51 results about "Dynamic screening" patented technology

The utility model relates to performance test field, concretely relates to a dust -removal -fan combined performance test device. It includes test box body, both sides in test box body inside are fixedly connected with two electric telescopic rods. The utility model electric telescopic rod drive screening plate changes from linear type to inverted V type, in the form transformation process, the filter hole on screening plate carries out dynamic screening to the material after dust removal, makes the material that meets the requirement pass through screening plate and falls into test box body, avoids the partial material accumulation that cannot pass through filter hole because of static screening, promotes screening precision, the inclination angle that screening plate deformation produces, promotes the material that does not meet the requirement automatic along the board surface and falls to test box body both sides, and the movement of screening plate can also push the material that accumulates on the limiting plate into test box body both sides, prevents the limiting plate from blocking, avoids the influence of the follow -up screening because of the material residue, and, the limiting plate cooperates with the baffle that is in the oblique line shape, and the material that slides down plays the role of direction.

The method for large scene real-time three-dimensional reconstruction based on 3R belongs to the field of computer vision and three-dimensional reconstruction technology, and comprises the following steps: acquiring images of an RGB monocular camera; constructing a multi-level reconstruction architecture of "ordinary frame-key frame-scene frame", and dynamically screening frame categories based on inter-frame point cloud overlap and reconstruction confidence; performing multi-frame three-dimensional reconstruction based on 3R on ordinary frames and related scene frames to generate point clouds in the same coordinate system; after a new key frame is confirmed, taking the scene frame as a medium, calculating a preliminary transformation between point clouds based on singular value decomposition, and then performing fine registration by using a GICP algorithm; and performing point cloud fusion by using a TSDF technology, and selectively locking high-quality areas to improve efficiency. The method breaks through the bottleneck of existing methods in terms of reconstruction accuracy and the like by innovatively integrating 3R multi-frame reconstruction, GICP registration and TSDF technology, and realizes large-scale scene three-dimensional reconstruction with high robustness, high accuracy and real-time performance.

The present application belongs to the technical field of intelligent control, and particularly relates to a kind of material quantity compensation conveying control method and device of pneumatic conveying system.The method comprises: receiving the starting instruction of material quantity compensation conveying control method, initializing the parameters of pneumatic conveying system;Based on the fault duration and historical operation data, the accumulated cumulative material quantity accumulated in the hopper during the fault is calculated;Compare the cumulative material quantity with the preset material quantity threshold, and select the conveying scheduling strategy according to the comparison result;Based on the conveying scheduling strategy, and combined with system pressure data, the current optimal pipeline combination is dynamically screened out through intelligent scheduling algorithm;Control the pneumatic conveying system to execute material quantity compensation conveying task according to the optimal pipeline combination;In the conveying process, real-time acquisition of conveying data is carried out, and the conveying data is fed back to the intelligent scheduling algorithm to dynamically optimize the classification of pipeline combination and update the operation parameters associated with each pipeline combination, so as to improve the stability, continuity and efficiency of pneumatic conveying system.

This invention discloses a resume screening and display method and system for human resource management. It constructs a keyword-dimension mapping table based on job description text using a natural language processing engine; analyzes keyword frequency, syntactic position, modification strength, and semantic relevance to generate a job requirement intensity vector; retrieves historical recruitment data based on job meta-information to generate a historical weight vector; adaptively calculates a smoothing coefficient based on the amount of historical data; and integrates dual-source weights to generate a dynamic weight vector; standardizes the scoring of each dimension of the resume, using a normalized formula based only on valid dimensions to calculate the matching degree, avoiding score distortion caused by missing fields; and finally displays the results sorted by matching degree. This invention abandons the preset weight mode, achieving dynamic screening with a tailored approach for each job, improving matching accuracy, operational efficiency, and the quality of human-machine collaborative decision-making, providing a scientific, efficient, and transparent intelligent solution for human resource management.

The present application relates to the field of artificial intelligence tracking technology, and discloses a pedestrian trajectory tracking method based on artificial intelligence.The method comprises collecting multi-source sensor pedestrian movement feature data stream, extracting initial trajectory key points as tracking reference points;dividing associated historical position data into a high-confidence trajectory segment set and a to-be-verified trajectory segment set, and discarding the to-be-verified set;arranging the high-confidence set in descending order according to the number of trajectory points, selecting the first several segments as optimal trajectory segments, and calculating the proportion;comparing the proportion with a dynamic screening threshold, outputting the high-confidence set as an initial tracking result, or outputting a trajectory checking instruction generated by comparing trajectory data;in response to the checking instruction, dividing the space grid of the optimal trajectory segment, and outputting an optimization instruction in combination with historical trajectory features;updating the reference points based on the optimization instruction, and screening and outputting secondary divided trajectory data;finally, obtaining parameters to generate a tracking efficiency evaluation coefficient, and starting a parameter correction strategy when the coefficient is lower than an optimization threshold.

The application provides an enteroscope video intelligent detection method and device based on double-system cascade decision, and belongs to the technical field of computer vision. The device comprises: a rapid screening module, which extracts multi-dimensional feature information from an input enteroscope video stream, calculates a diagnosis value score of a current frame according to the multi-dimensional feature information, compares the diagnosis value score with a dynamic screening threshold, and screens out a high-value frame. An accurate detection module is used for target detection on the high-value frame, and outputs a detection result and a confidence. The accurate detection module at least comprises a reference frame dynamic selection mechanism based on screening decision and a time sequence consistency mechanism based on feature fusion constraint. A cooperation optimization module receives the target detection result and the detection confidence, generates a feedback control signal for dynamically correcting the dynamic screening threshold based on multi-dimensional indexes of the target detection result, and realizes dynamic adjustment of detection.

The application relates to the field of unmanned aerial vehicle confrontation, and discloses a dynamic shielding launching method and system of an unmanned aerial vehicle smoke screen jamming bomb, which comprises the following steps: three-dimensional situation analysis is performed on the terrain undulation, meteorological shear layer, radar and photoelectric reconnaissance source distribution in a task airspace, a threat accessibility density field is generated, and a mobile sensitive section is divided; a back-stepping calculation is performed on the current flight attitude, heading bias and power margin of the unmanned aerial vehicle, a shielding and flight path superposition control parameter set is formed; trial calculation is performed on each launching time and release height, an overlapping interval of smoke screen formation and line-of-sight blocking is determined, and a continuous misleading candidate launching node is formed; the node is mapped to a preset avoidance route library, geometric deviation and time dislocation between a real avoidance route and a virtual induced flight path are compared, and a complete mobile instruction chain is formed; and according to the mobile instruction chain, real-time wind field return data and target tracking beam steering trend, a cooperative avoidance execution instruction is output. The application has the advantage of improving shielding continuity.

The application discloses a photovoltaic surface defect detection system and method based on image recognition processing. The system comprises a feature extraction network, a hybrid encoder and a decoder. The feature extraction network comprises a feature enhancement module adopting a convolution and additive self-attention hybrid structure, which is used for extracting multi-scale features. The hybrid encoder is composed of an intra-scale feature interaction module and a cross-scale feature fusion module. The intra-scale feature interaction module performs global modeling and noise suppression on high-level features through a self-attention unit and a frequency domain discriminative feedforward unit. The cross-scale feature fusion module adopts a fusion strategy based on a gating convolution unit to realize dynamic screening and fusion of multi-scale features. The method corresponds to the operation process of the system. The application is aimed at the characteristics of low contrast, multiple noises and defect superposition of EL images. Through the cooperative optimization of the above modules, the weak defect capture ability, the anti-interference ability and the multi-defect distinguishing ability are improved, and high-precision and high-real-time defect detection is realized.

Examples provide a system and method for dynamically filtering candidate item identifiers (IDs) from a pool of item IDs in real-time for automatic labeling of images for use as training data used to train computer vision (CV) models. Images of carts are paired with item receipts. Candidate item IDs are extracted from the receipts. Item recognition inference results generated by CV models are used to pair images of individual items with item IDs identifying the item in each item image. As each candidate item ID is assigned to an item image, the item ID is dynamically filtered. Any candidate item IDs remaining after filtering are assigned to any item images failing to pair with an item ID based on the infer results. The results are presented for review and status update via a user interface device for faster and more accurate auto-labeling of training data for CV models.

The application provides an AR video fusion superimposition method and system for ultra-low delay, which comprises the following steps: obtaining a display refresh event and a picture submission timestamp, calculating a next refresh time and calculating a remaining available time interval, and generating display synchronization constraint information; dynamically screening a synchronizable superimposition information set based on a remaining budget and an estimated execution time of virtual information; analyzing anchor points to generate geometric data, aggregating resources to a texture atlas, and calculating fusion weights combined with parameters such as urgency and stability; finally, the virtual and real scene pixels are weighted and fused by using a pixel shader, and the display is submitted. Through accurate control of the time window and intelligent screening of the content, the end-to-end delay is effectively reduced, the picture lag and trailing are avoided, the priority presentation of key information is ensured, and the smoothness, real-time performance and hardware energy efficiency of AR display are significantly improved.

This invention discloses an online inventory method, system, and medium, belonging to the field of inventory technology. The method includes: acquiring user behavior data based on data tracking; determining multi-dimensional indicators and comprehensive learning progress based on the behavior data; performing user behavior anomaly identification and generating identification results; performing dynamic feature filtering guided by learning behavior trends to generate a feature system; performing clustering on the feature system based on the K-means clustering algorithm to generate clustering results representing user group categories; wherein, the K value of the K-means clustering algorithm is determined by a dynamic adjustment rule guided by teaching weights; performing cluster feature anchoring processing and teaching matching on the clustering results to generate core features representing user learning details and teaching suggestions for guiding user learning; and generating an inventory report based on the core features, teaching suggestions, and clustering results. This invention has high inventory efficiency and data accuracy.

The application discloses a kind of cascade lithium battery consistency screening methods, comprising the following steps: step I: appearance inspection;Step II: voltage and resistance measurement;Step III: dynamic screening, to be screened battery is carried out charge-discharge test, export charge-discharge data, obtain average voltage curve;According to voltage deviation control to move curve to obtain the upper control line of voltage deviation, move curve to obtain the lower control line of voltage deviation, and the battery in voltage curve is located in the upper control line and the lower control line, that is, qualified battery;Step IV: after standing, according to new measurement voltage, resistance and other static sorting data grouping.Compared with prior screening method, the application combines dynamic and static comprehensively, further obtains battery performance parameter data, according to which batch sorting battery, consistency is better, later operation is longer, and safety is more reliable.

The application relates to the computer technical field, in particular to a traditional Chinese medicine processing parameter optimization method and system based on small sample transfer learning, which comprises the following steps: collecting multi-source domain historical data and target domain small sample data, extracting high-order statistics and calculating initial distribution distance; constructing an adaptive distribution difference measurement network, compensating density estimation deviation by dynamically adjusting kernel bandwidth; designing a negative transfer risk dynamic monitoring mechanism to monitor gradient direction consistency; establishing a collaborative failure detection model by using a bidirectional gate recurrent network to identify positive feedback amplification trend; and dynamically screening source domains and redistributing weights according to risk scores. The technical scheme can effectively inhibit negative transfer and collaborative failure of process parameters in the traditional Chinese medicine processing process, and realize stable optimization of traditional Chinese medicine processing process parameters under small samples.

The utility model discloses a kind of electric power cable protection pipe raw material automatic feeding devices, including installation box, rotatingly installed with rotary table in the installation box, fixedly embedded with screening frame on the rotary table, the rotary table is sleeved with second gear ring, rotatingly installed with driving wheel in the installation box, fixedly installed with discharge pipe in the installation box, the screening frame is rotatably connected with discharge pipe, rotatingly installed with mounting ring in the discharge pipe, discharge pipe is equipped with multiple groups of ring distribution flap, rotating is driven by rotary table screening frame, realize the dynamic screening of raw material, effectively separate the particle and impurity meeting production requirement, metal impurity or agglomerate after screening remains in screen frame, periodically open motor drive a group of mounting shaft in discharge pipe, rotate, under the action of first gear ring and multiple first gear, multiple flap are synchronously opened, metal impurity and agglomerate accumulated in screening frame fall into discharge pipe and are automatically discharged.

The utility model provides a kind of horizontal formula fast clamp's dynamic screening sorting device, including main body frame, feeding part, transport adjustment part, screening part, shunt storage part and control part, main body frame includes pedestal, screening seat, transfer carrier plate, shunt carrier plate and "n" shape dust shield, feeding part includes chain conveyer belt, flexible storage box, permanent magnet and correction iron block, transport adjustment part includes transport mechanism and adjusting mechanism, screening part includes driving mechanism and detection mechanism, shunt storage part includes shunt mechanism, temporary storage mechanism and storage mechanism. Operator only needs to go up and down horizontal formula fast clamp, saves artificial complicated, dull and stereotyped screening step, to reduce labor intensity;Screening efficiency is stable and controllable, significantly higher than artificial screening;Mechanical adjustment horizontal formula fast clamp is used, so that its position, angle is unified, through the acquisition and processing of digitized information, significantly reduce screening error, improve the accuracy of screening result.

The application discloses a content delivery method and device of a social platform, a storage medium and equipment, and belongs to the technical field of deep learning. A node to be dispatched is acquired in a strategy map, the node is generated according to a delivery target and is associated with multiple delivery strategies; a platform ecological snapshot and target crowd coverage are generated according to platform data of the social platform; an account adaptation degree is generated according to a publishing record of a user account; the most adaptive n triplets are screened according to the platform ecological snapshot, the target crowd coverage and the account adaptation degree, each triplet comprising a delivery strategy, a social platform and a user account; and content delivery is performed using the corresponding user account under the corresponding social platform by using the delivery strategy corresponding to the triplet. The application can dynamically screen the optimal "strategy-platform-account" combination, improve the content triggering precision and interactive conversion efficiency, update the scheduling weight corresponding to the delivery effect to the node, schedule the node according to the scheduling weight, and realize autonomous optimization of delivery.

The application belongs to the technical field of electric power warehousing, and discloses a multi-source material demand prediction and replenishment decision method for electric power warehousing, wherein a cross-system dynamic federal query system is constructed, an OPC UA protocol and a RESTful API fusion gateway are adopted, seamless docking of multiple systems such as electric power warehousing, power grid monitoring and weather warning is realized, data is standardized into a four-dimensional structure of materials, time, scene and attributes, and then implicit space-time correlation is completed through a space-time enhanced knowledge graph to form a standardized fusion data set; a hybrid prediction model combining migration learning is constructed, small sample scenes are adapted through similar scene data migration, and differentiated sub-models are designed for regular consumption materials and emergency materials, combined with time series trend decomposition and attention mechanism to strengthen the influence of key scenes; meanwhile, an adaptive data cleaning module and an automatic feature extraction mechanism are adopted, abnormal data is removed through double verification, missing values are intelligently completed, and core features are dynamically screened.

This invention discloses a liquid deposition coating device and process for metal powder, relating to the field of metal powder surface modification technology. It aims to solve the technical problem of uneven distribution of powder and grinding media within a drum due to the presence of the material's natural angle of repose. The device includes two support pipes, a drum, a wave-sequence pushing mechanism, and a rolling assembly arranged inside the drum. This invention uses the sequential action of the wave-sequence pushing mechanism to form a mechanical peristaltic wave that propagates from both ends to the middle within the drum, forcibly breaking the material's angle of repose and solving the "dead zone" problem of material accumulation at the ends of traditional drums. This achieves uniform mixing and efficient conveying throughout the entire drum axis. Combined with the dynamic screening and agglomeration effect of the rolling assembly, the distribution of grinding media and energy transfer path are optimized, transforming disordered collisions into ordered concentrated shearing. This significantly improves the sphericity, sphericity, and surface smoothness of the coated powder, and effectively prevents over-grinding.

The utility model discloses a peanut shell crushing and skinning machine for peanut butter processing, including the body, the front end surface both sides fixed mounting of body have second motor, and the output of second motor is fixedly connected with the shell crushing roller that penetrates the front end surface of body, the utility model discloses, by second motor drive shell crushing roller rotation completes the shell crushing procedure, and then the shell crushing peanut falls naturally to the initiative skinning roller work area, at this moment, the third motor drives initiative skinning roller operation, realizes the continuous skinning processing of peanut, and at the same time, the first motor drives the rotation of rotating rod and cam, and the cam periodically pushes the screen to make vertical displacement along the limiting rod, and the screen moves up and compresses the elastic deformation of limiting rod spring in this process, forms the continuous up-and-down reciprocating motion, and the dynamic screening mechanism increases the movement amplitude of screen in the body, not only optimizes the screening efficiency of peanut material, but also enhances the material fluidity and separation effect, and the overall processing quality and production efficiency are improved.

This invention relates to a carbon emission data accounting method based on activity data tracing, aiming to solve the problem of accurate adaptation and dynamic updating of emission factors under multi-source heterogeneous activity data. Its core technical solution includes: extracting and encoding core semantic elements from multi-source activity data to generate fixed-length activity semantic fingerprints; establishing a multi-dimensional emission factor evolution map based on historical emission factors and their change conditions; achieving dynamic screening and verification of candidate factors and data completion through bidirectional mapping between fingerprints and the map, and mapping the macroscopic and microscopic levels of the activity fingerprints to the map in parallel to achieve hierarchical weighted fusion output of standard carbon emission accounting factors; the system supports manual review signal feedback and real-time optimization and adjustment of map parameters. This solution improves the matching accuracy of emission accounting factors and the system's adaptability, supporting efficient dynamic carbon report generation and iterative optimization.

This application discloses a method, apparatus, storage medium, and electronic device for processing game data. The method includes: responding to a received match merge request; determining the matching degree of candidate match instances based on the difference in match progress between the requesting match instance and candidate match instances, the dynamic intensity of the match, and the predicted probability that the candidate match instance will accept the match merge request; selecting a target match instance from the set of candidate match instances based on the matching degree and a dynamic filtering radius; performing conflict detection on the merged operation data after merging the request and target match instances based on the historical operation data of the requesting match instance and the historical operation data of the target match instance to obtain global state data; and sequentially executing each operation in the merged operation data according to the round in the global state data. This application solves the technical problem of low operability in turn-based game matches.

A method and system for identifying key elements of power grid equipment based on the spider-bee optimization algorithm is disclosed. The method first constructs a full lifecycle element index system and extracts initial common factors, then constructs a correlation matrix to initialize the spider-bee population. Next, a fitness function is constructed to calculate individual fitness, obtaining local optima and updating the population accordingly. Constraint optimization of the population is then performed to obtain the optimal rotation angle vector, followed by the construction of the optimal orthogonal rotation matrix and the combination of the factor loading matrix to obtain the optimal factor loading matrix. Finally, after weighted column variance maximization rotation, extraction of common factors, and screening, the key elements of the power grid equipment are obtained. This invention improves the spider-bee optimization algorithm, enabling it to combine global search and local exploitation capabilities. Combining factor analysis and weighted column variance maximization rotation enhances the interpretability of factor loadings, avoids the influence of subjective analysis, and adapts to the data characteristics of power grid equipment, achieving dynamic screening of key elements and further improving the accuracy of identification.

The application discloses a kind of electric power bilateral transaction settlement deviation strategy optimization method, system and storage medium, belong to electric power market transaction technical field.The application obtains user historical load data, electricity demand prediction and transaction package parameters in real time through data interface;Based on probability distribution, construct load random fluctuation model, generate multi-scenario simulation load curve using Monte Carlo algorithm;Parallel trial calculation is carried out to candidate package using simulation settlement engine;The optimal transaction package is dynamically screened by multi-objective optimization function, and transaction instruction is generated;In transaction execution, deviation is monitored in real time by closed-loop feedback module, and contract adaptive adjustment is triggered.System includes five modules of data acquisition, random modeling, simulation settlement, strategy optimization and closed-loop feedback, integrates LSTM-GARCH hybrid prediction, GPU accelerated calculation, block chain storage technology.Improves the accuracy and adaptability of deviation strategy, reduces settlement risk, optimizes transaction efficiency, supports stable operation of electric power market.

This invention belongs to the field of building structure safety assessment and urban renewal, specifically a rapid detection and assessment method for prestressed concrete hollow slab floor systems with brick-concrete structures. Through comprehensive dynamic screening, the first-order natural frequencies of each slab are obtained using accelerometers. Based on a modified dynamic model considering actual rotational constraint stiffness, the most unfavorable components are identified. Boundary treatment and graded static load tests are then performed on the most unfavorable components, and the overall load-bearing capacity is reliably assessed using load-displacement curves. This invention replaces traditional random sampling with a "general survey followed by detailed investigation" strategy to avoid missed safety hazards. The accuracy of dynamic testing is improved by inverting actual boundary stiffness. A single-person jump excitation method is used to achieve rapid non-destructive screening, and static load verification is performed only on a very small number of key components, significantly reducing testing costs, minimizing resident interference, and forming a comprehensive assessment system that considers both breadth and depth.

The application relates to the field of agricultural intelligent technology, in particular to an agricultural vertical field intelligent system based on multi-agent cooperation and tool enhancement, which comprises a state construction module, a competition falsification module, an active probe module and a path synthesis module. The state construction module is used for generating plot state information; the competition falsification module is used for generating a candidate abnormal reason set, key missing evidence and an abnormal reason ranking result; the active probe module is used for supplementarily collecting key missing evidence corresponding data and updating the plot state information; and the path synthesis module is used for generating a farm treatment path. Through the application, dynamic screening, supplementary evidence and treatment decision of agricultural abnormal reasons can be realized, and the consistency of the results and actual production conditions is improved.

This invention discloses a dynamic screening and trajectory tracking method and system for accurate assessment of sperm motility, relating to the interdisciplinary fields of medical image analysis and artificial intelligence. This invention aims to address the problems of high subjectivity and low tracking accuracy in existing sperm motility analysis methods. The system consists of a preprocessing module, a detection module, a preheating screening module, a locking and tracking module, and a visualization output module. It includes: acquiring and preprocessing sperm motility videos; constructing an improved YOLO11 model for sperm detection; generating temporary trajectories using the ByteTrack algorithm and calculating quantification parameters; constructing a weighted scoring model based on velocity, persistence, and confidence to dynamically screen out high-activity trajectories; and locking and tracking only high-activity sperm in subsequent frames. This invention overcomes the limitations of existing methods that rely on single velocity or morphology recognition, achieving accurate grading and dynamic tracking of sperm motility, and has clinical application value.