and belongs to the technical field of photovoltaics. The method comprises the following steps: calculating an impact torque generated by the impact of wind on the speed reducer according to wind parameters; converting the impact torque into an output torque of a motor according to the transmission ratio of the speed reducer; controlling the motor to work based on the output torque to simulate the impact generated by the wind on the speed reducer; and evaluating the life of the speed reducer according to the simulation result. According to the application, the impact torque generated by the impact of wind on the speed reducer is calculated through wind parameters, so that the influence of wind on the speed reducer is quantified, the impact torque is converted into the output torque of the motor by using the transmission ratio of the speed reducer, the motor can run at a torque matched with the actual wind condition, the wind-induced impact generated by the wind acting on the speed reducer is simulated, the actual working scene can be reproduced in an experimental environment, the problem that long-time waiting is needed in outdoor environment testing is reduced, and the evaluation efficiency of the life of the speed reducer is improved.

This invention discloses a sewage pipeline water quality and quantity monitoring device, including a pipeline sewage detection mechanism. The sewage detection mechanism includes a sewage transport pipeline, the interior of which is filled with dynamically flowing sewage. An online sewage detection mechanism is fixedly installed on the top surface of the sewage transport pipeline. A plugging device is used to both reset the continuous flow device and remove blockages from the sewage sampling component, preventing it from being blocked by foreign objects. A position monitoring mechanism monitors the position of the sewage sampling component, allowing the online sewage detection mechanism to limit the upward and downward displacement limits of the sewage sampling component based on preset maximum and minimum values. This ensures that the bottom of the sewage sampling component does not separate from the dynamically flowing sewage, guaranteeing uninterrupted monitoring of the dynamically flowing sewage and improving the practicality of the sewage pipeline water quality and quantity monitoring device.

The invention discloses a sample preparation pretreatment device for chloroiridic acid detection, and relates to the technical field of sewage detection. The sample preparation pretreatment device for chloroiridic acid detection comprises a sample water bucket, the outer wall of the sample water bucket is fixedly connected with a fixed support, and the interior of the sample water bucket is movably connected with a sampling mechanism. According to the sample preparation pretreatment device for chloroiridic acid detection, a driving motor drives a rotating frame to rotate through a conveying belt, sewage in a sample bucket is driven to rotate, solid substances in water move around under the centrifugal effect, and a gas bin enables a notch in the top of a sampling pipe to float at a certain position of the liquid level; according to the sewage sampling device, water at the top of the liquid level continuously flows into the sampling pipe through the notch, and meanwhile, the blocking filter plate can block solids in sewage from entering the sampling pipe, so that the accurate volume of water flowing out of the bottom of the sampling pipe can be measured when the water is detected, and the detection accuracy is improved.

The invention relates to the technical field of graphite negative electrode materials of lithium ion batteries, and discloses a method for evaluating the uniformity of a coating layer on the surface of coated graphite, which comprises the following steps: S1, respectively carrying out Raman surface scanning detection on a graphite base material and the coated graphite by using a laser Raman spectrometer to obtain ID / IG values of a plurality of point positions in a scanning range; s2, arranging ID / IG values of the graphite base material in a descending order, and removing front 10%-20% of point locations to obtain optimized data I; selecting the maximum ID / IG value in the optimized data I as a critical point M; s3, arranging ID / IG values of the coated graphite in a descending order, and removing front 10%-20% of point positions and rear 10%-20% of point positions to obtain optimized data II; and S4, calculating the coating rate K of the coated graphite: K = A / B. The accuracy of calculating the coating rate is high.

This utility model discloses an automatic oil sample collection device for exploration wells, belonging to the field of oil well sampling. It includes a fixed frame, with a winding roller rotatably connected to the top of the frame. A cable is wound around the outer wall of the winding roller, and a sampling cylinder is fixedly connected to the end of the cable. An oil suction port is located at the bottom center of the sampling cylinder. A hydraulic cylinder is fixedly connected to the upper part of the sampling cylinder, and a piston disc is fixedly connected to the output end of the hydraulic cylinder. In this design, as the piston disc moves upward, the oil sample enters the sampling cylinder under the action of a pressure difference. After sampling, a sealing plate closes, sealing the oil sample inside the sampling cylinder. This effectively prevents oil sample leakage or external contamination, especially avoiding sample leakage caused by vibration when the winding roller moves the sampling cylinder upward. This ensures the representativeness and purity of the collected oil sample, providing a reliable sample basis for subsequent oil sample testing and guaranteeing the accuracy of the test results.

The invention relates to the technical field of coal powder sampling. The invention provides a coal powder sampling system, comprising: an intelligent trolley, an action mechanism, a sampling mechanism and a sample screening device; the action mechanism is arranged on the top of the intelligent trolley, the sampling mechanism is fixedly installed on the action mechanism, the sample screening device is fixedly installed in front of the action mechanism on the intelligent trolley, the action mechanism comprises a lifting mechanism and a sliding mechanism package, the lifting mechanism is responsible for height adjustment of the sampling mechanism, and the sliding mechanism is responsible for sampling depth adjustment of the sampling mechanism; the invention can be moved to different positions for sampling, sampling can be achieved in sampling pipe openings at different heights through the action mechanism, rapid classification of samples according to different sample particle sizes can be achieved through the sample screening device, constant speed sampling can be achieved through adjustment of the sampling mechanism, so that the obtained samples are more representative.

The utility model discloses a novel ton bag, which comprises a bag body for containing materials, a hoisting fixing structure sewn on the outside of the bag body for hoisting and fixing the bag body, a top connecting component installed on the top of the bag body, and a bottom connecting component installed on the bottom of the bag body for connecting the inside and outside of the bag body.

This utility model discloses a wastewater collection monitoring device, including a wastewater tank. An inlet pipe is located on the upper side surface of the wastewater tank, and a drain pipe is located on the lower side surface. A vortex-shaped groove is formed on the upper surface of the wastewater tank, connecting the inside and outside of the tank. An I-shaped slider is slidably mounted within the groove. A geared motor is installed at the center of the lower surface of the wastewater tank. The output shaft of the geared motor extends through the upper surface of the wastewater tank and connects to a rotating column. The side surface of the rotating column is connected to the slider via multiple telescopic rods. At least one ultrasonic depth gauge is mounted on the lower surface of the slider. The geared motor drives the rotating column, which in turn drives the slider equipped with the ultrasonic depth gauge via the multiple telescopic rods, moving it along a pre-designed vortex-shaped groove trajectory. This trajectory covers most of the area from the edge to the center of the tank, allowing a single sensor to complete a large-scale scanning measurement of the wastewater tank's cross-section.

The utility model discloses a simple device for water quality detection, and relates to the technical field of water quality detection. Comprising a suitcase main body, the suitcase main body is provided with a mounting mechanism for water quality detection equipment, and the mounting mechanism comprises the following steps: shaking a test tube to enable a water source and pH test paper to be in full contact and react more fully, so that inaccurate detection results caused by local concentration difference are avoided, and the detection results can better represent the pH value of a whole water sample; the detection accuracy and reliability are improved, shaking promotes material exchange between a water sample and the test paper, the reaction reaches a balanced state more quickly, the test paper can present a stable color more quickly, so that the detection time is shortened, the detection efficiency is improved, the test tube is shaken without additional complex equipment or operation steps, and the detection accuracy and reliability are improved. Therefore, full contact between a water source and the test paper and mixing of the water source can be realized, and a user can conveniently and quickly detect water quality in different scenes.

The utility model provides coal-fired power plant coal feeding equipment and a raw coal sampling device, the coal-fired power plant coal feeding equipment comprises a coal feeder, a raw coal bunker, a coal discharging pipe, a sampling pipe seat and a sampler, the raw coal bunker is communicated with the coal feeder through the coal discharging pipe; the sampling pipe seat is provided with a sampling pipe cavity, the head end of the sampling pipe seat is arranged on the side wall of the coal discharging pipe, and the head end of the sampling pipe cavity is communicated with the coal discharging pipe; the sampling tube seat is provided with a compressed air inlet and a first valve, the compressed air inlet and the first valve are sequentially distributed in the direction from the head end of the sampling tube seat to the tail end of the sampling tube seat, and the compressed air inlet is directly or indirectly communicated with the sampling tube cavity; the sampler is detachably matched with the sampling pipe seat, and when the first valve is opened, the sampler can extend into the sampling pipe cavity through the tail end of the sampling pipe seat and extend into the coal discharging pipe, so that the technical problems that raw coal is easy to splash and the sampling pipe is easy to block in the raw coal sampling process are solved.

The present application relates to the technical field of data processing, and especially to a multi-dimensional reconciliation method and system based on a group meal platform, which comprises the following steps: determining the state of a sub-node according to a steady-state metric value and a correlation index, and determining a reference data selection method according to the state of the sub-node; in the single-node direct selection, the sub-node corresponding to the maximum comprehensive evaluation value is selected as the reference data; in the multi-node compensation selection, a compensation method is determined according to a steady-state mutual correlation degree and a steady-state balance coefficient to select the reference data; and a reconciliation sub-node selection method is determined according to a reference comparison coefficient and a cross-correlation coefficient of the sub-node corresponding to the to-be-reconciled data and the reference data; and the present application can improve the reconciliation processing efficiency.

The application relates to a fine path loss prediction method of a bimodal network correction, and belongs to the technical field of wireless communication.The method is used for solving the problem that an existing method cannot balance the complexity and accuracy of path loss prediction, the method gives a statistical prediction value by using a path loss empirical model, completes common characterization of path loss, then a bimodal network is used to learn specific propagation characteristics of a communication environment from two modes of vision and features, a correction value of the path loss empirical model is obtained, and specific description of path loss at different positions is completed.The application is applied to the field of wireless communication, combines artificial intelligence and statistical methods, and can realize fine modeling of path loss.

This invention discloses a method, system, and storage medium for capacity compensation of lithium-ion battery cells. The method includes: constant current charging of the lithium-ion battery cell under test to a charging cutoff voltage, then switching to constant voltage charging until the charging current drops to the cutoff current; constant current discharge of the fully charged cell to a first cutoff voltage using a first discharge current, recording the released capacity as the main discharge capacity; after the main discharge, allowing the cell to rest for a preset time; continuing constant current discharge of the rested cell to a second cutoff voltage using a second discharge current, recording the released capacity as the reference discharge capacity; and calculating the compensated capacity using a capacity compensation formula based on the main discharge capacity, the reference discharge capacity, and a pre-determined reference discharge capacity benchmark value. This invention can eliminate the influence of polarization differences caused by ambient temperature fluctuations on the capacity test results during capacity testing, improving the accuracy of capacity testing.

This utility model discloses a material conveyor for smelting, comprising a sampling tube at the sampling port, a sealing head inside the sampling tube, and a drive rod at the lower end of the sealing head. The lower end of the drive rod passes through the bottom wall of the sampling tube and extends outward, controlling the drive rod to move the sealing head up and down inside the sampling tube. A discharge port is provided on one side of the portion of the sampling tube outside the conveying pipe, and the discharge port is arranged inclined downward from the inside to the outside. This utility model, by setting several sampling tubes on the conveying pipe, with a sealing head, drive rod, and discharge port inside each sampling tube, allows aluminum hydroxide to be discharged along the sampling tube and the discharge port when sampling is required, by controlling the sealing head to move below the discharge port. After sampling, the sealing head moves above the discharge port, stopping the discharge of aluminum hydroxide. This allows for sampling of aluminum hydroxide at any time, and the obtained samples are more random and representative, thereby improving the accuracy of testing.

This application discloses an adaptive optimization method and system for thermal coupling parameters of automotive backlight panels, relating to the field of parameter simulation optimization technology. The specific implementation scheme is as follows: A full-envelope operating condition script is compiled; a thermal model and thermal coupling parameter set are imported; thermal simulations are automatically run in batches sequentially using the full-envelope operating condition script; raw datasets for each operating condition segment are collected; risky operating condition segments are screened; thermal coupling parameter perturbation groups are applied to each risky operating condition segment; high-risk operating condition segments are identified; parameter inversion is performed on each high-risk operating condition segment; and the thermal coupling parameter update strategy for each high-risk operating condition segment is determined, along with the optimal thermal coupling parameter version. This invention can improve the prediction accuracy of the thermal model under complex or extreme operating conditions, thereby avoiding problems such as underestimated junction temperature peaks, distorted hotspot locations, and drifting temperature rise rates. This provides a scientific and reliable data basis for the structural design, safety margin setting, and temperature control strategy optimization of automotive backlight panel radiators.

The utility model discloses a portable water quality detection sampling device relates to water quality detection technical field, including main support frame, one end top of main support frame is equipped with U type handle, the other end of main support frame is equipped with adjusting assembly, is used for carrying out water quality sampling to the target water area of different water depth and off shore distance, the other end bottom of main support frame is equipped with sampling assembly, is used for guaranteeing the smooth progress of water quality sampling process, the sampling assembly includes fixed cylinder, the fixed cylinder is located in the other end bottom of main support frame, the fixed cylinder bottom is connected with the pivot of bearing, the utility model discloses through arc plate drive several blocking lever around sampling cylinder rotation, all with sampling cylinder insulate waterweeds and silt etc, realize sampling through several sampling holes to avoid sampling blockage, ensure that the water quality of collection is more representative, reduces sample pretreatment step, guarantees the smooth progress of water quality sampling process.

The utility model relates to the technical field of polymer polyol sampling, and particularly discloses an energy-saving polymer polyol sampling device which comprises a closed sampling chamber with a transparent window and a side door, a medium feeding pipeline is arranged in the closed sampling chamber and is connected with a medium discharging pipeline, and the medium discharging pipeline is connected with the closed sampling chamber. A sampling pipe is connected to the joint of the medium discharging pipeline and the medium feeding pipeline, the sampling pipe is connected with a nitrogen purging pipeline, a threaded connector matched with a sampling bottle is arranged at a sampling opening of the sampling pipe, the sampling bottle is sleeved with a sampling bottle film sleeve molded by polyurethane, and the closed sampling chamber is further connected with a tail gas absorption pipeline. In the sampling process, operators can be prevented from being in direct contact with high-temperature, high-pressure or harmful materials, and the safety of the operators is guaranteed. The device can be integrated with a production line to reduce manual operation and improve production efficiency. The reasonably designed sampling device can reduce loss and waste of materials in the sampling process.

This invention relates to the field of environmental protection technology for coal-fired boilers, solving the problem of the difficulty in obtaining integrated, automated, and precise information on the characteristics of fly ash from coal-fired boilers. Specifically, it discloses a system and method for obtaining fly ash characteristics in coal-fired boilers, including a fly ash collection module, a fly ash pretreatment module, a characteristic detection module, a data processing module, and a control module. The fly ash collection module is connected to the flue of the coal-fired boiler; the fly ash pretreatment module is connected to the fly ash collection module; the characteristic detection module is connected to the fly ash pretreatment module; the data processing module is connected to both the characteristic detection module and the control module; and the control module is electrically connected to each of the three modules. The method of this invention includes S1, fly ash collection; S2, fly ash pretreatment; S3, characteristic detection; and S4, data processing and output. This invention is used for obtaining and detecting fly ash characteristics during combustion in coal-fired boilers, and features integration, automation, and high precision.

A PTEE powder automatic barreling packaging machine belongs to the field of barrel packaging machinery and comprises a feeding box, a vertically arranged segmented feeding mechanism is arranged at the upper end of the feeding box, the segmented feeding mechanism comprises a first adjusting valve, the first adjusting valve is connected with the upper end of the feeding box, at least two sets of discharging barrels are arranged at the upper end of the first adjusting valve, an adjusting valve is arranged between the discharging barrels, and the adjusting valve is connected with the first adjusting valve. A horizontally-arranged vibration feeding conveyor is arranged at the lower end of the feeding box, a dust removal mechanism is arranged at a discharging port in front of the vibration feeding conveyor, a weighing and compacting mechanism is arranged below the dust removal mechanism and can convey packaging barrels, and a sampling mechanism is arranged on the side of the dust removal mechanism. According to the PTFE powder packaging device, reliable and stable automatic packaging of PTFE powder is achieved through coordination and cooperation of all the mechanisms, the labor intensity of workers is relieved, and the production efficiency is greatly improved.

This invention proposes a student book recommendation system and method based on an improved temporal graph neural network, comprising a student borrowing graph representation model generation module, a graph node embedding matrix generation module, a graph-level embedding vector generation module, a book borrowing relationship prediction matrix generation module, and a borrowing relationship decoding and reconstruction module. It is implemented through five processes: determining the student book borrowing graph representation model, obtaining graph-level embedding vectors, obtaining a book borrowing relationship prediction matrix based on an improved gated recurrent unit model, and obtaining the borrowing relationships after decoding and reconstructing the prediction matrix. This invention considers the changes in students' borrowing interests over time, thus influencing their borrowing behavior and preferences. Compared to the previous recommendation algorithm, this invention reduces computation time by 50% and doubles efficiency.

The invention relates to a death risk prediction model for severe burn and hypoxic hepatitis, a construction method and a storage medium. The construction method of the death risk prediction model comprises the following steps: collecting clinical feature data of patients with severe burns and hypoxic hepatitis; using a regression model to analyze and screen the training set clinical feature data with the p value less than 0.05 and whether death exists, and screening out serious burn and hypoxic hepatitis and death-related clinical feature data; and constructing a death risk prediction model based on the screened clinical feature data. The invention also provides a death risk prediction model constructed by the construction method. The invention further provides a storage medium. According to the method, risk factors causing death of patients suffering from severe burns and hypoxic hepatitis are identified based on clinical basic data and disease related indexes of the patients, so that the death probability of the patients is conveniently, quickly and accurately predicted in advance, and doctors are helped to take corresponding prevention and treatment measures for the patients.

The application belongs to the technical field of sampling needle cleaning, and discloses a back-flushable sampling device, which comprises a sampling mechanism and a flushing mechanism. The sampling mechanism comprises a driving assembly and a sampling needle. The top of the driving assembly is provided with a sampling port. The inside of the driving assembly is provided with a sampling channel. The sampling channel is communicated with the sampling port and the sampling needle. The driving assembly can drive the sampling needle to move along the axial direction. The flushing mechanism is arranged below the sampling mechanism and comprises a flushing part, a sliding block and a driving part. The inside of the flushing part is provided with a flushing chamber. The flushing chamber penetrates through the flushing part. The driving assembly can drive the sampling needle to extend into or out of the flushing chamber so as to extend into or out of a sampling bottle. The flushing part is further provided with a flushing port. One end of the flushing port is communicated with the flushing chamber, and the other end can be connected with cleaning liquid. The sliding block can block the flushing chamber. The sliding block is provided with a communication hole and is connected with the output end of the driving part. The sampling and cleaning are integrated, the cleaning efficiency is high, the consumption of cleaning liquid is low, and the interference of residual liquid in the sampling needle on the next sampling can be eliminated.

The present application relates to the field of exploration survey, disclose a kind of rock sampling pose calculation method for field geological reconnaissance robot, comprising: the color image and depth image of target area are collected by depth camera, and three-dimensional point cloud is generated;Based on multi-scale geometric feature analysis, combined with spatial distribution constraint and confidence score, candidate points are automatically screened from point cloud, and stable sampling points and their pixel coordinates are output by time sequence smoothing and stability discrimination;Local depth data is extracted in the neighborhood of sampling point and converted into local point cloud, and the three-dimensional position and surface normal vector of the point in camera coordinate system are calculated using plane fitting algorithm;The position and normal vector are converted to the base coordinate system of mechanical arm using the pre-calibrated hand-eye conversion matrix, and the complete pose of the end effector is constructed based on the normal vector, and the target pose matrix is obtained by combination.The present application realizes the stable, accurate and automatic calculation of rock sampling point pose in complex outdoor environment.

The invention discloses a gas detection system with a high-sensitivity H-type photoacoustic cell, the gas detection system comprises a photoacoustic cell assembly, a first cylinder assembly and a second cylinder assembly, the photoacoustic cell assembly comprises a shell (1), a first protruding part is arranged on the A side of the shell (1), a laser (2) is arranged in the first protruding part, a first lens (3) is arranged in the emergent direction of the laser (2), and a second lens (4) is arranged in the first lens (3). Similarly, a second protruding part is further arranged on the side A of the shell (1), a second lens (4), a third lens (5), a reference cell (6) and a pyramid (7) are arranged in the second protruding part, a Porro prism (8) is arranged on the side B in the shell (1), the side A and the side B are two opposite side faces, meanwhile, the Porro prism (8) can reflect laser emitted by the laser device (2) into the second protruding part, and the laser device (2) can reflect the laser emitted by the laser device (2) into the second protruding part. And a photoacoustic cell (9) is also arranged in the middle of the shell (1).

The utility model discloses an automatic circulating temperature control quantitative sampling device, which belongs to the field of material sampling, comprises a sampling box, a quantitative bottle in the sampling box, a three-way valve a, a steam space heater, a material condenser, a sampling bottle, a sampling valve, a purge valve, a temperature measuring thermocouple and a three-way valve b, and is characterized in that the quantitative bottle is arranged in the sampling box; a three-way valve a is arranged above the top of the quantitative bottle through a pipeline, a nitrogen purging line is arranged on the three-way valve a, a purging valve is arranged on the nitrogen purging line, a three-way valve b is arranged below the bottom of the quantitative bottle through a pipeline, a material condenser and a temperature controller are arranged on the side edge of the sampling box, and a material pipeline of the material condenser is connected with the three-way valve b; a pipeline extends out of the right side of the three-way valve b and is communicated with a sampling bottle; a steam space heater and a temperature measuring thermocouple are embedded in the sampling box. The problems that in the sampling process, samples are not representative, the sampling number is not accurate, stub bars are multiple, and oxidation is prone to occurring when the sampling temperature is too high or crystallization is prone to occurring when the sampling temperature is too low are solved.

The application discloses a hyperspectral image target intelligent detection method based on deep learning and belongs to the field of remote sensing image processing. The method comprises the following steps: selecting a background training set with large difference and representativeness between each other through a coarse detection and de-correlated background pixel selection strategy; generating sufficient target training sets by using a target spectrum band random replacement target training sample data enhancement strategy; mixing and disordering the background and target training sets, and inputting the background and target training sets into upper and lower branches of a multi-depth-multi-branch target detection network respectively for training; inputting a to-be-detected pixel and a prior target into the upper and lower branches of the trained network respectively for target detection, and outputting the network to form a final detection result. By using the application, target pixels in a hyperspectral image can be detected and highlighted, and background pixels can be effectively suppressed, so that a detection result with high detection precision, high background suppression degree and high target-background separation degree is obtained.

The invention relates to the field of data processing, and provides a data verification method and device, electronic equipment and a readable storage medium. The method comprises the steps of obtaining list item data corresponding to a to-be-bid-invitation project; matching the list item data with historical list item data of a historical calibration project database by using a preset chapter matching priority to obtain historical matched list item data corresponding to the list item data, each chapter comprising at least one piece of historical list item data; performing data updating on the list item data by using calibration data in the historical matching list item data to obtain target verification data; and comparing the bidding data of the to-be-bid project by using the target verification data so as to verify the bidding data. The data verification efficiency in the bidding and tendering field can be improved, and meanwhile the data verification accuracy is improved.