256 results about "Feature evaluation" patented technology

The invention provides an image noise mark feature selection method and system, a storage medium and a computer. The method comprises the steps of obtaining a to-be-processed image noise mark data set; embedding a sample set in the image noise mark data set into a multi-granularity fuzzy cluster to construct a dynamic fuzzy membership evaluation matrix; dynamically evolving a multi-level high-precision granular ball cluster; obtaining mark distribution with high identification degree; constructing a rough perception feature evaluation framework based on granular ball topology driving, extracting decision equivalence classes by combining rough set upper and lower approximation and extended positive domain models, and determining and measuring the contribution degree of each feature to a decision system by fusing multi-granular-ball decision boundary information based on a dependency degree quantitative model; a particle and ball structure consistency verification mechanism is introduced, and multi-level evaluation is carried out on the importance of the features through dependency and consistency. According to the method, the optimal feature subset with strong anti-noise performance and high discrimination capability is obtained, and stable and efficient input support is provided for a subsequent image noise mark learning model.

The invention discloses an underwater robot real-time three-dimensional map reconstruction system and method fused with an SLAM algorithm, and belongs to the technical field of three-dimensional map reconstruction. By constructing a confidence coefficient system of three-dimensional points, a spatial trajectory fluctuation index and an inter-frame texture change rate are introduced as dynamic feature evaluation indexes; and a regression model is adopted to score and grade the severity of the false points, and differential processing of different grades of point clouds is realized in combination with a dynamic suppression mechanism, so that an unstable structure is effectively eliminated, and the stability and reliability of the sparse three-dimensional map are remarkably improved. Therefore, the positioning precision, the path planning capability and the task execution safety of the underwater robot in a complex environment are enhanced.

The invention provides a dynamic data traceability method and system oriented to network security, and relates to the technical field of network security and data governance crossing, and the method comprises the steps: carrying out the real-time visual monitoring of a user interaction interface of a data transaction platform, and capturing the visual behavior information related to data calling; extracting feature parameters based on the visual behavior information to obtain a visual feature data set, and performing structured conversion on the visual feature data set to obtain a structured call log record containing visual behavior associated information; based on the structured call log record, extracting a time sequence, a frequency and a spatial distribution feature of a call behavior as basic indexes; a plurality of feature sampling states are dynamically selected in a monitoring time window, and a dynamic feature evaluation set is constructed based on the feature sampling states. According to the invention, the accuracy and controllability of network security protection in a data transaction scene can be improved.

The invention discloses a tracking and tracing method and system based on an RFID Internet of Things technology. The method comprises the following steps: firstly, realizing full-link abnormal risk quantification through multi-source data fusion and dynamic evaluation; the method comprises the following steps: carrying out feature embedding processing on RFID full-link sensing data of a tracked article, and extracting a sensing feature vector; generating fusion depth features reflecting full-link association through depth feature fusion; evaluating the fusion depth feature based on a multi-traceability link to obtain the abnormal confidence of each link; analyzing the perception feature vector to obtain an influence coefficient of each link on the whole link abnormity; and dynamically aggregating the abnormal confidence coefficient and the influence coefficient, and calculating a full-link abnormal probability. According to the method, the problems of multi-source data time sequence alignment and feature fusion are solved, accurate positioning of abnormities of all links and dynamic evaluation of full-link risks are achieved, the method is suitable for full-link tracking scenes such as agricultural products and aquatic products, and the quality control efficiency is improved.

The invention provides an efficient data retrieval method and system oriented to a large language model. The method comprises the following steps: determining an intention vector set matched with a user intention; determining a specified number of candidate text fragments with the highest correlation with the user intention in an index database; obtaining multi-dimensional feature evaluation data of each candidate text fragment, and constructing a multi-dimensional feature numerical matrix of each candidate text fragment according to the multi-dimensional feature evaluation data; according to the multi-dimensional feature numerical value matrix, selecting selected text fragments from the candidate text fragments; sorting the selected text fragments, and sequentially performing scene matching on the selected text fragments and a pre-cached high-frequency query scene according to the sorting, so as to extract cache content matched with the target high-frequency query scene from the cache as a query result when a matching result represents that the current query scene accords with the target high-frequency query scene. The invention provides an efficient data retrieval method, and the quality and precision of data retrieval are improved.

The invention relates to the technical field of underwater detection, and discloses a forward-looking sonar underwater detection system based on multi-beam forming. The system comprises seven modules: a sonar data acquisition module obtains a multi-beam sonar original data sequence; a historical sonar database retrieval module retrieves a matched historical detection record set according to the region identifier; the heterogeneous sonar record distinguishing module classifies the historical sets and determines a plurality of distinguishing sets; a sonar feature extraction module traverses and distinguishes the set calculation to obtain a sonar feature set value and an associated bandwidth; the multi-scale sonar analysis module processes a network layer receptive field by taking a feature association bandwidth as a beam, and analyzes original data to obtain a multi-scale detection feature set; a cross-scale sonar fusion module performs interactive fusion on the multi-scale features to generate a target interactive fusion sonar feature set; and the underwater target area evaluation module outputs a thermodynamic map containing potential target area probability distribution based on fusion feature evaluation, and adapts to complex underwater environment detection.

The invention discloses an intelligent inspection method and system for a construction site, and belongs to the technical field of image processing. The method comprises the following steps: processing a remote sensing image of a construction site cement pavement, and positioning a pavement pixel area; calculating a relative difference value of each pixel point according to a pixel mean value of the region, and generating a difference value distribution image; and extracting a maximum value and a minimum value in each window region of the distribution image to respectively obtain a high-difference value compressed image and a low-difference value compressed image. Then, marking a non-pavement pixel region as an abnormal point, carrying out grid division on the two types of compressed images, calculating a difference characteristic value based on the abnormal point in a grid, and forming a high and low difference characteristic matrix; respectively calculating the joint deviation degree of each grid difference characteristic value to obtain a high joint deviation matrix and a low joint deviation matrix; and finally, processing the matrix through a pavement defect feature evaluation network, and outputting a pavement quality score. According to the invention, through multi-dimensional feature extraction and intelligent evaluation, the precision of pavement evaluation is effectively improved.

To improve the defect detection accuracy of an object in a focused process of inspection.SOLUTION: A defect inspection device that inspects a defect of an object in a focused process of inspection, acquires a training image that is an image of the object in the focused process of inspection, and further trains a base model neural network intended for feature extraction using the training images and data regarding defects visible in the training image, then acquires an inspection image that is an image of the object's target inspection area in the focused process of inspection, and uses an individual model obtained by additional training of the base model in a fine-tuning unit to evaluate a defect of the object in the focused process of inspection from the inspection image, evaluates a defect of the object in the focused process of inspection based on a feature quantity corresponding to the defect of the object depicted in the inspection image to perform defect inspection of the object based on the evaluation result from a first evaluation unit and the evaluation result from a second evaluation unit.SELECTED DRAWING: Figure 2

The invention provides a health state depth feature extraction method for key components of an extra-high voltage direct current transmission converter valve, and belongs to the technical field of extra-high voltage transmission equipment.The health state depth feature extraction method comprises the steps that firstly, different fault state models are constructed through PSCAD simulation, data are collected, and dimension reduction processing is conducted on multi-source heterogeneous data through principal component analysis; and establishing a time sequence sliding window mechanism to calculate data characteristic parameters. And then temperature features are extracted based on a thyristor junction thermal diffusion mechanism equation, deep feature extraction is performed by using a multi-head self-attention enhanced bidirectional long-short-term memory network, multi-source data such as infrared temperature measurement and ultraviolet discharge are fused, and abnormal feature representation is calculated through an isolated point feature evaluation function. And finally, constructing a feature vector space containing electrical features, temperature features, isolated point features and multi-component correlation features, outputting complete health state feature representation, and providing a basis for state evaluation and fault prediction of the converter valve.

The invention discloses a music playing intelligent evaluation system and method based on multi-mode and man-machine cooperation, and relates to the technical field of music playing intelligent evaluation, and the method comprises the steps: collecting audio signals, video images and playing motion data in a music playing process, and obtaining a multi-mode information data set; performing feature extraction on the multi-mode information data set, and analyzing the audio signal, the video image and the playing action data by applying a convolutional neural network and a recurrent neural network model to generate a basic feature set; based on the basic feature set, utilizing a deep learning algorithm to identify and analyze emotion content conveyed in the playing process, and outputting an emotion intensity value and an emotion category; analyzing intonation error, rhythm deviation and strength matching degree according to comparison between the standard music score and the playing record, evaluating action normalization of the player in combination with action characteristics extracted from the playing action data, and calculating scores of all dimensions; and adjusting the weight between the objective score and the subjective score according to the application scene.

The invention discloses a video small target detection method and system based on density features, and the method comprises the following steps: taking a plurality of frames of images of a video as input, carrying out the feature extraction of a backbone network, enabling a spatial-temporal feature fusion module to fully utilize the features of adjacent reference frames to enhance the target features of a current frame through deformable convolution, and carrying out the feature extraction; and the information loss in the feature extraction process is effectively compensated. The space-feature fusion module introduces feature features and combines space and channel attention mechanisms to dynamically generate reasonable query, so that the detection capability of small targets in a dense region is remarkably enhanced. The coarse-to-fine reference feature screening and enhancement module is composed of a reference feature evaluation and selective feature enhancement module, richer information is provided for small target detection, and finally a target detection result is output through a prediction module. The modules cooperate with each other to improve the overall performance of video small target detection.

The invention discloses a product recommendation method and device, computer equipment and a storage medium, belongs to the technical field of artificial intelligence, and is used for determining recommended customers adapted to insurance products. Firstly, an advanced natural language processing model is utilized to accurately analyze a user intention, and key semantic information is extracted; secondly, user requirements are accurately mapped to specific industries and business scenes through semantic mapping rules; newest market data and policy information are obtained in real time through a networking search interface, and timeliness and comprehensiveness of the data are guaranteed. Based on a preset report template, the system automatically integrates the upstream and downstream structures and policy dynamics of the industrial chain, and generates a structured and visual market insight report. And finally, extracting high-value customers meeting business requirements from the report through a customer portrait matching algorithm, and forming an accurate recommendation customer set in combination with multi-dimensional feature evaluation. According to the invention, precise product recommendation and high-value customer mining based on natural language input of the user are realized.

The invention relates to a blockchain-based mesenchymal stem cell safety inspection method and system, and relates to the field of data processing, core detection data and environmental parameters of stem cells are acquired for data formatting, timestamps and equipment ID metadata are embedded, a structured data object is established, and data state feature evaluation is executed; an encryption strategy is configured for encryption according to the evaluation result and the disturbance strategy, zero-knowledge proof is generated for an encrypted ciphertext and encryption parameters, the disturbance strategy and the encryption parameters serve as metadata records, and contract management is controlled through special disturbance; and uploading the encrypted ciphertext, the zero-knowledge proof and the special disturbance control contract to the block chain according to the preset block data structure to perform safety inspection management, thereby solving the technical problems that the safety inspection data of the mesenchymal stem cells are easy to tamper and lose, the processing efficiency is low, and tracing and sharing are difficult.

The invention discloses a text content risk identification method and system, a computer device, a medium and a product. The text content risk identification method comprises the following steps: splitting a to-be-identified multi-language text initiated by a target user according to different languages to obtain a plurality of language texts; translating a non-target language text in the plurality of language texts to obtain a translated text of a target language; obtaining texts of all target languages, and recording the texts as target texts; obtaining multi-dimensional data of a target user from a business system database based on an MCP mechanism, and constructing a user portrait according to the multi-dimensional data; the target text, the user portrait and a risk feature evaluation algorithm are input into a semantic analysis understanding large model, semantic analysis information is obtained, and the semantic analysis information comprises risk feature scores and risk text positions; and determining a risk type according to the risk feature score, and triggering a corresponding processing mechanism according to the risk type. According to the method, rapid and accurate multi-language text risk identification can be realized.

The embodiment of the invention discloses a news content recommendation method based on a value-aware double-layer attention network. A specific embodiment of the method comprises the steps of inputting candidate news information into a pre-trained double-layer attention network to generate a news feature evaluation value, and performing value perception on the candidate news information to generate candidate news value features; performing attention feature extraction on the candidate news value features to generate candidate news value attention features; encoding the candidate news information to generate candidate news codes; performing feature evaluation on the candidate news value attention features and the candidate news codes to generate news feature evaluation values; and according to the news feature evaluation value, adding the candidate news information to a corresponding position in a news information recommendation queue, and sending the news information meeting a preset pushing condition in the news information recommendation queue to the user terminal. According to the embodiment, waste of transmission resources can be reduced.

The aerosol visual detection system comprises a base, a light source cavity, a smoke diffusion cavity and a camera shooting cavity are formed in the base in sequence, a shading insertion plate is inserted between the light source cavity and the smoke diffusion cavity, a transparent smoke isolation insertion plate is inserted between the smoke diffusion cavity and the camera shooting cavity, and the light source cavity, the smoke diffusion cavity and the camera shooting cavity are communicated through the transparent smoke isolation insertion plate. A plane light source is arranged on one side of the base, a cover plate is arranged on the other side of the base, a camera is arranged on the side, facing the camera shooting cavity, of the cover plate, and a smoke exhaust pull plate is detachably arranged at the front end of the smoke diffusion cavity. According to the aerosol visual detection system and the characteristic parameter evaluation method, the camera can directly obtain the two-dimensional space distribution of the aerosol through plane imaging, and in combination with an image analysis technology, not only can the concentration information be inverted, but also multi-dimensional characteristics such as textures, contours and dynamic diffusion can be extracted; the defects of a traditional photoelectric method in spatial information and multi-feature analysis can be overcome, and a new technical path is provided for fine detection and feature evaluation of aerosol.

The invention relates to the technical field of energy consumption interval prediction, and particularly discloses a building energy consumption interval prediction method, system and equipment, and the method comprises the steps: collecting historical energy consumption data, meteorological data, building characteristic data and use mode data of a target building, and carrying out the hierarchical processing, thereby obtaining a hierarchical data set; performing wavelet transform decomposition on the historical energy consumption data, and decomposing the energy consumption time sequence into a trend term, a periodic term and a random term to obtain multi-scale decomposition features; constructing a feature evaluation model, calculating a contribution degree and dynamically allocating weights to obtain a weighted feature set; constructing an integrated prediction framework based on the weighted feature set, and generating a prediction interval through quantile regression; and performing adaptive adjustment according to the historical prediction deviation and the environmental factor change to obtain a final prediction interval. Through multi-scale feature processing, dynamic weight optimization and prediction interval adaptive calibration, the accuracy and reliability of the prediction interval are improved, and more accurate support is provided for building energy management.

The invention relates to the technical field of medical image auxiliary diagnosis, and provides an intervertebral joint osteoarthritis image feature evaluation method based on deep learning, which can synchronously identify five types of FJOA image features such as joint space stenosis, osteophyte, hypertrophy, subchondral bone erosion and subchondral cyst, and improves the comprehensiveness and efficiency of evaluation. The nnU-Net model is adopted to perform high-precision segmentation on an intervertebral joint region, so that the positioning precision is effectively improved; by introducing a shared feature extraction network based on ResNet-18 and five parallel classification sub-networks, joint modeling of multi-scale semantic information is realized, and the recognition accuracy and generalization ability of the model are improved; according to the method, a Grad-CAM technology is combined to generate an activation thermodynamic diagram, a model interpretation basis is superposed to an original image, visual display of an evaluation result is realized, interpretability and clinical applicability of the model are enhanced, and FJOA image features in axial lumbar vertebra CT images from two central data sets can be quantitatively evaluated so as to comprehensively quantify individual FJOA image features.

The invention relates to the technical field of data processing, and discloses a multi-source data acquisition processing method and system based on artificial intelligence, and the method comprises the steps: carrying out the priority evaluation of the data of a data source based on a data multi-dimensional feature evaluation system and an LSTM network model, determining an association result of the data in an acquired data set based on an association rule algorithm, and carrying out the calculation of the association result. Whether correlation verification is passed or not is judged according to the reproduction frequency, a correlation result is directionally modified, a data correlation identifier is generated, the correlation result is supplemented based on the data correlation identifier and a graph theory method, data without correlation in the collected data set is classified through a three-level classification system, and a classification result is determined. And determining a data degree score for the associated data set and the classification result based on a priority evaluation result, verifying the integrity of the storage according to the hash value, and adjusting the storage position of the data storage according to the call page view. According to the invention, the real-time performance, integrity and accuracy of multi-source data acquisition and processing are ensured.

The invention discloses a digital twin multi-source data anomaly monitoring method and system based on intellectualization, and belongs to the technical field of digital twin, and the method comprises the steps: obtaining multi-source data from a multi-sensor data collection device, and carrying out the preprocessing of the obtained multi-source data, according to the method, the monitoring area is intelligently divided through factors such as physical position, functional logic and equipment distribution, and an independent digital twinborn model is constructed for each sub-area, so that local conditions can be reflected more accurately, the accuracy and flexibility of the model are improved, and the real-time monitoring of the target area is realized by acquiring and analyzing the situation information of the target area in real time. The situation model is dynamically updated to adapt to changing environmental conditions, sensitivity and response ability to external changes are enhanced, digital twin data and situation data are deeply fused, key features related to anomaly detection are extracted, and comprehensiveness and pertinence of feature selection are ensured in combination with a multi-scale feature evaluation mechanism. And the accuracy of anomaly detection is improved.

The invention discloses a postoperative sleep disorder key factor identification method, and belongs to the technical field of medical informatics, and the method comprises the steps: collecting data, and preprocessing the data into a candidate feature set; carrying out feature importance calculation by adopting evaluation methods of at least five different principles; the importance and stability of the features are evaluated through score and ranking analysis path fusion; the features are divided into four quadrants according to importance and stability indexes by using a two-dimensional scatter diagram, and feature classification is performed, so that key factors of the postoperative sleep disorder are accurately positioned. The method improves the robustness and consistency of feature evaluation through multi-model fusion, reduces the deviation of a single method, achieves the precise recognition of key factors of postoperative sleep disorders, supports the construction and intervention optimization of a clinical prediction model, and improves the diagnosis accuracy and patient management efficiency.

The invention relates to the technical field of voltage regulation cabinet monitoring, and particularly provides a medium and low voltage voltage regulation cabinet intelligent monitoring method based on big data and Internet of Things, and the method comprises the following steps: installing a sensor in voltage regulation cabinet equipment, and collecting key parameters, such as pressure, temperature, flow, current and the like, in the operation process of the equipment in real time; transmitting the data to a cloud platform through a wireless network; and the cloud platform performs deep analysis on the acquired data based on big data storage, processing and analysis technologies, and performs equipment operation health scoring, state evaluation and fault prediction by utilizing innovative design and fusing a vector random forest (SRA) of a support vector machine and a random forest algorithm. According to the algorithm, fine classification capability, noise immunity and feature evaluation are fused, the equipment operation health state can be accurately scored, and faults can be effectively predicted. The innovation point lies in that the advantages of the two algorithms are complemented by using a vector fusion method, efficient feature extraction and decision fusion are realized in a multi-dimensional feature space, and the complex monitoring requirements of big data and the Internet of Things are met. According to the invention, a data acquisition module of a high-precision sensor and a data transmission module of wireless communication are deployed in the gas medium-pressure equipment, and a big data storage and processing technology, a machine learning algorithm and an intelligent early warning mechanism are combined, so that real-time monitoring, fault prediction and maintenance optimization of the operation state of the equipment are realized; therefore, the safety, the reliability and the operation and maintenance efficiency of the gas equipment are improved.

The invention discloses an AGV driving path control method and device considering energy consumption optimization, equipment and a medium, and relates to the technical field of AGV control, and the method comprises the following steps: obtaining a first acceleration limit; a first maximum load configuration; performing segmented proportional scaling processing on the first maximum load configuration and the first acceleration limit, and randomly combining to generate a plurality of first energy consumption optimization control sets; aGV driving is controlled according to the first energy consumption optimization control set, feature extraction is carried out on the driving process of each group of AGVs, and an optimization evaluation value is generated through evaluation; and constructing an energy consumption optimization-AGV display model according to each group of first energy consumption optimization control set and the corresponding generated optimization evaluation value, performing data analysis, screening out a second energy consumption optimization control set, and applying the second energy consumption optimization control set to AGV driving path control. The problem of contradiction between energy consumption and stability caused by AGV acceleration and load coupling is effectively solved.

The invention discloses an urban three-dimensional greening feature measurement method and system based on a human-based view angle and ground-air fusion, a terminal and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: obtaining multi-source data corresponding to a target region, the multi-source data comprises oblique photography data acquired based on aerial equipment and laser point cloud data acquired based on ground acquisition equipment; coloring the laser point cloud data according to a preset point cloud coloring operation to obtain target point cloud data; constructing a three-dimensional greening model corresponding to the target area according to the oblique photography data and the target point cloud data; according to a preset viewpoint height, determining a corresponding human-based viewpoint in the three-dimensional greening model; and constructing a ray beam according to the human-based visual angle point and a preset vision field parameter, and determining a value of a greening characteristic evaluation index corresponding to the target area based on a collision detection result of rays in the ray beam and the three-dimensional greening model. Therefore, the accuracy of urban landscaping characteristic measurement can be improved.

The invention discloses a highway vehicle driving identity information characterization method, which comprises the following steps of: constructing a driving identity index system comprising a vehicle relative characteristic index and a vehicle dynamic characteristic index, and realizing accurate characterization of a vehicle identity in combination with multi-dimensional data acquisition and an improved matter element extension model. The method specifically comprises the following steps: collecting expressway vehicle driving data, and constructing an expressway global historical data set and a vehicle historical data set; designing a double-layer node domain matter element and a classic domain matter element, and optimizing feature evaluation; and calculating a vehicle driving characteristic comprehensive evaluation index value through the correlation coefficient, quantifying the correlation degree of the target vehicle and historical data, and judging the identity of the vehicle in combination with a preset threshold. According to the method, the matter element extension theory and multi-dimensional data analysis are fused, the method has the advantages of being high in interpretability and low in complexity, fee evasion behaviors such as fake plates and abnormal tracks can be effectively recognized, and technical support is provided for intelligent monitoring and auditing of expressways.

The invention discloses a wind shear dynamic risk assessment and grading alarm method, and aims to solve the problems that a wind shear detection method is easily influenced by turbulent flow and topographic factors, multi-dimensional information and environmental factors are not fully utilized, so that the false alarm rate is high, the missing report risk is high, the environmental adaptability is poor, and an effective dynamic assessment mechanism is lacked. And real-time reliability evaluation and optimization cannot be carried out on a detection result, so that the flight safety of the airplane is low. According to the method, the comprehensive risk index and multiple performances of the multi-dimensional features are evaluated according to the multi-dimensional features of the aircraft, the comprehensive reliability index is calculated according to the evaluation result, the comprehensive risk index and the comprehensive reliability index are updated according to the historical detection rate and the false alarm rate, the detection threshold value is updated according to the reference threshold value and the updated comprehensive reliability index, and the reliability of the aircraft is improved. And performing risk degree grading according to the updated comprehensive risk degree index and the detection threshold value, performing reliability grading according to the updated comprehensive reliability index, and generating grading alarm information and comprehensive decision suggestions according to the two results.

The invention discloses an image restoration method, system and device, a medium and a product, and belongs to the field of power grids, and the method comprises the steps: obtaining a to-be-restored image of a power scene under an extreme weather condition, inputting the to-be-restored image to an image restoration model, and obtaining a target image, the image restoration model is obtained by guiding an initial restoration model under a semi-supervised framework through an evaluation model to carry out iterative training, in each iteration, the label-free data is input into the first restoration model to obtain a restoration result, the restoration result is input into the evaluation model to carry out quality evaluation to obtain an evaluation signal, and the evaluation signal is sent to the semi-supervised framework; dynamically adjusting model parameters of a current second repair model based on the evaluation signal to guide the current second repair model to learn key features of the power equipment under extreme weather conditions, the evaluation model being obtained by performing all-parameter supervision fine tuning training on a multi-modal large language model based on power scene data; therefore, the generalization ability and the repairing effect of the repairing model can be improved by implementing the method and the device.

The invention belongs to the technical field of engineering management, and provides a decoration supervision service quality optimization method and system based on eight-dimensional feature evaluation, and the method comprises the steps: collecting multi-source heterogeneous data related to supervision service through a distributed data processing platform, carrying out the integrated preprocessing and deep fusion of the multi-source heterogeneous data, and carrying out the optimization of the quality of decoration supervision service. Outputting an eight-dimensional feature vector based on a depth feature engineering framework, generating an evaluation report through causal reasoning, generating an improvement suggestion according to an evaluation result, performing real-time updating, pushing the evaluation result and the improvement suggestion to a supervisor through a mobile terminal, tracking an improvement progress, and forming closed-loop management. According to the invention, the supervision personnel are evaluated from eight dimensions including supervision efficiency, service quality and satisfaction, and supervision human efficiency, core influence factors of each dimension are accurately found out, evaluation and improvement directions are output, the supervision personnel are supervised and promoted to learn and promote through the mobile terminal, a professional high-efficiency service team is established, and the efficiency of the supervision personnel is improved. And new development opportunities and revolution power are brought to the decoration industry.

The invention relates to the technical field of laser radar data real-time processing, in particular to an airborne laser radar data real-time processing platform based on cloud computing. The platform comprises a point cloud data blocking module, a point cloud data screening module and an end cloud fusion calculation module, wherein the point cloud data blocking module realizes dynamic blocking through flight state driving basic setting and point cloud characteristic driving optimization; the screening module constructs a two-dimensional feature evaluation system, divides the point cloud into a local core feature anchor point set Q1 and a cloud auxiliary modeling redundant point set Q2, and dynamically adapts to a screening ratio; and the end-cloud fusion module corrects the deviation of the cloud preliminary model through Q1, embeds local details, and realizes local dynamic update in combination with incremental data. The platform can solve the problems of time delay, resource adaptation and privacy security of airborne laser radar data processing, and is suitable for emergency monitoring, conventional inspection and other scenes.

The invention belongs to the field of intelligent medical treatment. The invention provides a two-channel feature screening method for cognitive impairment recognition modeling and a modeling method thereof, and the method comprises the steps: taking multi-site cognitive impairment screening data as input data, and carrying out the preprocessing of the input data; constructing a traditional robust feature screening channel and an LLM knowledge enhancement screening channel, and performing feature screening on the preprocessed input data; integrating dual-channel feature screening results, performing bias perception joint score optimization, and obtaining a feature set; and performing semantic alignment and version normalization on the feature set to obtain a high-quality feature set. And applying the high-quality feature set to a classifier for cognitive impairment recognition modeling, and generating a clinical decision support result. According to the parallel feature screening method based on combination of a large language model and traditional feature screening, the problem of data heterogeneity bias in cognitive impairment recognition is systematically solved by constructing a dual-channel collaborative feature evaluation architecture, and organic unification of statistical robustness and clinical interpretability is achieved.