220 results about "Pattern identification" patented technology

The application provides a method and system for detecting camouflaged targets by unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs). The system ensures the synchronization of UAVs and UGVs through the global positioning system (GPS), and uses the infrared cameras, binocular cameras, and radar sensors carried by both to efficiently collect data in the target area. The system further preprocesses and analyzes the collected data, and uses improved SSD algorithms and pattern recognition techniques to identify potential camouflaged targets, and performs pattern matching and information fusion to improve the accuracy of the identification results. The SE attention module is introduced innovatively, which optimizes the feature fusion process, enhances the network's spatial correlation capture ability, and enables the system to use global information more effectively, improving the detection accuracy of camouflaged targets. The application solves the problem of poor reliability in traditional methods for detecting camouflaged targets, improves the real-time performance and effectiveness of the cooperative operation of UAVs and UGVs, and significantly improves the accuracy and response speed of camouflaged target identification in battlefield environments. It has important theoretical value and application prospect in various military crisis response.

A diagnostic system for communication behavior is provided. The diagnostic system includes a wireless device configured to communicate with an intranet, and a diagnostic device. The diagnostic device includes a data receiving module, a pattern identification module, an event detection module, and a processing module. The data receiving module is configured to receive at least one log data from the wireless device. The pattern identification module is configured to receive the log data and identify whether the log data has at least one key pattern of data. The event detection module is configured to obtain an event corresponding to the key pattern of data. The event represents a communication behavior of the wireless device. The processing module is configured to perform a specific operation corresponding to the event.

This application relates to the field of computer vision and image processing technology, and discloses a large-model pattern recognition method and system based on deep learning. The method includes: acquiring a temporal image sequence containing a target to be recognized; extracting the geometric topological features of the target in each frame of the image; tracking the target across frames to obtain a temporal numerical set of geometric topological features evolving over time; statistically analyzing the fluctuation parameters of the temporal numerical set within a preset temporal interval, and selecting geometric topological features that meet preset stability conditions from the fluctuation parameters as the essential features of the target; constructing a target pattern representation based on the essential features of the target, and matching the target pattern representation with a pre-stored pattern to determine the recognition result. This application significantly improves the robustness and generalization ability of the recognition model in complex dynamic scenarios such as material changes, illumination changes, pose changes, and even the emergence of new categories, effectively reducing the false positive rate and false negative rate.

The present application relates to the technical field of additive manufacturing online monitoring and closed-loop control, in particular to a 3D printing workpiece defect identification system based on image detection; containing coaxial acquisition, potential mapping, diffusion analysis, singular point extraction and bidirectional feedback module; the system converts the collected image stream into a virtual flow velocity vector field; the core is to simulate the evolution of the physical field by using the virtual viscosity diffusion algorithm, calculate the difference of the vector field before and after diffusion to extract the topological mutation, and generate a defect potential thermal map; based on the potential value of the thermal map, the system performs bidirectional feedback of generating G code intervention instructions and adjusting the virtual viscosity coefficient; the present application reduces the pattern recognition to local physical field simulation, without sample training, and realizes millisecond-level real-time response.

This invention discloses a weakly supervised semantic segmentation method and system for remote sensing images based on adversarial background interference, belonging to the fields of pattern recognition and machine learning. The method includes: First, prototyping a background prototype mining approach. By constructing a pure background prototype library and calculating pixel-level similarity, a background mask is generated to suppress false activations of interfering backgrounds from a priori level. Second, foreground-background decoupling is designed. A contrastive loss based on prediction entropy weighting is introduced, driving the model to aggregate background features and move away from foreground features in the feature space, enhancing semantic discriminative power. Finally, a pseudo-label optimization strategy is employed. Through hole filling and dual-threshold screening, the structural integrity of pseudo-labels is repaired and noise is filtered, providing high-quality supervisory signals. This method aims to solve the technical problems in existing weakly supervised semantic segmentation of remote sensing images, where severe background interference leads to high pseudo-label noise and incomplete foreground target segmentation.

This invention relates to the field of marine information and pattern recognition technology, and discloses a method for automatic tracking and feature parameter extraction of ocean temperature fronts. The method includes: acquiring and preprocessing continuous sea surface temperature remote sensing data; constructing an adaptive multi-scale temperature gradient tensor field; automatically identifying initial seed points using a joint criterion of local extremum response and global structural saliency; generating a preliminary front through bidirectional chain growth along the main gradient direction; optimizing the front trajectory by fusing ocean dynamics priors and spatiotemporal continuity constraints; and finally extracting feature parameters such as position, intensity, direction, curvature, and lifespan. Through the above technical solution, this invention achieves fully automatic and highly robust temperature front tracking and accurate parameter extraction, significantly improving cross-scenario generalization capabilities and operational application value.

The application provides a kind of intelligent pathological section label identification method, system and medium, the method includes: receiving the input image of pathological section label, based on the identification mode of pre-set identification mode, the image format corresponding to input image and OCR type configuration string are identified;Call identification mode to execute identification operation to input image, analyze whether the identification result is valid;If the identification result is valid, then based on the identification mode of pre-set identification mode, the identification result is output;If the identification result is invalid, then switch identification mode, secondary identification is carried out to input image, until the identification result is valid, improve the identification efficiency of intelligent pathological section label;Wherein the priority strategy under automatic mode and intelligent back mechanism, combined with image enhancement technology, ensure the normal operation of system under the condition of multiple angles, low definition, information loss etc. Efficient identification of OCR and two-dimensional code is realized through multi-strategy joint identification mechanism.

The present application belongs to the technical field of pattern recognition and intelligent agriculture, and particularly relates to a crop disease and pest intelligent identification and crop condition perception method. The method first collects crop environment and image data through a multi-source perception network, extracts features using a physical information neural network, and introduces a physiological constraint operator containing a transpiration model and a chlorophyll fluorescence decay parameter therein. At the same time, micro-meteorological parameters are injected into the network as weight correction factors to establish the coupling relationship between environmental factors and physiological characteristics, so as to realize decoupling identification of physiological adversity and pathological infection. Finally, state evaluation is carried out in combination with a physiological adversity formula, and the identification result and crop condition report are output. The present application uses physical laws to decouple the identification logic, accurately distinguishes adversity and infection with similar visual forms, reduces the dependence on sample size, and improves the accuracy and robustness of crop condition monitoring in complex environments.

The invention discloses a PCIe link state monitoring system and a monitoring method thereof. The PCIe link state monitoring system comprises a PCIe monitoring subsystem, a PCIe controller subsystem and a PHY (Physical Layer) module, wherein the PCIe controller subsystem and the PHY module are connected through a PIPE interface, and the PCIe monitoring subsystem is used for monitoring state information of a PCIe link; four levels of leaky bucket modules are integrated on the same layer of the PCIe monitoring subsystem, and the four levels of leaky bucket modules are used for dropping correctable error information in the state information of the PCIe link into leaky buckets, carrying out overflow counting to obtain leaky bucket overflow times, carrying out error pattern recognition according to the leaky bucket overflow times and preset different execution thresholds, and outputting the error pattern recognition result. Link recovery is carried out by adopting a progressive link recovery strategy; therefore, extra special equipment does not need to be introduced into the PCIe link, the observability of the PCIe link can be improved, and correctable errors caused by the signal integrity problem on the link can be analyzed and diagnosed in real time, so that a corresponding link recovery strategy is adopted.

This invention discloses a novel intelligent rapid screening device for depression / Alzheimer's disease, used for early auxiliary detection of either condition. It comprises: an EEG acquisition module, a human-computer interaction module, a wireless transmission module, and an intelligent analysis module. The EEG acquisition module collects resting-state and task-oriented EEG signals from the subject. The human-computer interaction module selects the screening mode, inputs subject information, performs impedance detection, signal verification, and provides task guidance. The wireless transmission module enables data transmission between the modules. The intelligent analysis module receives the EEG signals, analyzes the data using a machine learning model, and outputs the screening results. This device uses dry electrode technology, eliminating the need for conductive adhesive. The brain-computer interface is made of skin-friendly material for comfortable wear. Wireless transmission and cloud analysis provide high flexibility. AI-based data analysis and pattern recognition improve diagnostic efficiency and accuracy.

The present application relates to the technical field of biological information data processing, in particular to a kind of arthritis data processing method and system based on ceRNA-network analysis, comprising the following steps: obtaining arthritis sample RNA data and target annotation, extract shared element screening regulation pair, by pathological pathway enrichment and function verification, measure correlation to determine priority, integrate ceRNA network structure to evaluate regulatory influence, parse node role to adjust centrality, generate specific core hub node identification atlas.In the present application, by introducing dynamic transcription consistency pattern recognition and transcription correlation and target co-annotation relationship joint comparison, the accuracy of arthritis data analysis is improved, the evaluation of candidate regulatory pair is strengthened, the result reliability and regulatory confidence level are improved, combined with ceRNA network node regulatory influence evaluation, the identification ability of key node is enhanced, effectively solve the blind spot of traditional method, ensure the accurate identification of arthritis specific core hub node.

This invention discloses an open-set radar interference pattern recognition method, apparatus, and electronic device. The method includes: matched filtering of the radar received signal to construct a dual-modal input of a one-dimensional range sequence and a two-dimensional time-frequency matrix; feature extraction via a dual-branch network and adaptive fusion based on cosine similarity; introducing cross-modal consistency regularization during the training phase, constructing pseudo-unknown samples by shuffling intra-batch modes, and combining energy constraint loss to compress the energy of known classes and increase the energy of unknown classes to form a clear decision boundary; and adaptively setting a threshold based on the energy distribution of the validation set during the inference phase to achieve accurate identification of known interference and effective rejection of unknown interference. This invention overcomes the performance degradation defects of traditional closed-set methods in the face of unknown interference, and improves the generalization ability, robustness, and engineering practicality of radar interference recognition in complex electromagnetic environments.

The application relates to the technical field of information technology of construction engineering, and particularly discloses a bidding document review auxiliary method and system based on artificial intelligence, which comprises bidding document preprocessing, technical specification similarity analysis, commercial specification consistency analysis and analysis result collection. The scheme establishes an objective quantitative evaluation system based on the combination of TF-IDF statistical characteristics and pre-training word vector semantic characteristics, provides accurate numerical similarity scores, enhances the robustness of technical specification text content detection through deep semantic understanding, realizes integrated data analysis through a unified numerical extraction framework, can find cross-table type correlation abnormalities, adopts adaptive extraction technology based on numerical pattern recognition, constructs a multi-dimensional abnormal pattern recognition system, effectively detects bid-rigging behavior among bidders, introduces feature contribution degree analysis and abnormal pattern recognition mechanism, and greatly improves the reliability of analysis results.

The application discloses a kind of dual paradigm combined remote sensing image end-to-end fine-grained target detection method, it is related to computer vision and pattern recognition technical field, including: extracting multi-scale feature map by feature extraction network;Based on sparse directional proposal network, using one-to-one sparse matching strategy, generate no duplicate sparse directional region proposal and its corresponding proposal feature and coarse-grained target confidence;Based on query perception refinement head, using one-to-many dense matching strategy, obtain fine-grained classification probability and refined bounding box;In the training stage, introduce double auxiliary supervision head to provide additional dense supervision signal;In inference stage, adopt two-stage consensus scoring mechanism, finally obtain fine-grained target detection result.The method realizes the end-to-end remote sensing image fine-grained target detection without NMS dependence, through the cooperation of sparse and dense dual paradigm, effectively improves the positioning accuracy and fine-grained classification performance.

The application discloses a transformer fault diagnosis method based on a small sample unbalanced data set, comprising the following steps: S1, acquiring a transformer dissolved gas analysis data set and a comprehensive feature set; S2, constructing a transformer fault diagnosis model based on a small sample unbalanced data set; S3, according to the gas analysis data set and the comprehensive feature set, performing model training on the constructed transformer fault diagnosis model to obtain an optimal fault diagnosis model; and realizing transformer fault diagnosis based on the small sample unbalanced data set according to the optimal fault diagnosis model. The application solves the problems that the current traditional method cannot accurately diagnose transformer faults due to the technical problems such as complex fault mode recognition, specific class accurate diagnosis, insufficient model generalization ability and difficulty in fusion parameter optimization under a small sample unbalanced fault data set in the prior art.

The application relates to a method and device for identifying a proxy signature, electronic equipment and a storage medium, and relates to the technical field of information security and pattern recognition. The method comprises the following steps: acquiring a set of signature images without labels; for each original signature image, performing standardization preprocessing on the original signature image; inputting each obtained target signature image into a feature extraction model trained through migration learning to extract a deep feature vector; freezing the parameters of a pre-trained bottom model and fine-tuning the parameters of a top model during training; using a density-based unsupervised clustering algorithm to cluster the target signature images according to the deep feature vectors; performing character recognition on each target signature image in each cluster to obtain signature texts; and if each signature text corresponding to a cluster contains at least two different names, it is determined that a proxy signature exists. The application realizes efficient, automatic and high-credibility identification of the specific illegal mode of one person proxying for multiple people without relying on supervised learning.

The application provides a multi-modal feature fusion-based opponent intention pattern recognition method, relates to the technical field of intention recognition, and obtains a plurality of opponent time slice execution opponent situation information feature extraction by calling historical game data from an adversarial deduction system, performing time slice segmentation, generating a plurality of sample multi-modal situation information features and a plurality of preset intention label identifiers as training data, performing parameter iterative optimization training of an opponent intention recognition model, locally observing game information in a preset time window length, inputting the opponent intention recognition model for intention reasoning, and outputting a current opponent intention probability distribution. The technical problems that the prior art relies on single modal data, leading to feature fragmentation, resulting in insufficient intention recognition accuracy and poor adaptability to local observation information are solved. The technical effects of effectively integrating multi-modal time series data, reducing the uncertainty of information in the game process, improving the accuracy and robustness of intention recognition are achieved.

The present application relates to clustering analysis technology in data mining and high-level fusion technology in information fusion, and belongs to the field of pattern recognition and intelligent information processing. It includes: 1) setting the attributes and type labels of the target; 2) representing the target data in the form of a space-time graph; 3) designing a space-time graph autoencoder with an attention mechanism, learning node representation by aggregating adjacency matrix information, and reconstructing the space-time graph network structure by calculating the inner product of node pairs; 4) constructing a self-training graph neural network model to aggregate the reduced neighbor target information; 5) designing a graph convolutional neural network and a deep neural network double self-supervised module; step 6, setting the target behavior rule label; 6) visualizing the target behavior rule. The method can solve the problems of traditional clustering methods such as strong data dependence, high computational complexity and inaccurate measurement description, and realize efficient mining and analysis of target behavior rules.

This invention discloses a method and system for transformer partial discharge pattern recognition based on an optimized probabilistic neural network. The method first acquires the transformer partial discharge signal; then, it establishes a two-dimensional spectrum of the partial discharge phase distribution pattern based on the partial discharge signal and extracts discharge statistical features from this spectrum; finally, it inputs the discharge statistical features into the optimized probabilistic neural network for pattern recognition to obtain the partial discharge pattern. The optimized probabilistic neural network uses a pollination algorithm to optimize the smoothing factor, and the switching probability in the pollination algorithm is a nonlinear function that decreases with the number of iterations. This invention can more accurately and efficiently classify and identify different partial discharge patterns of transformers, providing a data foundation for transformer fault diagnosis and resolution.

This application discloses a method and device for enhancing and evaluating multimodal humor understanding based on reinforcement learning. Addressing the problem that existing large-scale visual language models overly rely on pre-trained knowledge and pattern recognition, making it difficult to perform effective reasoning in humorous scenarios with complex contexts and cultural backgrounds, this application proposes a technical solution that uses reinforcement learning to drive the model's autonomous evolution of reasoning paths, thereby enhancing the model's ability to capture deep semantic details across multiple modalities. Specifically, this application constructs a reward model with a dual reward mechanism of format and answer, and combines it with a group relative policy optimization algorithm to fine-tune the pre-trained large-scale visual language model for humor understanding and generation tasks. Experimental results show that, compared with traditional supervised fine-tuning methods, the present invention significantly improves the accuracy and naturalness of multimodal humor understanding and generation, and exhibits stronger cross-domain generalization ability.

This invention relates to an intelligent monitoring system and deployment method for building module data interfaces based on the Internet of Things (IoT), belonging to the field of building information monitoring technology. The system consists of distributed sensing units, an edge computing gateway, a cloud platform, and a visualization terminal. The edge computing gateway incorporates an adaptive filtering algorithm and an anomaly pattern recognition model. The cloud platform uses a time-series database to construct a multi-dimensional data warehouse and performs structural health assessment by fusing LSTM neural networks and random forest algorithms. The deployment method includes: optimizing sensor placement strategies based on BIM models, establishing a wireless mesh self-organizing network communication architecture, and configuring a hierarchical early warning mechanism and fault tracing function. The innovation lies in proposing a dynamic threshold adjustment algorithm and an interface performance degradation prediction model to achieve real-time monitoring and lifespan prediction of building module connection status. This system has the advantages of flexible deployment, high detection accuracy, and low maintenance costs, effectively improving the intelligent level of building structural safety monitoring.

The invention provides a tumor medical mode recognition method and system based on image detection, and relates to medical image processing and artificial intelligence auxiliary diagnosis, and the method comprises the steps: carrying out the partitioning of a digital pathological section image, evaluating the color distribution, light and shade contrast and microstructure geometric features of each block, and generating a local quality evaluation graph to recognize a quality damaged region; a local diagnosis judgment graph is generated based on tumor recognition model analysis, and the diagnosis confidence of the model on each region is visually reflected; performing correlation analysis on a low-confidence area and a quality damaged area in the two images, if the overlapping degree reaches the standard, generating quality correlation interpretation, and determining that uncertainty is derived from image quality; finally, an interpretability report containing the original image, the two evaluation images and interpretation is generated, a clear basis is provided for doctors, traditional compensation defects are avoided, recognition reliability and transparency are improved, precise clinical decision making is assisted, and practical value is achieved.

Embodiments include methods performed by a monitoring function for a computing environment configured to host a plurality of atomic software functions (AFs) usable by applications executing in the computing environment. Such methods include performing pattern analysis on entries of a database to identify one or more candidate recurrent patterns. Each database entry includes an AF identifier uniquely associated with one of the AFs and a time at which the identified AF was invoked in the computing environment. Each candidate recurrent pattern includes a plurality of instances of a same sequence of AF identifiers in a same chronological order. Such methods include validating a first one or more candidate recurrent patterns as applications and / or use cases and assigning respective use case tags to the validated first candidate recurrent patterns. Such methods include updating the database such that each assigned use case tag is stored in association with the database entries that are associated with the corresponding validated candidate recurrent pattern. Other embodiments include monitoring functions (e.g., apparatus) configured to perform such methods.

The application belongs to the technical field of computer memory management, and discloses an active page replacement method and system based on regional reuse mode identification, which comprises the following steps: working set identification based on memory access sample clustering, obtaining memory access samples by sampling the memory access instructions of a process, and clustering the samples to obtain the working set in the current monitoring window in real time; adaptive memory region division based on working set integration, dividing the address space into regions according to virtual address continuity and adaptively splitting / merging; reuse mode identification based on state transition, determining the reuse mode of each region according to the switching between hot and cold states of each region and the state duration; active page replacement and prefetching method based on the reuse mode, prefeteching the regions that will reach the reuse time, and triggering the replacement of the regions that are in the cooling state for a long time. Compared with the existing passive page fault triggering method, the application can reduce the page fault and jitter, reduce the replacement traffic, and improve the application execution efficiency and system throughput.

The application discloses a kind of based on pattern recognition's storage tank corrosion defect C scan analysis method, including the following steps: obtaining storage tank C scan image, decay characteristic time chart, amplitude chart and wall thickness estimation chart;With the preprocessed data set input image boundary passage of cross-modal corrosion boundary perception network;With the preprocessed data set input physical decay passage;Based on the cross-modal fusion module of cross-modal corrosion boundary perception network, cross-modal attention fusion is executed;With the cross-modal fusion feature set input boundary refinement module, generate corrosion region initial segmentation chart and corrosion boundary confidence chart;Based on corrosion boundary confidence chart, corrosion region initial segmentation chart is executed iterative boundary refinement processing;According to target corrosion region segmentation chart and preprocessed data set, establish spatial correspondence.This application cross-modal corrosion boundary perception network realizes the fine identification and quantitative analysis of storage tank corrosion region.

The application discloses a kind of based on multi-source data fusion and process evaluation's college student comprehensive performance automatic generation method and system, including S1 establishes ideological and political evaluation model, academic performance evaluation model, practical ability evaluation model, comprehensive quality evaluation model, development potential evaluation model comment model. S2 by middleware establishes standardization interface and automatically reads the heterogeneous data source data of educational administration system, school system, campus card system, library system, scientific research and teaching research practical training system, second classroom activity platform etc.S3 to behavior sequence is carried out pattern recognition and feature extraction, establishes student panoramic data warehouse, and the data of step S2 is labeled with S1 evaluation model label and storage.S4 user selects comment purpose.S5 dynamic weight distribution.S6 to student data is screened.S7 comment automatic generation.S8 artificial check comment.S9 generation visual report.The application improves work efficiency, and can provide accurate student performance in school for parents and employing units.

This invention discloses a method for constructing a risk warning model for medical device testing based on big data. This invention relates to the field of data processing and risk warning technology, and solves the technical problem of failing to effectively correlate the deep nonlinear relationships between personnel behavior, equipment status, environmental fluctuations, and final test results, resulting in a large number of risk signals latent in process data going undetected. This invention introduces deep process features such as equipment stability indicators, personnel pass rate deviation, report modification rate, and environmental parameter deviation, enabling it to capture weak risk signals that traditional methods cannot detect. Five-dimensional feature engineering covers all key aspects of laboratory operation, and the unsupervised learning model can discover hidden anomalies beyond preset rules, compensating for the shortcomings of supervised learning in recognizing unknown patterns. The warning threshold automatically floats with recent data distribution, adapting to seasonal changes, new project launches, and other scenarios, avoiding frequent false alarms caused by a one-size-fits-all approach.

The application discloses a safety-critical software failure mode identification method based on a large language model, comprising the following steps: constructing a safety-critical field knowledge base, injecting the safety-critical field knowledge base into an initial large language model through a P-Tuning v2 technology to obtain a large language model after first-time fine-tuning; constructing an instruction optimization data set, and performing multi-round iterative training on the large language model after first-time fine-tuning by using the P-Tuning v2 technology to obtain a large language model after second-time fine-tuning; using the large language model after second-time fine-tuning to predict failure modes of industrial failure text data, and based on the failure text data of the prediction failure, constructing a thinking chain data set, and using the thinking chain data set to continue training the large language model after second-time fine-tuning to obtain a safety-critical field specific large language model with ideal final effect; inputting failure text data of a failure mode to be identified into the safety-critical field specific large language model to obtain a failure mode identification result.