143results about How to "Accurate classification" patented technology

The invention provides a target identification method and system based on multi-source information fusion, and relates to the technical field of low-altitude target detection. The method comprises the following steps: acquiring target radar track data, interception equipment track data and position area information data; based on target radar track data, extracting a first feature in an RCS form dimension, and extracting a second feature in a motion dimension; based on the target radar track data and the track data of the monitoring equipment, determining a frequency spectrum monitoring correlation factor and regional position information features; performing feature fusion on the first feature, the second feature, the spectrum interception correlation factor and the regional position information feature to obtain a target feature, and identifying a target type; and identifying a target threat level based on the target type and the target radar track data. The method and the device are used in a target identification process based on multi-source information fusion, and the technical problem that the target threat degree cannot be accurately identified in a complex environment in the prior art is solved.

The invention provides a plant disease feature extraction and classification method and system based on deep learning, and relates to the technical field of plant disease identification, and the method comprises the steps: mining the interdependence rule of different disease features through constructing a disease feature symbiosis wake-up network, and setting wake-up conditions; inputting a to-be-analyzed plant disease image into the network, capturing initial disease features, triggering associated feature wakeup, and generating a disease feature symbiotic set; conducting the characteristic information according to the hierarchical relationship to generate enhanced symbiotic disease characteristics; recording morphological change details to construct a disease characteristic evolution sequence; and inputting the disease characteristic evolution sequence into a pre-trained deep learning classification model, analyzing disease essential characteristics, and generating a classification result containing a disease type and a matching basis. The method can comprehensively and accurately extract features, and improves the accuracy and reliability of plant disease classification.

The application belongs to the technical field of optical lens detection, and particularly relates to an optical lens appearance defect detection device, which comprises a supporting assembly, a feeding device is installed on the supporting assembly, a first discharging slide plate is installed at the discharging end of the feeding device, a mounting seat is fixedly connected to the supporting assembly below the first discharging slide plate, supporting rollers are rotationally connected to both ends of the mounting seat, and the cooperation of the structures such as the belt ring, the first visual defect detection camera, the pushing cylinder, the guide plate and the driving roller is achieved, so that after the optical lens is accurately positioned in the positioning groove formed in the belt ring, the first visual defect detection camera arranged on both sides is used to detect the end of the optical lens, then the pushing cylinder is used to push the optical lens to the driving roller, the driving roller is rotated to drive the optical lens to slowly rotate, the second visual defect detection camera is used to detect the circumferential side of the optical lens, and the mechanical hand is not needed to be used for carrying and aligning, so that the detection efficiency is greatly improved.

Embodiments of the present application provide a method, device, medium, equipment and product for classifying wine samples, relating to the technical field of artificial intelligence. The method comprises: contacting odor molecules of a wine sample with at least one recombinant cell expressing an olfactory receptor and a reporter protein, the reporter protein generating a detectable signal after the receptor binds to the odor molecules; obtaining time series data of the signal, calculating the maximum value and baseline value thereof, and determining a response characteristic value of each olfactory receptor according to the same; and inputting the characteristic value into a trained machine learning model to obtain a wine sample classification result. The present method accurately extracts a stable characteristic value of the response of an olfactory receptor to a wine sample, thereby eliminating interference caused by initial value fluctuations and improving the accuracy of model classification.

This invention discloses a method, apparatus, electronic device, and storage medium for classifying license plate images. The method includes: in response to an image classification instruction for a target license plate image, determining image feature data of the target license plate image; inputting the image feature data into a pre-trained license plate classification model; and outputting an execution result for classifying the target license plate image, the execution result including at least two classification items and the probability of each classification item, wherein the at least two classification items are distributed in a tree-like structure. The technical solution of this invention achieves more accurate classification of license plate images, and the classification process is interpretable.

The application provides a kind of underwater structure apparent disease identification method and system based on deep learning, wherein, method includes: according to the combination of fusion model and target recognition model, generate the pre-set underwater structure apparent disease identification model;Underwater apparent disease is identified by the pre-set underwater structure apparent disease identification model;The fusion model is built by improved CycleGAN model and multi-scale Retinex algorithm (MSR) network, for converting underwater image into clear and clear image with obvious features;The target recognition model is obtained by YOLOv5 model, for realizing the positioning and classification of underwater structure apparent disease.The present application solves the problems of inaccurate classification and low recognition accuracy of underwater structure apparent disease by the underwater structure apparent disease identification model, caused by factors such as camera imaging blur, insufficient contrast, dispersion and noise in complex water area.

The application provides a die cutting and hot stamping equipment intelligent state monitoring and fault diagnosis system and method, and relates to the field of intelligent monitoring.The method comprises the following steps: collecting working parameters of multiple key parts of the die cutting and hot stamping equipment, constructing a time sequence collection window, slidingly collecting the working parameters, and obtaining characteristic information reflecting the equipment state; based on the characteristic information, constructing an anomaly detection model, performing anomaly detection on the equipment state, obtaining an anomaly score, and judging whether the equipment state is abnormal according to the anomaly score; for the characteristic information judged as abnormal, constructing a fault diagnosis model based on the fault type to which the characteristic information belongs, performing fault diagnosis on the equipment state, and generating a diagnosis result; and generating a comprehensive diagnosis and operation and maintenance decision report according to the diagnosis result.The application realizes comprehensive perception of the internal state of a closed host through multi-sensor collaborative monitoring and dynamic time sequence collection, breaks through the limitations of traditional monitoring, and provides accurate data basis for early fault warning and predictive maintenance.

The application discloses a voltage sag identification method based on a triple tuple prototype network under a small sample, and belongs to the technical field of power quality analysis. The method uses a triple tuple feature extractor, a large number of voltage sag triple tuples are constructed, and effective sag features can be extracted by the model under the condition of a small number of training samples. Then, in view of the problem that some voltage sag features are similar and easy to confuse, an efficient channel attention mechanism is integrated into the triple tuple feature extractor, cross-channel feature interaction information is captured under the condition of only a small number of parameters, the model can pay attention to the key feature area, a prototype classifier is finally constructed, representative class prototypes are learned for each class by using the extracted sag features, and the final sample class is determined by comparing the similarity between sample features and class prototypes. Under the condition of limited sample data, the method can realize accurate voltage sag classification effect, and has strong practical application significance.

The invention discloses an uplink service message identification processing method and device, a terminal and a medium. The method comprises the following steps: acquiring core feature information corresponding to an uplink service message; obtaining a target message core data structural body according to the core feature information; obtaining a PDU session identifier corresponding to an uplink service message based on the target message core data structure body; obtaining a QoS flow identifier based on the PDU session identifier and the target message core data structure body; based on the QoS flow identifier, obtaining an uplink service message after scheduling processing; performing query processing on the QoS flow identifier to obtain a target packet data convergence protocol instance; and completing a QoS identification processing flow of the uplink service message based on the target packet data convergence protocol instance. The invention aims to realize rapid QoS identification, classification and processing of the uplink service message, improve the message processing efficiency and accuracy, and reduce the system resource overhead.

The application discloses a cross-natural language code retrieval model training method, a cross-natural language code retrieval method, a device, equipment and a medium, and relates to the technical field of artificial intelligence and software engineering. The cross-natural language code retrieval model training method comprises the following steps: obtaining an original corpus database, and constructing training data according to the original corpus database; performing confusion and inversion on main language codes to obtain main language code samples, wherein the main language code samples comprise main language code positive samples and main language code negative samples; and training an initial model through a gradient inversion layer according to the training data and the main language code samples to obtain a target model. According to the application, the natural language-specific "fingerprint" features in the codes can be removed, the embedding space alignment direction can be unified, the sampling distribution deviation in the training process can be reduced, and the consistency and generalization capability of cross-language code retrieval can be improved.

The invention relates to the technical field of risk assessment of diabetic patients, in particular to a risk assessment method and system for diabetic patients. The eye fundus image containing local defects is directly processed through the trained lesion risk assessment model, lesion risk assessment is carried out on the decoupled lesion feature vector, and the preprocessing step of carrying out manual or algorithm restoration on the defect image is omitted, so that distortion errors possibly introduced in the restoration process are avoided, the assessment efficiency is improved, and the method is suitable for popularization and application. By constructing a feature decoupling network and constructing a total loss function including comparison loss, independence constraint loss and classification loss, the model is forced to learn pure lesion feature vectors, lesion information is ensured to be effectively separated from imaging quality information, and the defect that a traditional model excessively depends on image integrity is overcome; the technical problem that the risk assessment effect of most existing DR risk assessment models based on deep learning is poor when a repaired complete eye fundus image is input is solved.

The utility model relates to a landfill garbage classification device, which relates to the technical field of garbage classification treatment, and comprises a winnowing cavity, a crushing box is arranged at the input end of the winnowing cavity, a crushing mechanism for crushing a packaging film is arranged in the crushing box, and the packaging film on the surface of garbage is cut and packaged by using a crushing serrated knife. The garbage in the garbage bag is fully released, so that more accurate classification of the garbage is realized; a draught fan is installed at the position of an air inlet in the front end of the winnowing cavity, a plurality of classification openings are sequentially formed in the bottom of the winnowing cavity in the output direction of the draught fan, the spoilers are obliquely arranged towards the classification openings, garbage is divided into heavy materials and light materials through winnowing and classified, and a cyclone separator for separating packaging films is installed at the position of an air outlet in the tail end of the winnowing cavity. And the cyclone separator is used for separating and recycling the packaging film fragments crushed by the crushing mechanism and doped in the airflow.

The invention discloses a quantum classical mixed image classification method based on group isovariant and delayed aggregation. The method comprises the following steps: lifting a convolution module, inputting a target image, initializing a convolution kernel and rotating the convolution kernel, and carrying out convolution and stacking on the target image to obtain an output image; the group convolution module is used for converting the output image of the convolution module into an image sample and carrying out convolution and reverse remodeling operation to obtain an output image; the group pooling and flattening module is used for carrying out adaptive average pooling on an output image of the group convolution module, compressing the output image into a feature vector and obtaining an output feature vector; the group equivariant quantum feature processing module encodes the feature vectors to quantum bits according to the feature vectors output by the group pooling and flattening module; and the delay aggregation and output module measures the quantum bits, aggregates and classifies measurement results, and completes classification of target images. The method provided by the invention has strong nonlinear feature fusion capability, and can realize more accurate image classification.

The invention discloses a rock slice image classification method based on domain self-adaption, and the method comprises the steps: collecting rock slice image data, the method comprises the following steps: acquiring a rock slice image, performing multi-scale data preprocessing and geological field data enhancement, extracting multi-level visual features of the rock slice image by utilizing a pre-trained DINOv3 model, performing field specialized adaptation on general visual features through a geological field adaptive Adapter module, and enhancing rock slice discriminative feature representation by adopting a double-path attention mechanism. Constructing a progressive hierarchical classification head to realize coarse-to-fine rock classification; and designing a multi-stage progressive training strategy to optimize the overall performance of the model. According to the method, mineral composition and structural features of the rock slices under different scales can be accurately captured, and multi-scale features and an attention mechanism are fully utilized, so that accurate classification of the rock slices is realized, and the accuracy and reliability of rock slice identification are remarkably improved.

The application provides a ship type classification prediction method and system based on K-means and XG-Boost, acquires ship data and carries out pretreatment, then adopts a K-means clustering algorithm to respectively cluster each kind of data in the pretreated ship data to obtain multiple clusters, calculates error sum of squares of all data in each cluster, calculates the classification number of each kind of data according to the error sum of squares, selects a certain classification number by using an elbow method, marks the ship type of all clustered ships according to the classification number, then takes the ships with marked ship types as training set samples, adopts an XG-Boost classification algorithm to train the training set samples to obtain multiple classification prediction models, verifies the multiple classification prediction models to obtain an optimal classification prediction model, and predicts the ship types of all ships in the world according to the optimal classification prediction model and marks the ship types. The application can accurately classify all ships in the world, and can avoid overfitting and underfitting of the model while ensuring the accuracy.

This invention discloses a method for identifying unipolar and bipolar depression based on deep learning-based multi-state EEG fusion, comprising: Step 1, performing continuous wavelet transform on EEG signals in open and closed states respectively to obtain open-eye time-frequency maps and closed-eye time-frequency maps; Step 2, using a deep learning model to extract features from the open-eye and closed-eye time-frequency maps obtained in Step 1 to obtain feature vectors for open-eye and closed-eye states; then, fusing the feature vectors in open-eye and closed-eye states to obtain a multi-state fused feature vector; finally, using a deep learning classification network to classify and identify the multi-state fused feature vector to obtain the identification result, thus completing the identification. This invention uses a deep learning model based on EEG signals to perform three-class classification identification of unipolar depression, bipolar disorder, and healthy individuals, improving classification performance.

The application provides a cabin adjustment method, device, equipment, medium and program. It relates to the technical field of cabin adjustment. The method comprises the following steps: acquiring video data and pressure data of passengers in a vehicle within a preset time length; performing feature extraction on each frame of image in the video data to obtain a target seat of a child among the passengers, a head posture, a facial expression and a continuous closed-eye time length; obtaining a pressure sum, a pressure center and a pressure change of the child based on the target seat and the pressure data; performing weighted processing on the head posture, the facial expression and the continuous closed-eye time length, the pressure sum, the pressure center and the pressure change according to a fusion weight to obtain fusion data of the child; taking the fusion data as an input of a state estimation model to obtain a child state corresponding to the child; and adjusting the cabin of the vehicle to a state conforming to the child state according to the child state and a preset cabin adjustment rule. The application achieves the effect of improving the safety and comfort of the child during the ride.

This invention relates to the field of ore identification technology, specifically to a method and system for preliminary identification of the quality of rare metal coal-bearing ores in the field. The method includes the following steps: collecting ore samples and acquiring main peak, structural, and infrared images; extracting image features to generate mutation numbers; analyzing sampling coordinates to reconstruct the connectivity structure; drawing closed boundaries to determine coordinate attribution; and outputting an ore quality identification scheme. In this invention, by uniformly numbering and temporally binding the acquisition results of main peak reflection, microscopic layers, and infrared spectrum bands, a synchronous correspondence between multi-source images is established. By combining offset trajectories and structural features to identify continuously changing nodes and abrupt change regions, spatially concentrated patches are generated using numbering and coordinate mapping, and the connectivity structure is reconstructed. Closed boundaries are drawn based on trajectories to form the basis for regional classification. The direction of quality change is verified through image sequence coherence, and labeled identification results are output, achieving rapid positioning and accurate classification of field ore samples.

The application provides a kind of geological disaster post-vegetation recovery monitoring method based on high-resolution remote sensing image, comprising: constructing fusion type "spectrum-vegetation index-texture" feature set;In sunny weather conditions, more evenly select n typical vegetation samples in the target area;Construct bagging type ensemble learning model;Analysis of the obvious differences of arbor, shrub and herbaceous vegetation in vegetation height, single plant vegetation horizontal projection coverage area, root depth and root extension range;By analyzing the vegetation change rate index and vegetation type change rate index of several continuous time phase remote sensing images according to the time phase change information, the vegetation recovery of the target area is quantitatively analyzed, so as to effectively improve the accuracy of pixel classification method, greatly improve the accuracy of quantitative analysis of vegetation in the target area, and greatly reduce the cost of long-term accurate monitoring.

The invention belongs to the technical field of smart city information, and particularly relates to a multi-scene adaptive communication protocol software system and an optimization method. And the whole process of communication protocol adaptation, data transmission and abnormity management and control is covered. Core algorithms such as protocol adaptation modeling, data transmission optimization and abnormal management and control early warning are adopted, the technical bottlenecks of'heavy transmission and light adaptation, heavy rate and light reliability, and heavy response and light pre-judgment 'of a traditional communication protocol software system are broken through, and adaptive adaptation, high-reliability and low-delay data transmission and full-process abnormal real-time management and control of communication protocols under multiple scenes are achieved. The adaptability, reliability and stability of a communication protocol software system are remarkably improved, deep fusion of communication protocol software and multi-scene application is promoted, and a brand new intelligent communication solution is provided for the fields of industrial communication, the Internet of Things, intelligent terminals and the like.

The invention relates to the technical field of nondestructive testing, in particular to a copper bar coating lower substrate defect nondestructive testing device based on terahertz waves, which comprises a terahertz scanning acquisition module used for controlling a transmitting and receiving unit to perform two-dimensional scanning so as to acquire an original waveform; the flight time dynamic correction module is used for resolving the local coating thickness and carrying out dynamic time axis alignment; the substrate roughness deconvolution module is used for calling the reference model to carry out deconvolution filtering so as to strip background scattering noise; the interface dielectric feature analysis module is used for extracting a dielectric feature vector reflecting an interface dielectric constant mutation state; the defect risk assessment imaging module is used for constructing a three-dimensional chromatography map and outputting a detection result; according to the method, the physical characteristic decoupling of the signal source is realized, the coating thickness fluctuation and the real defect are effectively distinguished, the misjudgment rate is obviously reduced, and the evaluation accuracy is ensured.

The invention discloses a thread hole type identification method, device and system and machining equipment, and belongs to the field of machining. After the target complete circle on the to-be-detected part is obtained, the target bolt diameter corresponding to the preset bottom hole diameter is obtained based on the parameter table; constructing a theoretical cylinder at the position of the target complete circle; the theoretical cylinder and the to-be-detected part are differenced to obtain a target entity, and the type of the surface of the target entity is a cylindrical surface; if the target entity with the diameter being the diameter of the target bolt exists, the thread hole type of the position where the theoretical cylinder is located is determined to be the target type. According to the scheme, two parameters of the bottom hole diameter and the bolt diameter are actually adopted to identify the thread hole. Even if the thread hole is a non-standard geometry, the thread hole can be accurately identified and classified, and the identification efficiency and the automation level are greatly improved.

This application discloses a method, apparatus, device, storage medium, and program product for classifying complaint work orders, aiming to solve the problems of low processing efficiency, insufficient classification accuracy, and high labor costs caused by the reliance on manual classification of complaint work orders. The method includes: acquiring user complaint text data; inputting the complaint text data into a trained work order classification model, and outputting the classification result of the complaint text data; wherein the work order classification model includes at least a feature extraction layer, an attention layer, and a classification layer; the feature extraction layer is used to extract text features at least two scales from the complaint text data, and fuse the text features at least two scales to obtain fused features; the attention layer is used to assign weights to features corresponding to different words in the fused features to obtain weighted features that reflect the differences in word importance in the complaint text data; the classification layer is used to output the classification result based on the weighted features.

The application discloses an open set cross-network node classification method and device, relates to the field of machine learning, and designs a framework of separating first and then adapting to a domain. First, an unknown class and a known class are separated by constructing a rough boundary through adversarial learning, and then a pseudo label is allocated to iteratively train a model in a self-training manner, so that a more accurate boundary is gradually generated for separating the known class and the unknown class. Secondly, in the domain adaptation stage, a negative domain adaptation coefficient is allocated to the nodes of the unknown class, and a positive domain adaptation coefficient is allocated to the nodes of the known class, so that the nodes of the known class of the target network are aligned with the source network, and the nodes of the unknown class of the target network are pushed away from the source network, thereby realizing the adversarial domain alignment excluding the unknown class, and further realizing the classification of the open set cross-network node with high accuracy.

The invention relates to the technical field of security communication protocols of the Internet of Things, in particular to an automatic protocol identification method used in an environment of the Internet of Things, which comprises the following steps of: acquiring a difference value between a message index and frequency, aggregating a field section to generate a group number, matching a structure offset to calculate a fluctuation quantity, and identifying a period hopping field to output an identification result. According to the method, the distribution characteristics and the structure change trend of byte sections can be effectively described by performing difference analysis on repetition frequency and density change of each byte position in a communication message and establishing a field aggregation relationship, and the structure stability and drift fields in the message are extracted and the offset amplitude of the fields is quantized, so that the communication efficiency is improved. A message structure consistency judgment mechanism is established, a comprehensive evaluation mode of periodic change and structure stability is formed in combination with analysis of a periodic field byte change range and frequency hopping frequency, and field position mapping and periodic characteristics of a newly received message are subjected to matching judgment, so that a message structure consistency judgment result is obtained. Accurate classification and efficient identification of the dynamic change communication data are realized.

The invention discloses an image enhancement method and system for an intelligent network connection automobile test scene, and the method comprises the following steps: S1, obtaining original image data in the intelligent network connection automobile test scene, and carrying out the preprocessing of the original image data; s2, constructing a scene feature recognition model, performing scene dynamic feature extraction on the preprocessed image data, and determining environment category parameters of a current test scene; and S3, based on the environment category parameters, calling a corresponding scene adaptive enhancement strategy library. The invention relates to the technical field of intelligent network connection automobile testing. According to the image enhancement method and system for the intelligent networked automobile test scene, a multi-index image quality evaluation system is established, the system comprises the peak signal-to-noise ratio (PSNR), the structural similarity (SSIM) and the information entropy, quantitative evaluation is carried out after enhancement each time, enhancement parameters are automatically adjusted by taking the evaluation result as a feedback signal, a closed-loop iterative optimization process is formed, and the image enhancement efficiency is improved. And the output image is ensured to meet the quality threshold requirement.

This invention provides an intelligent CNC hydraulic system and control method, including a sensing and monitoring unit comprising a multi-source heterogeneous sensor network deployed at key nodes throughout the system. The invention is rationally designed, using a multi-source heterogeneous sensor network deployed throughout the system to simultaneously collect multi-dimensional operating parameters such as pressure, flow rate, temperature, and vibration. Edge computing is used to complete data preprocessing and fault-sensitive feature extraction. Relying on an SVM-LSTM dual-model fusion fault intelligent diagnosis module and integrating a fault tree FTA analysis submodule, it achieves accurate classification of fault types, rapid location of fault points, and root cause tracing. It also provides early warning of early system faults, significantly improving fault diagnosis accuracy compared to traditional threshold alarm methods. Furthermore, it can identify fault types that traditional methods cannot detect, such as directional valve sticking, predicting fault development trends in advance and effectively preventing equipment damage caused by fault escalation.

This utility model discloses a cable fault location and detection device based on EEMD, relating to the field of underground cable monitoring technology. The EEMD-based cable fault location and detection device includes a Hall effect sensor, a signal amplification circuit, an ADC analog-to-digital converter module, a DSP chip, an EEMD processing unit, a classification model, and a display screen 112. The Hall effect sensor detects magnetic field signals; its output is electrically connected to the input of the signal amplification circuit. The output of the signal amplification circuit is electrically connected to the input of the ADC analog-to-digital converter module, and the output of the ADC module is electrically connected to the input of the DSP chip. The signal amplification circuit and the ADC module amplify and process the magnetic field signal, respectively, and convert the magnetic field signal into a digital signal. The output of the DSP chip is electrically connected to the input of the EEMD processing unit, and the DSP chip is used to preprocess the magnetic field signal. This EEMD-based cable fault location and detection device can determine the fault type and accurately locate the fault point.

This invention proposes a cybersecurity knowledge question-answering method based on a large language model, comprising the following steps: S1, collecting cybersecurity data to construct a cybersecurity knowledge corpus and preprocessing it to obtain a standardized cybersecurity knowledge corpus; S2, using a cybersecurity-specific Prompt template to fine-tune the pre-trained large language model to generate a cybersecurity large language model; S3, receiving user cybersecurity question-answering requests, and after word segmentation, entity recognition, and intent parsing, obtaining standardized question-answering requests, further inputting them into the cybersecurity large language model, which calls the standardized cybersecurity knowledge corpus, and generates preliminary question-answering results through semantic understanding and reasoning; S4, calling the standardized cybersecurity knowledge corpus to perform consistency verification on the preliminary question-answering results, if consistent, using it as the final result, otherwise corrected by the cybersecurity large language model to obtain the final result.

The invention relates to the technical field of motor control, and discloses an electrical transmission system parameter self-tuning system based on a neural network, and the system comprises a state monitoring and gating module which is used for activating the system when the high-frequency energy characteristic of a torque instruction exceeds a threshold value; the homomorphic mapping and reference reconstruction module is used for constructing a homomorphic digital filter to convert a torque instruction into a homomorphic instruction aligned with a feedback speed time sequence; the momentum residual calculation module is used for calculating the difference value between the theoretical impulse and the actual momentum increment based on the momentum theorem; the morphological decoupling and reasoning module is used for calculating morphological similarity between the residual vector and the reference vector by using the neuron structure so as to output confidence; and the parameter updating module is used for adjusting the adaptive updating gain according to the confidence coefficient and iteratively correcting the inertia parameter. According to the method, through signal homomorphic reconstruction and waveform form reasoning, the influence of loop delay and load disturbance is effectively inhibited, and the accuracy and robustness of parameter setting are improved.