13results about How to "Fully capture" patented technology

The invention relates to the technical field of nickel-containing dangerous and solid waste recycling, and discloses a complex nickel-containing waste smelting flue gas cleaning and comprehensive utilization method which comprises the steps that smelting flue gas is fed into a dry-method deacidification tower after being subjected to waste heat recovery and shock cooling, coarse-particle calcium hydroxide is sprayed into the dry-method deacidification tower, defluorination is preferentially carried out in a first temperature interval of the dry-method deacidification tower, and defluorination is carried out in a second temperature interval of the dry-method deacidification tower; a defluorination product is collected, and fluorine-containing dust is separated and collected through electrostatic dust collection; the dedusted flue gas enters a semi-dry deacidification tower, and fine-particle calcium hydroxide is sprayed into the semi-dry deacidification tower for deep dechlorination in a lower second temperature interval of the semi-dry deacidification tower; and discharging the purified gas after denitration, washing and ionic liquid desulfurization. The defluorination product is washed and purified to prepare hydrofluoric acid, and the dechlorination slag is dissolved and subjected to a double decomposition reaction to prepare hydrochloric acid. According to the method, a temperature gradient and absorbent particle size gradient coupling process is utilized, so that directional separation and enrichment of gas-phase fluorine and chlorine pollutants are effectively realized, the problem that carnallite is difficult to utilize is solved, and full-process recycling and ultralow emission are realized.

This invention relates to the field of time series forecasting technology and discloses a stock index forecasting method based on 1DCNN-ResBiLSTM, comprising the following steps: S1, data acquisition and sample construction; S2, data preprocessing; S3, local feature extraction; S4, long-term dependency learning; S5, residual feature fusion: extracting the feature vector of the last time step output by the 1DCNN module in S3, linearly mapping it to the same dimension as the output feature of S4 through a fully connected layer, and then adding it element-wise with the output feature of S4 to achieve residual feature fusion; S6, prediction result output; S7, model training and optimization. By adopting a technical solution that combines the 1DCNN module with time-dimensional sliding convolution and ReLU nonlinear activation, the method accurately captures the local fluctuation features and short-term trend information of stock time series, solving the problems of insufficient characterization of short-term stock price changes and inability to effectively mine local time series patterns.

The embodiment of the invention discloses a point cloud data processing method and device, electronic equipment and a storage medium. The initial features of the point cloud data can be obtained; performing feature extraction processing on the output features of the (i-1) th layer of coding block by adopting the ith layer of coding block to obtain the output features of the ith layer of coding block; performing feature fusion processing on the output feature of the (K-j + 1) th layer of coding block and the output feature of the (j-1) th layer of decoding block by adopting the jth layer of decoding block to obtain the output feature of the jth layer of decoding block; and performing point cloud identification processing based on the output feature of the last layer of decoding block to obtain an identification result of the point cloud data. According to the method, geometric dependency between local and overall shapes of the point cloud data is considered, so that the dependency relationship is effectively captured through layer-by-layer refinement and fusion, features of different scales are fused in a decoding process, and effective transmission of local and overall features is ensured. According to the scheme, the accuracy of feature representation of the point cloud data can be improved.

This application discloses a biomedical event assembly method, apparatus, device, and medium, relating to the field of natural language processing technology. The method includes: combining trigger words and arguments of the text to be assembled based on their trigger word types to obtain candidate events; tagging the trigger words and arguments of the candidate events using a nested tagging method to obtain candidate instances; encoding the candidate instances using a preset deep learning model to obtain an output representation of the semantic information of the candidate instances; acquiring a first probability result for a preset legal category and a second probability result for a preset illegal category of the output representation; and then determining a target biomedical event from the candidate events based on the first and second probability results. This method can improve the performance of biomedical event assembly.

The invention discloses an indoor personnel video behavior process identification system based on target detection and an MS-TCN + + algorithm, accurate detection and identification of a personnel behavior process in an indoor free scene are realized through cooperative processing of target detection, behavior triggering and time sequence identification, and the system utilizes adaptive switching of high and low frame intervals to realize accurate identification of the personnel behavior process in an indoor free scene. Details when behaviors occur are fully captured, and the calculation amount in a non-behavior period is remarkably reduced, so that automatic segmentation and positioning of behavior segments in a real-time video stream are realized; through key limb detection and cross-frame integration based on YOLOv7, continuity and detection stability of target tracking are guaranteed, and detection errors caused by shielding, posture changes and multi-person interaction are effectively coped with; and in combination with multi-scale time sequence modeling and inter-frame consistency constraint of the MS-TCN + + model, the system can extract behavior laws in long time sequence data and suppress the influence of noise frames, so that the recognition accuracy and robustness are improved while the real-time performance is ensured.

The invention discloses an animal delivery automatic counting method and system based on image recognition and threshold adjustment, and the method comprises the steps: firstly collecting a delivery segment video in real time, and obtaining a video detection result through employing a target detection model in combination with a bounding box similarity algorithm; performing preliminary segmentation on the detection frame sequence by adopting a preset interval value, and calculating an interval threshold value based on the interval between the candidate segments; then identifying abnormal short interval segments by using the extracted interval threshold, and merging the abnormal short interval segments to adjacent segments to generate an effective childbirth segment set corresponding to one actual childbirth event; calculating a confidence coefficient dynamic threshold value based on the local sliding window average and a preset minimum confidence coefficient, and setting continuous frame requirements according to confidence coefficient level grading; and finally, in combination with a delivery section division result, a confidence coefficient dynamic threshold value and a continuous frame requirement, carrying out validity judgment on each candidate delivery section, and carrying out statistics on effective delivery times so as to calculate the total number of cubs. The practicability and the intelligent level of the automatic counting system for animal delivery are remarkably improved.

The embodiment of the invention discloses a thyroid cancer iodine treatment dose prediction method and system based on multi-modal fusion, and the method comprises the steps: obtaining original multi-modal data of a patient through a multi-modal data integration module, carrying out the preprocessing, feature extraction and feature fusion processing of the original multi-modal data, and obtaining multi-modal fusion features; wherein the original multi-modal data comprises original clinical data, original pathological data, original biochemical index data and original iconography data; a dynamic time sequence modeling module is used for determining a disease evolution sequence based on the multi-modal fusion features, and the disease evolution sequence is used for representing time sequence characteristics of disease development and treatment response; an iodine therapy dose regimen is determined using an adaptive dose decision module based on patient characteristics and an adaptive decision model, the patient characteristics including the raw multi-modal data, risk preferences of the patient, and the sequence of disease evolution.

The invention relates to the technical field of artificial intelligence and voice processing, can be applied to the field of intelligent medical treatment and finance, and discloses an audio forgery detection method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the preprocessing of a to-be-detected audio signal, and extracting the frequency domain features and time domain features of the preprocessed audio signal, obtaining a time domain feature sequence and a frequency domain feature sequence; according to the time-domain feature sequence and the frequency-domain feature sequence, establishing correlation between self-modals and cross-modals of the time-domain features and the frequency-domain features in a graph neural network mode by using an attention mechanism, and obtaining a fusion feature map of fusion of the time-domain features and the frequency-domain features; calculating a global feature of the fusion feature spectrum according to each node feature in the fusion feature spectrum; and adopting a classifier to carry out audio forging detection on the global features of the fusion feature spectrum.

The application relates to the technical field of machine learning, and particularly discloses a spatial local XGBoost machine learning model based on multi-scale geographical weighting, which comprises the following modules: a feature decoupling module for constructing a double-channel input structure of geographical features and non-geographical features, realizing feature decoupling and fusion through a multi-scale spatial weight matrix; a bandwidth allocation module for dynamically determining a bandwidth scale in an XGBoost tree splitting process and establishing dynamic weights of tree levels; a constraint gain module for generating a splitting point marked with a scale; a contribution decoupling module for extracting splitting features and correlating geographical features and non-geographical features, realizing salted prediction and contribution index extraction; and a verification optimization module for optimizing model parameters through multi-scale heat maps and spatial autocorrelation analysis. The model can capture geographical spatial effects of different scales, improve spatial local prediction accuracy, and be applied to a scene with spatial heterogeneity in soil salinization analysis.

The utility model discloses a three-layer composite filter cartridge for a central air-conditioning filter system, which comprises a mounting bottom plate and a filter barrel, and the upper side surface of the mounting bottom plate is provided with uniformly distributed insertion grooves; the filtering barrel comprises an inner barrel, a middle barrel, an outer barrel, rotating shafts and spiral blades, the lower ends of the inner barrel, the middle barrel and the outer barrel are inserted into the inserting grooves adjacent to the lower sides, the inner barrel, the middle barrel and the outer barrel are distributed in a staggered mode, the rotating shafts which are evenly distributed are arranged between the middle barrel and the outer barrel, and the spiral blades are arranged on the outer arc surfaces of the rotating shafts; according to the three-layer composite filter cartridge for the central air-conditioning filter system, the contact time of airflow and a filter material is prolonged, the filter material of the outer barrel is not easily and quickly blocked by large particles, so that the service life of the whole filter cartridge is prolonged, meanwhile, the three-layer composite filter cartridge, the separation cover plate and the filter barrel can be quickly disassembled, and the three-layer composite filter cartridge is convenient and quick to use. And the maintenance efficiency is improved.

This invention belongs to the field of large-scale power language models and discloses a method and related apparatus for recommending test cases for large-scale power models. It constructs state data including attack success rate and recommendation latency, utilizes reinforcement learning pre-trained depth-determining models to adaptively select the current knowledge graph exploration depth, dynamically adjusts the knowledge graph propagation range based on historical recommendation results, and employs a relation-aware attention mechanism in recursive propagation to weighted aggregate neighbor tail entities. Entity features under different relations are projected onto the corresponding relation space for semantic matching. A bidirectional interactive aggregator is combined to fuse its own features with neighboring features through addition and multiplication, enhancing feature representation capabilities. A layered aggregation mechanism concatenates features from various depths into a fusion vector and sorts them by inner product to select test cases, enabling the recommendation results to incorporate hierarchical semantic information from multi-hop propagation. This achieves synergistic optimization of recommendation accuracy and response speed, effectively supporting rapid evaluation of the security performance of large-scale power models.

The application relates to the technical field of dust removal devices, in particular to a reinforced dust removal electric dust collector and electric dust removal system. A plurality of dust removal areas are arranged in the electric dust collector and are spaced apart along the airflow direction to process dust-containing gas in stages, so that the dust can be fully charged and captured when passing through each electric field. Even if part of the dust cannot be completely captured in the front-stage electric field, the dust can be efficiently separated through re-charging in the subsequent electric field. The overall performance of the electric dust removal device is significantly improved through the step-by-step optimization mode. At least one dust removal area is connected with a reinforced dust removal assembly. The assembly can further enhance the electric field strength or improve the particle charging effect according to the actual working condition requirements (such as dust properties, airflow speed, etc.). In this way, the shortcomings of the traditional electric dust removal device in processing high-concentration dust or difficult-to-capture particles can be compensated for, and the dust removal requirements in different scenes can be flexibly adapted to, so that the applicability and performance of the equipment are significantly improved.

The application discloses a smart contract vulnerability detection method based on multi-view learning, and the method obtains three representation modes of a smart contract source code, an abstract syntax tree, a control flow graph and a data flow graph through static analysis of the smart contract; noise codes outside called external functions and variable positions are pruned for different representation modes, and features of the noise codes are obtained; abstract syntax tree features are learned through an extended recurrent neural network, and control flow graph and data flow graph features are learned through a graph attention network; and finally, features obtained through fusion of the three kinds of features are used to detect smart contract vulnerabilities. The smart contract vulnerability detection method based on multi-view learning can more comprehensively capture indicative features of vulnerabilities from codes, simplify redundant noise, and improve the performance and effect of smart contract vulnerability detection.