4370 results about "Identification system" patented technology

The invention discloses a robot real-time potential safety hazard recognition system based on multi-modal sensor fusion, and particularly relates to the technical field of intelligent inspection and safety monitoring, the system comprises five parts of data acquisition, information fusion, behavior response, trajectory analysis and risk output, and the potential safety hazard recognition system is used for recognizing potential safety hazards through image acquisition, thermal imaging, gas concentration and temperature and humidity information. Carrying out numerical value normalization and feature extraction, identifying potential abnormity and generating early warning; triggering data enhanced acquisition and track recording in the target area, and constructing a space-time path model to analyze an abnormal evolution trend; and finally, outputting a potential safety hazard assessment result according to a risk level classification rule by combining the enhanced information and the trajectory features. According to the method, high-precision early warning is realized through multi-source data acquisition and normalization fusion, the local recognition capability is improved based on dynamic enhanced acquisition of a behavior response mechanism, an abnormal development trend is tracked by combining track evolution modeling, risk level assessment is output according to the abnormal development trend, and accurate recognition and dynamic management and control of hidden dangers are realized.

The invention discloses an electrical fire intelligent identification system based on multi-dimensional sensor fusion. The system comprises the following steps: constructing a reference environment model through multi-sensor scanning, data dimension reduction and intelligent node deployment; multi-sensor time sequence alignment is carried out through edge calculation denoising and dynamic time warping, and high-priority data is processed in real time through a layering mechanism; establishing a fire feature modeling system through LSTM time sequence analysis, mutual information correlation mining and self-supervised learning; through multi-level data fusion, GAN abnormal data generation and fuzzy logic reasoning; through grading alarm, an intelligent fire extinguishing strategy and remote control, full-process coverage from fire detection to emergency response is realized. A fire scene is visualized by means of a three-dimensional thermodynamic diagram, flame dynamic analysis and an augmented reality technology. The system is suitable for fire detection, alarm and response in a complex industrial scene, and can be widely applied to intelligent management of electrical fire.

The invention discloses a system for realizing crop intelligent identification based on a CLIP multi-mode method, and belongs to the technical field of crop identification, and the method specifically comprises the steps: collecting real-time images, text description and environment data of crops; performing image processing on the real-time image; a CLIP model is used for carrying out feature extraction on the image and text description, visual features are extracted from the image, semantic features are extracted from the text, the text description comprises crop types and symptom description of diseases and pests, the environment data and the visual features are fused, and a multi-modal feature vector is generated; the multi-modal feature vectors are classified by using a pre-trained classifier, specific crop types and pest and disease damage types are identified according to extracted multi-modal features, identification results are displayed to users through a visual interface, and information is fed back to a monitoring center; according to the method, visual, semantic and environmental features are fused, so that the accuracy of crop disease and insect pest recognition is remarkably improved.

The invention relates to the technical field of power system monitoring, and discloses an infrared thermal image feature fusion-based power transmission line abnormal area identification method, which comprises the following steps of: acquiring infrared thermal image data of a power transmission line, and preprocessing the data; the invention further provides an infrared thermal image feature fusion power transmission line abnormal area identification system, which comprises a data acquisition module, an infrared thermal image feature fusion module, an infrared thermal image feature fusion module, an infrared thermal image feature fusion module, an infrared thermal image feature fusion module and an infrared thermal image feature fusion module, and is characterized in that the data acquisition module is used for acquiring infrared thermal image data of a power transmission line; and the preprocessing module is used for preprocessing the collected infrared thermal image data. According to the method, through combination of multi-scale wavelet transform, nonlinear dynamic modeling, graph neural network optimization and reinforcement learning, the abnormal region identification precision is improved, the robustness and adaptive ability of the system in a complex environment are enhanced, and it is ensured that the abnormal region can still be efficiently and accurately identified under dynamic change and noise interference.

The invention relates to the technical field of soil pollution identification, and discloses a soil heavy metal pollution identification system. A multispectral remote sensing sensing module of the system obtains surface reflectance data and soil in-situ spectral data through a satellite load and a vehicle-mounted mobile platform respectively, and the surface reflectance data and the soil in-situ spectral data are processed by a heterogeneous data fusion gateway to generate multiband spectral response signals. In the pollution risk assessment module, a spatial distribution analysis unit outputs a heavy metal spatial distribution map, a migration risk prediction unit generates a pollution migration probability cloud map in combination with meteorological and hydrological data, and a pollution threshold defining unit outputs a soil remediation safety threshold. In the treatment decision execution module, an in-situ remediation execution unit adjusts passivator injection parameters, a pollution source management and control unit regulates pollution source blocking equipment and collects monitoring signals, and a three-dimensional dynamic early warning platform generates a comprehensive pollution risk index. According to the system, the cooperative operation of soil heavy metal pollution identification, evaluation and treatment is realized.

The invention relates to the technical field of nondestructive testing, and discloses a steel structure weld defect ultrasonic detection and identification system. A data acquisition module of the system acquires an original ultrasonic signal of a steel structure welding seam through ultrasonic detection equipment and acquires geometric attribute data of the welding seam; the model construction module constructs a welding seam three-dimensional digital model based on the data; a feature extraction module performs feature mining on the three-dimensional digital model and extracts a weld defect feature index set; the difference analysis module carries out deviation calculation on the characteristic index set and a reference index set in a standard welding seam characteristic database, and an abnormal area is identified; the risk assessment module calculates a defect sensitivity index according to the abnormal region in combination with real-time environmental parameters, and assesses a defect risk level; and the report generation module formulates a detection scheme according to the defect risk level, generates a detection instruction, executes ultrasonic scanning, collects performance data and generates a defect detection report. The system has the advantages of high detection precision, high reliability, automatic and standardized process and the like.

Disclosed are a multilingual event causality identification method and a multilingual event causality identification system based on meta-learning with knowledge. The method includes: partitioning a to-be-processed multilingual dataset into a plurality of sub-datasets; tagging target events corresponding to all data samples in the sub-datasets; obtaining background knowledge for the various events of different language types and combining the background knowledge with a corresponding data sample; basic input samples of all non-target languages in the basic input sample constituting a plurality of basic datasets, and all the remaining basic input samples constituting a target dataset; partitioning support sets and query sets; constructing a multilingual causal identifier; training the multilingual causal identifier based on the support sets and query sets in the plurality of basic datasets to obtain an optimal hyper-parameter; and training the multilingual causal identifier by using the support set in the target dataset, to obtain an optimal non-hyper-parameter.

The invention provides a traditional Chinese medicine physique dynamic change identification system. The system comprises a data acquisition module, a feature extraction module, a deep learning analysis module, a physique analysis and prediction module and a diagnosis report generation module. The data acquisition module is used for acquiring tongue image video streams, pulse condition waveforms and body surface infrared thermal imaging data and recording environment temperature and humidity, user behavior logs and medication information. The feature extraction module is used for extracting various feature data. And inputting the multi-dimensional data set into a deep learning analysis module, and calculating the transformation relation probability of the traditional Chinese medicine constitution types. The physique analysis and prediction module judges the current physique type based on the probability data and predicts the physique evolution trend in combination with historical data, and finally the diagnosis report generation module outputs a diagnosis report containing physique evolution analysis and conditioning suggestions. According to the method, multi-dimensional physiological, environment and behavior data can be integrated, dynamic identification of traditional Chinese medicine physique is realized, the accuracy of physique analysis is improved, and a personalized health management scheme is provided.

The invention relates to the technical field of intelligent inspection, in particular to a pipeline inspection abnormal hidden danger intelligent identification system based on an unmanned aerial vehicle. According to the invention, the three-dimensional grid construction is carried out on the data collected by the unmanned aerial vehicle in the inspection process, so that the space division of the inspection area is realized, and the detection of the gas pipeline has higher precision. In combination with hyperspectral data analysis, measurement of methane concentration can be accurately mapped to space grid points, interference of environmental factors is reduced, and preliminary recognition accuracy of a leakage area is improved. On the basis of local concentration gradient calculation, through a data smoothing and diffusion optimization method, the boundary of a leakage area is clearer, interference of environmental noise is eliminated, meanwhile, the concentration value is dynamically adjusted, and the adaptive capacity to the change trend of leakage points is enhanced. By means of the construction of the virtual diffusion field and in combination with the space occupation condition of terrain obstacles, the analysis of the gas flow path is more accurate, and the problem of misjudgment caused by terrain complexity is solved.

The invention relates to the technical field of digital economic risk control, and discloses a digital economic risk identification system and method based on artificial intelligence. A risk data acquisition engine of the system obtains transaction behavior data streams from a plurality of digital economic transaction platforms in real time, and converts the transaction behavior data streams into a structured transaction feature matrix; an abnormal mode detection engine extracts time sequence abnormal features through a deep residual network to generate an abnormal feature vector set; the risk association analysis engine constructs a risk propagation path map through a graph neural network, and outputs a risk association degree scoring matrix; the dynamic threshold adjustment engine performs adaptive threshold calibration according to the historical risk event database to generate a dynamic risk threshold vector; and the risk decision engine compares the scoring matrix with a dynamic threshold value, marks risk transaction nodes and generates a risk early warning instruction set. The system can adapt to digital economic transaction characteristics, and the comprehensiveness and accuracy of risk identification are improved.

The invention discloses a multi-target pedestrian re-identification system based on multiple modes and a vector database, relates to the technical field of network communication and positioning, and solves the problem of cross-target and cross-mode trajectory association in a complex multi-camera scene. The multi-target pedestrian re-recognition system comprises a monocular tracking module, a multimode extraction module, a trajectory generation module, a multi-objective matching module and a global retrieval module, through organic combination of multi-modal features and a multi-modal multi-path recall strategy, the accuracy and applicability of cross-modal pedestrian re-identification are significantly improved. Through track-level feature generation and storage design, the modeling capability of dynamic features of a target in a complex scene is enhanced; through collaborative design of a space-time constraint mechanism and multi-modal features, logic consistency and global optimality of target person trajectory association are ensured.

The invention provides a multi-modal target detection method and device and a multi-modal recognition system. The method comprises the steps that a scene image is acquired, and the scene image is an image of a current environment acquired by adopting image acquisition equipment; acquiring a point cloud image, the point cloud image being an image of point cloud data of the current environment acquired by using a laser radar; according to the scene image and the point cloud image, fusion is carried out to obtain a target image, and the fusion mode at least comprises image fusion and / or feature fusion; and performing target identification on the target image to obtain a target object in the target image. According to the scheme, the problem of low accuracy of target detection based on single data in the prior art is solved.

The invention discloses an oil field power distribution network operation safety violation behavior deep learning recognition system. The system comprises a video acquisition module, a data preprocessing module, an improved YOLO model module, a violation behavior judgment module and a result output module. The video acquisition equipment is distributed in a key area of an oil field site and transmits video data to the server through a wireless network; the data preprocessing module adopts histogram equalization and sharpening operation to enhance the image contrast. The improved YOLO algorithm model is subjected to customized training, and behavior actions of operators and equipment can be accurately recognized. And the illegal behavior judgment module performs matching judgment on the result output by the model in combination with the safety specification of the oil field operation. According to the method, the difficult case mining technology and the multi-stage training strategy are adopted, the judgment capability of the model on illegal behaviors under complex conditions is improved, the OpenCV technology is combined, the capability of the system for coping with light changes and severe weather conditions is enhanced, and the recognition accuracy under different illumination intensities is ensured.

The invention discloses an autonomous collision avoidance method and system for an unmanned ship in a mixed traffic mode, and the method comprises the following steps: obtaining the current position coordinate information, course information and surrounding environment information of the unmanned ship in real time through a ship positioning system and a ship recognition system on the unmanned ship; combining the target point, constructing a path plan and calculating the energy consumption of a navigation path, selecting a first navigation path, identifying and classifying static obstacles and dynamic obstacles, monitoring the static obstacles in real time, calculating and evaluating a detour difference, adjusting the path according to a collision avoidance rule, and generating a second navigation path; predicting the movement direction of the surrounding dynamic obstacles, and judging whether a collision risk exists or not; predicting a future position and adjusting the course to generate a third navigation path; and respectively evaluating the electric quantity threshold, the energy consumption threshold, the battery electric quantity and the energy consumption value, and adjusting an energy use strategy in real time. According to the invention, the accuracy of the navigation path is improved, and the safety of the unmanned ship in a complex environment is improved.

The invention relates to the technical field of fire safety monitoring, in particular to a firework identification system and method based on multi-modal fusion perception, and the core of the scheme is a visible light, multispectral and temperature three-modal framework: feature extraction optimization of each modal, improved YOLOv8s for visible light branches, dynamic background modeling and flame color screening, and multi-modal fusion perception. False positive is rejected by a multispectral branch depending on a waveband ratio and an index, an error compensation algorithm is introduced into a thermopile branch, and finally, a final smoke and fire area and the confidence coefficient thereof are determined by associating a three-mode area through collaborative decision. According to the scheme, the complex environment adaptability and the recognition reliability can be improved, the false alarm risk is reduced, the extremely-early smoke and fire detection capability is enhanced, good real-time performance and deployment flexibility are achieved, and the method is suitable for various types of fire safety monitoring scenes.

The invention relates to the technical field of underground engineering and geotechnical mechanics, and provides a marine facies soft soil tunnel construction disturbance induced surrounding rock energy dissipation grading evaluation method which comprises the following steps: step 1, establishing a marine facies soft soil energy dissipation constitutive model based on thermodynamics; 2, determining mechanical parameters of the constitutive model; 3, establishing a tunnel construction mechanical model, embedding the constitutive model in the step 1 and the mechanical parameters in the step 2 into the tunnel construction mechanical model, and outputting an energy subitem output quantity in real time; step 4, establishing a damage unit identification system; 5, arranging a monitoring system to obtain monitoring data and feeding the monitoring data back to the numerical model for verification; and step 6, performing graded early warning according to the closeness degree of the structural unit to the instability failure energy threshold value. According to the scheme, a surrounding rock damage grading system is constructed through an energetic perspective, rapid risk identification is realized in combination with multi-source monitoring data, and a new theoretical and engineering means is provided for safe construction of the marine soft soil tunnel.

The invention discloses an intelligent steel pipe surface defect recognition system based on deep learning, and particularly relates to the technical field of pipe surface defect analysis. An annular polarization light source array and a high-frame-rate CMOS sensor are adopted to synchronously collect visible light and near-infrared multi-polarization images; a surface normal is calculated based on Stokes parameters, mirror surface suppression and diffuse reflection enhancement are realized, a defect candidate area is generated by fusing multi-scale Laplacian pyramid residual error and Renyi entropy segmentation threshold positioning, multi-physical quantity registration is completed through white light interference and infrared thermal imaging, a six-channel feature cube is constructed, and a three-dimensional image is obtained. According to the method, space, spectrum and thermal characteristics are jointly extracted in the multi-head attention convolutional neural network, the confidence coefficient is evaluated in combination with Jensen-Shannon divergence, and the polarization angle and the focal length are dynamically adjusted according to the confidence coefficient, so that closed-loop parameter self-optimization is realized, and the micro-scale pitting corrosion and millimeter-scale crack detection precision is remarkably improved.

A system for material detection and identification includes an interface configured to access a material database associating each of a plurality of materials with one or more corresponding resonance frequencies; an RF transmitter configured to, for each material of at least a subset of the plurality of materials in the material database, transmit into an environment an RF signal at a first resonance frequency for the material; an RF receiver configured to receive a response signal from the environment for each RF signal; and a processor configured to analyze each response signal for resonance characteristics that indicate a presence of the material and identifying the material to a user if the presence of the material is indicated by the resonance characteristics.

The invention discloses a power grid fault online identification system and method based on big data, and relates to the technical field of power systems, and the method comprises the steps: collecting multi-source data of a power grid system through a sensor; data filtering is performed through a hierarchical storage strategy, a data lake is constructed in combination with multi-dimensional data indexes, and multi-source data is stored in a classified manner; aggregating and converting data in a data lake by adopting a real-time stream processing framework, and extracting high-dimensional features related to a fault by combining wavelet transform with principal component analysis; based on the high-dimensional features, identifying the real-time state of the power grid by using a graph neural network in combination with a deep learning model; and according to the identification result of the real-time state, combining a power grid topological structure, and carrying out fault positioning through a time difference method and a graph theory algorithm. The power grid fault on-line identification system based on big data provided by the invention can efficiently manage and store a large amount of multi-source data in a power grid, and improves the data processing and access speed.

The invention discloses a quality management and control system for fabricated decoration construction, and the system comprises a sensing layer which constructs a multi-modal data collection network, carries out the three-dimensional real-time data synchronous collection through combining logistics API docking and an OCR recognition system, and constructs a construction process digital twin bottom plate; in the edge calculation layer, an edge node carries out lightweight processing on the original data; the cognitive layer is used for calling a Prolog rule through a process knowledge graph engine to reasone the feature snapshots, carrying out defect instant diagnosis and dynamic constraint propagation, outputting a root cause path with probability weight through three-stage verification, and quantifying intervention influence; the decision-making layer is used for constructing a dynamic prediction model based on a bidirectional LSTM and an attention mechanism, automatically activating a compensation mode when key interference is detected in combination with an anti-fact memory bank and a case-based reasoning compensator, and generating an alternative scheme of optimal cost / optimal construction period / comprehensive balance through a multi-target optimizer; and in the application layer, a Unity engine is utilized to develop the digital twinborn billboard.

The invention discloses a sonar target recognition system based on a residual network, and the system comprises a sonar preprocessing module which is used for collecting and preprocessing an original sonar echo signal; the frequency spectrum construction module is used for generating a multi-channel frequency spectrum image; the spectrum enhancement module is used for performing spectrum enhancement processing; the residual feature extraction module is used for extracting sonar target feature representation; the label screening module is used for calculating a label credibility score and constructing a label training set; the joint training module is used for combining the label training set and the real labeling samples to form a joint training set and executing iterative optimization of the SonarResBlock model; and the identification output module is used for performing reasoning identification by using the updated model and outputting a category label of the sonar target. According to the method, multi-class spectrum construction and a residual attention mechanism are fused, accurate sonar target recognition is achieved, and the method has the advantages of being comprehensive in modeling, high in robustness and efficient in training.

The invention relates to the technical field of deep learning, in particular to a new energy station illegal behavior intelligent recognition system and method based on machine vision. The method comprises the steps of obtaining new energy station image data, performing preprocessing and data enhancement, and creating a behavior image data set; a CNN-based behavior recognition model is constructed, and training is carried out through the data set; meanwhile, a clustering algorithm based on comparative learning is constructed for judging whether the unknown behavior belongs to a new violation type or not; if a new violation type is found, transmitting a sample of the new violation type to a behavior recognition model for incremental learning, and expanding the number of the sample; and through a knowledge distillation technology, knowledge of the trained CNN behavior recognition model is migrated to a miniaturized student model, and lightweight deployment is realized. According to the method, the illegal behaviors of the new energy station can be automatically identified, new illegal behavior types can be continuously found, the model is dynamically updated, and the adaptive capacity and the real-time performance of the system are improved.

A system for material detection and identification includes an interface configured to access a. material database associating each of a plurality of materials with one or more corresponding resonance frequencies: an RF transmitter configured to, for each material of at least a subset of the plurality of materials in the material database, transmit into an environment an RF signal at a first resonance frequency for the material; an RF receiver configured, to receive a response signal from the environment for each RF signal; and a processor configured to analyze each response signal for resonance characteristics that indicate a presence of the material and identifying the material to a user if the presence of the material is indicated by the resonance characteristics.

The invention relates to the technical field of Internet of Things, and discloses an Internet of Things-based campus self-service laundry equipment abnormity identification system, which comprises a user operation behavior alignment module, a dynamic time warping algorithm quantification behavior deviation degree and a first weight factor generation module, the multi-source state feature extraction module is used for extracting an equipment state matrix to generate a second weight factor in combination with vibration spectrum and motor current waveform analysis; the health degree fusion decision module dynamically distributes weights based on an entropy method, and calculates a health degree score to trigger equipment-level anomaly detection; the abnormal propagation topology modeling module constructs a fusion topological graph, dynamically distributes propagation weights in combination with a historical fault rate and a real-time load, and generates an abnormal propagation path probability graph; and the space-time early warning visualization module integrates the equipment position and the abnormal probability, multiple alarm levels are divided, and the risk distribution is dynamically displayed through the thermodynamic diagram layer, so that the detection precision and efficiency of abnormal identification of the campus self-service laundry equipment are remarkably improved.

The invention provides a multi-modal multi-factor depression recognition system fusing emotion information, relates to the technical field of multi-modal fusion, and provides a transfer learning and multi-dataset training method to extract more accurate emotion features so as to solve the problem of insufficient emotion recognition of the existing method. According to the method, feature extraction is carried out by taking clauses as units, and complete context information is reserved, so that language and emotion fluctuation of the user can be better understood. In order to optimize multi-modal data fusion, the invention adopts a fusion method based on an attention mechanism, which not only can more effectively capture the dependency relationship among the modals, but also can fully extract key information in each modality, thereby improving the overall detection effect. Meanwhile, the influence of gender difference and external knowledge is also considered, the accurate recognition and understanding ability of the model on the emotions of the users with different genders is improved by introducing the gender difference and an external common knowledge base, and the adaptability and accuracy of the model are further improved.

The invention discloses a pipeline defect recognition system based on a target detection algorithm, and the system comprises an image obtaining module which is used for obtaining image data in a pipeline, and a defect recognition module which is connected with the image obtaining module and is used for processing the image data based on the pre-trained target detection algorithm, recognizing defect features in the image data, and sending the defect features to the image obtaining module. The result generation module is connected with the defect identification module and used for generating a defect identification result, and the output module is connected with the result generation module and used for outputting the defect identification result to terminal equipment; according to the pipeline defect recognition system based on the target detection algorithm, the problems that in the prior art, image preprocessing becomes difficult, extraction of high-quality target features is affected, and then defect recognition precision is affected are solved, the problem that the detection effect is difficult to keep consistent is solved, and the problems that the environment challenges the real-time performance of the algorithm, the detection speed is insufficient, and the detection efficiency is low are solved. And the timeliness and practicability of defect detection are severely influenced.

Precise nerve detection during surgery is crucial for safe operational outcomes, which largely depend on the surgeon's skills. Therefore, automatic real-time identification of anatomical structures is of great importance. However, image processing times must be kept as low as possible to be a viable solution for real-time visual identification. By using a general purpose graphics processing unit (GPGPU) implementation for birefringence mapping, the process can achieve rates of 43 frames per second (FPS); a 118×gain from a CPU implementation. Furthermore, by including a deep learning network, the complete framework can automatically detect nerves close to 12 FPS. By leveraging GPU for the processing task, the framework can run on compact devices with NVIDIA modules, such as Jetson Xavier AGX, while still achieving reasonably fast nerve identification and visualization.

The invention provides an unmanned aerial vehicle inspection fault intelligent identification system and method, and relates to the technical field of unmanned aerial vehicle intelligent inspection, and the method comprises the steps: building a dual-target path model through historical fault data, carrying out the dynamic optimization of an inspection path of an unmanned aerial vehicle through the dual-target path model according to multi-source sensing data, and obtaining an optimized path and a sensing region; performing hierarchical identification on the multi-source sensing data to obtain a state prediction value of the unmanned aerial vehicle, and constructing an intelligent path guiding function based on the optimized path, the sensing area and the state prediction value; performing back propagation correction on the intelligent path guiding function to obtain fault type features and detection precision, and constructing a feature association weight matrix of the inspection path based on the fault type features and the detection precision; according to the method and the device, path reconstruction and fault intelligent identification based on identification feedback driving can be realized, so that the accuracy of an unmanned aerial vehicle inspection result is improved.

The invention discloses a multi-scale and mixed attention high-robustness motor imagery recognition method, which comprises the following steps: S1, acquiring motor imagery electroencephalogram signals, preprocessing the motor imagery electroencephalogram signals, dividing a training set and a test set, segmenting the training set, recombining the training set and expanding a training data set; s2, multi-scale feature extraction is conducted on the motor imagery electroencephalogram signals through a multi-scale convolution embedding module, and time dynamic and space cooperation features of different frequency bands are captured; s3, inputting the multi-scale features into LG-KAT, and respectively modeling a local fine-grained feature and a global time sequence dependency relationship through a local attention branch and a global attention branch; s4, features output by LG-KAT and low-layer embedded features are fused and flattened, a classification layer based on GR-KAN is input for nonlinear transformation and category mapping, model parameters are trained and optimized, and motor imagery task classification is achieved. The invention further discloses a multi-scale and mixed attention high-robustness motor imagery recognition system.

The invention relates to the technical field of image recognition, in particular to a harmful image detection and recognition system and method based on agent collaboration, and the system comprises a first agent module, a second agent module, a third agent module, a fourth agent module and a fifth agent module, the first agent module is used for analyzing image element semantic information, outputting structured data and constructing an image comprehensive semantic knowledge graph; and the second intelligent agent module is used for carrying out harmful feature detection and associated query on the image in combination with the structured data, and outputting a coarse-grained harmful semantic detection result and the confidence coefficient of the coarse-grained harmful semantic detection result. According to the harmful image detection and identification system based on intelligent agent cooperation, through hierarchical processing and cooperative work of the first to fifth intelligent agents, comprehensive analysis of the image is realized to obtain meta-semantic information, coarse-grained and fine-grained harmful semantic detection is performed on the meta-semantic information, and through multiple rounds of challenge and dynamic comprehensive analysis, the detection and identification efficiency of the harmful image is improved. Hidden harmful information can be accurately identified, so that the accuracy and interpretability of the harmful information are improved.