638results about How to "Realize automatic identification" patented technology

The invention discloses a self-evolution network security defense strategy generation and dynamic deployment method, which comprises the following steps of: acquiring multi-dimensional data such as original network flow data, and generating an optimized feature matrix through adaptive interval division and symbolization conversion; constructing a feature graph structure based on the optimized feature matrix, extracting threat features by using a graph neural network and an attention mechanism, and generating a threat mode set; analyzing threat propagation characteristics according to the threat evaluation index set and the threat incidence matrix, and generating a threat propagation graph; and generating an initial defense strategy set based on a threat assessment result, and generating an optimized defense strategy set through dependency analysis and conflict elimination. According to the invention, through adaptive feature extraction and dynamic strategy optimization, the intelligent level and protection effect of network security defense are improved.

The invention discloses a financial data automatic filling method and device, equipment and a storage medium, and belongs to the technical field of big data. The method comprises the following steps: determining a data source corresponding to original financial data by using a pre-trained data classification model; acquiring a data processing rule engine and a target data filling template matched with the data source; performing data cleaning on the original financial data based on a data cleaning rule; performing data analysis on the standardized data by using a data analysis rule; performing association relation extraction on the target data source field and the target filling field by using a data mapping rule, and performing data field mapping according to the field association relation; and according to a data field mapping result, filling the target data source field into the target data filling template to generate a financial data report. The invention further relates to the technical field of block chains, and financial data are stored on the block chain nodes. According to the method and the device, the applicability and the operation convenience of automatic filling and reporting of financial data in a multi-source data scene are improved.

The invention discloses a judicial field semantic abstracting method, system and device based on a large model and a storage medium. The method comprises the steps that voice recognition is conducted on a court trial video, voice is converted into a court trial text, the court trial text is labeled, and a labeled text set is obtained to serve as a training set; training the large model by using the labeled text set, and finely adjusting the large model after each round of training; performing voice recognition on the actual court trial video, converting the voice into an actual court trial text, and extracting a timestamp; utilizing the trained large model to identify the court hearing process of the actual court hearing text, and reasoning a court hearing process text; matching the reasoned court hearing process text to timestamps by using a matching algorithm, and generating video anchor points when the timestamps at the starting positions of all the processes in the court hearing process text correspond to the anchor points of the processes of the court hearing video; abstracting the reasoned court hearing process text; and combining the abstract text with the video anchor points to generate structured court hearing information. According to the invention, the court trial video processing efficiency is improved.

The invention discloses an optical fiber winding detection method and device, and the method comprises the steps: obtaining an optical pulse transmission signal transmitted by an optical time domain reflectometer to a to-be-detected optical fiber, and receiving a reflected optical pulse reflection signal; respectively carrying out signal waveform feature extraction on the optical pulse transmission signal and the optical pulse reflection signal to obtain a transmission signal waveform semantic feature map and a reflection signal waveform semantic feature map; processing the transmitted signal waveform semantic feature map and the reflected signal waveform semantic feature map to obtain a transmitted signal waveform semantic saliency feature map and a reflected signal waveform semantic saliency feature map; performing nonlinear correlation interaction processing on the transmitted signal waveform semantic saliency feature map and the reflected signal waveform semantic saliency feature map to obtain a transmitted signal-reflected signal waveform semantic correlation feature map; the classifier outputs an optical fiber winding identification result according to the transmitted signal-reflected signal waveform semantic association feature map; the method can improve the accuracy of optical fiber winding identification.

The invention discloses a tunnel lining steel frame recognition method based on GAR-Net and related equipment, spatial domain enhancement is performed on geological radar data to improve the robustness of a neural network structure, a GAR-Net network model is constructed, the network model comprises a mileage recognition model, a lining thickness recognition model and a steel arch recognition model, and the mileage recognition model, the lining thickness recognition model and the steel arch recognition model are used for recognizing a tunnel lining steel frame. The lining thickness recognition model and the steel arch recognition model perform lining thickness recognition and steel arch recognition on the basis of the mileage recognition model respectively, whether a tunnel lining steel frame has defects or not can be judged according to the lining thickness and positioning information of the tunnel steel arch, and the defects of traditional radar image interpretation are overcome. The method can achieve the automatic recognition of the tunnel steel arch and lining thickness, and remarkably improves the precision and recognition efficiency of the automatic recognition of a geological radar image.

The embodiment of the invention discloses a carbon emission monitoring method and device, a storage medium and a carbon emission terminal, and relates to the field of environment monitoring. According to the invention, the total ammeter data is automatically collected and the pre-training model is utilized to accurately identify the type and the number of the devices, so that fine decomposition of energy consumption is realized. And accurately calculating the carbon emission of each device in combination with the energy consumption of the device and the carbon emission factor, and then summarizing to obtain the total carbon emission. The process reduces manual intervention, improves the accounting efficiency, and ensures the accuracy of data. According to the scheme, enterprises can easily master the full view of carbon emission, solid data support is provided for formulating energy-saving and emission-reducing measures, and implementation of green development and sustainable development strategies is powerfully promoted.

The invention discloses a multi-modal lithology identification method and system. The method comprises the following steps: acquiring a rock sample image and a rock mesoscopic image; preprocessing the obtained images, and inputting the preprocessed rock sample images and rock mesoscopic images into the trained fusion model for real-time identification; outputting a lithology identification result by the fusion model, and naming the image according to the identification result; according to the method, the lithology of the surrounding rock is identified by establishing the fusion model based on deep learning, the fusion model can fuse the color, texture, shape and other features of the rock sample image with the crystal structure, pore distribution, particle size and other features of the rock mesoscopic image, mapping is formed by corresponding rock relations, and therefore the purpose of automatic identification is achieved; the lithology intelligent identification method based on deep learning is high in identification speed, low in cost, high in accuracy and high in automation degree, and the requirements for professional knowledge and identification experience of constructors are reduced.

A ship prefabricated pipe intelligent identification device based on visual inspection comprises edge device software and edge computing device hardware. The edge equipment software comprises an image acquisition preprocessing module, a pipe fitting feature recognition module, a character feature recognition module, a feature combination judgment module, a character combination judgment module, an engineering information database, a human-computer interaction interface and a process library; the edge computing equipment hardware comprises a camera, a touch screen and a communication module, the camera is used for shooting and obtaining pipe fitting image information, the touch screen is used for manual interface operation, and the communication module is responsible for information transmission of all modules of the software. According to the method, the image processing technology and the deep learning algorithm are utilized, automatic identification of the ship prefabricated pipe fitting is achieved through intelligent identification, and the assembling efficiency of ship pipe units, ship unit modules, ship segments and other scenes can be effectively improved.

The invention discloses a goods yard container positioning and identification system based on Beidou RTK positioning, the management level of a container goods yard is remarkably improved by applying Beidou RTK positioning, container number identification and visual analysis modules, the accurate position information of a gantry crane or a reach stacker is obtained in real time through the Beidou RTK technology, the positioning accuracy reaches the sub-meter level, and the positioning accuracy reaches the sub-meter level. The container number identification module uses a camera and a machine learning technology to automatically identify container numbers and replace manual input, the accuracy and efficiency of data entry are improved, informatization management of containers is realized, and the visual analysis module draws a goods allocation electronic map, so that the management efficiency of the containers is improved. Information such as the position, the container number, the size and the weight of the container is visually displayed, the state of the container position is monitored in real time, managers are assisted to optimize operation plans, and problems are found and solved in time.

The invention relates to the technical field of visual identification, in particular to a warehouse control management system and method based on computer vision and mobile robot technologies, and the method comprises the steps: training a target detection model for identifying a line bucket based on a computer vision algorithm, and deploying the target detection model to an AI control box; a camera, an AI control box, a warehouse management system, a robot management system and a robot are integrated through communication; the AI control box obtains a storage location image captured by a camera, inputs the storage location image into a target detection model, and identifies the line barrel and the state thereof to obtain identification data; and after the warehouse management system stores and updates the data, tasks are sent to the robot management system according to requirements, and the robot management system schedules one or more robots to carry the wire buckets. According to the method, automatic identification of the wire barrel and the state of the wire barrel is achieved, the robot can be accurately dispatched to move and place the wire barrel, automatic management of the wire barrel is achieved, workshop management efficiency is greatly improved, and manual errors and safety risks are reduced.

The invention discloses a reservoir area hydro-fluctuation belt rock crack image recognition method based on a deep learning network, and the method comprises the steps: S1, constructing a rock crack segmentation model, and training the rock crack segmentation model through employing a pre-processed rock crack image sample set; s2, recognizing a rock crack region in the target image by using a rock crack segmentation model to obtain a first type of recognition result; s3, on the basis of coordinate positions, pixel values and color space attributes of pixel points in the image, optimizing the first type of recognition result through a crack mask optimization algorithm of multi-algorithm weighted fusion to obtain a second type of recognition result; and S4, aiming at the second type of identification result, measuring the width of the rock crack through a maximum inscribed circle method and an orthogonal projection method so as to obtain geometric representation information of the rock crack. According to the invention, automatic identification of the geometric representation information of the rock crack image of the hydro-fluctuation belt can be realized, and the intelligent and informatization level of reservoir area hydro-fluctuation belt bank slope rock crack detection is improved.

The invention relates to a crucible defect detection method and device and computer equipment. The method comprises the following steps: performing defect identification on a to-be-detected crucible image to obtain a plurality of defect detection areas; each defect detection area corresponds to a defect type; merging the defect detection areas with the same defect type and the area spacing smaller than a preset threshold in the plurality of defect detection areas; and determining a defect detection result based on the plurality of defect detection areas after combination processing. By adopting the method, the labor cost can be reduced and the accuracy can be improved.

The invention provides a battery cell tab cutting and inspecting machine, and relates to the technical field of battery cell tab cutting and inspecting machines, the battery cell tab cutting and inspecting machine comprises a transfer device, a turntable device, a cutting device, a shaping device, a CCD detection device, an OCV / IR detection device and a feeding device, the transfer device comprises a feeding linear module supporting seat, a first bottom plate, a discharging conveying supporting seat and a discharging conveying assembly, the two sides of the surface of the first bottom plate are fixedly connected with a discharging conveying supporting seat and a feeding linear module supporting seat correspondingly, a discharging conveying assembly is installed on the surface of the upper end of the discharging conveying supporting seat, and a discharging linear module is arranged on one side of the discharging conveying assembly. According to the invention, the problem that the battery cell is inconvenient to cut due to the fact that the position of the battery cell is easy to deviate in the cutting process of the battery cell tab and the welding process of the protection plate when the battery cell tab needs to be cut and the protection plate needs to be welded on the battery cell in the packaging process of the battery cell is solved.

The invention belongs to the field of low-voltage power distribution of an electric power system, and discloses a multi-level low-voltage transformer area topology identification method based on linear regression and a related system. The connection relation between each meter box and a branch node, a main line and a transformer in a low-voltage transformer area can be identified more accurately, and identification errors are reduced. According to the method, the complex connection relation between the meter box and the branch nodes can be effectively processed and analyzed by using the multi-scale similarity measurement and hierarchical clustering method, and the problem that the traditional method is difficult to identify when facing a complex topological structure is solved. According to the invention, by automatically acquiring and processing the voltage load data, the current data and the correlation information thereof, manual intervention can be greatly reduced, and the efficiency of topology identification is improved.

The invention relates to a deep learning-driven carbon chip automatic detection and quantitative analysis method, which comprises the following steps: (1) digital image acquisition: making a carbon chip sample subjected to experimental treatment into a microscope glass slide, and generating a digital image by using a high-resolution glass slide scanner; (2) establishing an annotation data performing format conversion and annotation on the obtained digital image, and clearly marking outlines of carbon scraps, lycopodium clavatum and other impurities in the image so as to establish the annotation database; (3) deep learning model training: dividing the annotation database into a training set, a verification set and a test set; and (4) performing automatic identification and quantitative analysis on the carbon chips: performing automatic identification on the digital image of the sample to be identified by adopting a deep learning model passing precision verification, counting the number of the carbon chips and the lycopodium spores, calculating other statistical indexes of the carbon chips, and further performing quantitative reconstruction analysis on a fire event. The method has the characteristics of high precision, high speed, high universality, simplicity and convenience in operation and suitability for statistics of a large number of samples.

The invention relates to a wind shear recognition algorithm, which comprises data preprocessing and method recognition, and the data preprocessing comprises the following steps: S1, analyzing original data; s2, segmenting periodic data; s3, multi-channel wind field data; s4, generating a wind shear label; and S5, constructing a data set. According to the wind shear identification algorithm, a wind shear identification method based on a deep neural network is provided, specific radar scanning data is processed to obtain wind shear image data, the identification algorithm based on deep learning is completed, wind shear is identified by using the image data, and high-real-time wind shear identification and early warning requirements are met. Aiming at the laser wind finding radar data, the network model structure is improved, the recognition precision can be improved under the condition that the operand is reduced, automatic recognition of the target wind shear area is achieved through deep learning, conversion of the radar data is achieved through the image generation technology, and wind shear visualization is achieved.

The invention relates to an intelligent virtual cloud exhibition server, an intelligent virtual cloud exhibition method and electronic equipment, WebGL (Web Graphics Library) 3D (Three Dimensional) modeling service is provided by adopting a WebGL technology, complicated calculation is completed by the server as much as possible based on a browser, the loading speed is high, the flow is small, the equipment requirement is low, and cross-platform and cross-terminal can be realized. Therefore, compared with a traditional virtual display technology that modeling scene files need to be downloaded in advance, rendering is carried out mainly through local equipment. According to the WebGL technology provided by the invention, 3D modeling and rendering can be carried out in combination with the virtual cloud, and occupation of a rendering thread of a local server is avoided. According to the invention, the algorithm engine is adopted to carry out audio and video and action analysis and mapping, action interaction can be carried out in the exhibition model, the artificial intelligence algorithm is adopted to enable the exhibition model to realize interaction, and the dynamic interactivity and practical applicability of the exhibition are improved.

The invention relates to the technical field of risk early warning, and provides an operation risk early warning method, device and system for substation operation and maintenance personnel and a medium. According to the implementation scheme, the method comprises the steps of training a behavior recognition model based on multi-modal historical data to obtain a target recognition model; based on the current operation data of the operation and maintenance personnel, performing risk identification on the current operation behavior represented by the current operation data through a target identification model to obtain an identification result; if the identification result is that the current operation behavior belongs to the dangerous behavior, triggering a multi-dimensional risk assessment mechanism to perform risk assessment on the current operation behavior to obtain a risk assessment result; and generating risk early warning information based on the risk assessment result. According to the embodiment of the invention, the intelligent early warning of the operation risk of the operation and maintenance personnel of the transformer substation can be realized, and the safety guarantee level of the operation and maintenance personnel during operation is improved.

The invention discloses a photomask defect identification method, and belongs to the technical field of photomask detection. The method comprises the following steps: S1, acquiring a surface defect image; s2, preprocessing the surface defect image based on the imaging characteristics of the defect; s3, performing filtering algorithm correction on the preprocessed surface defect image; s4, performing colorimetric analysis on the surface defect image corrected by the filtering algorithm to obtain a particle region; s5, on the basis of morphological characteristics of defects, segmenting the particle region to obtain defect islands; and S6, performing morphological analysis on the defective island to obtain a defect type and a defect size. The photomask defect identification method provided by the invention combines morphological and colorimetric analysis methods to automatically process the surface defect image and extract the defect island, improves the accuracy of defect identification, gets rid of the constraint of the difference of different equipment imaging systems, realizes automatic batch processing, and saves the manpower and material investment in the mass production link.

The invention relates to the field of road traffic, in particular to a highway automatic auditing method aiming at the inconsistency of a charging path and an actual passing path, and aims to overcome the defects in the background technology so as to improve auditing efficiency, accuracy and real-time performance. According to the technical scheme of the invention, the highway automatic auditing method for the inconsistency between the charging path and the actual passing path comprises the following steps: S1, vehicle preliminary screening: extracting exit flow data, and preliminarily screening out problematic vehicles according to a troubleshooting rule; s2, actual toll collection path identification: establishing a mapping table of identification stations and toll collection units, and mapping the portal license plate identification data of the problem vehicle into an actual toll collection path; s3, complete charging path identification: collecting historical exit flow data, establishing a path cost mapping table, complementing identification station paths, and identifying a complete charging path in the path cost mapping table; and S4, matching the actual path and the charging path: when the complete charging path and the actual charging path do not conform to the matching rule, initiating an auditing work order.

The invention belongs to the field of artificial intelligence and finance, and relates to a risk identification factor mining method, which comprises the following steps of: setting different types of operators according to an insurance risk identification target through acquired data of different data types, constructing a genetic programming model according to the different types of operators, and obtaining a risk identification factor by initializing a formula population. And iteratively calculating the risk interpretation degree, continuously optimizing the formula tree through a genetic algorithm to obtain a final formula tree species group, selecting the formula tree with the highest risk interpretation degree from the final formula tree species group as a risk identification factor, and performing test optimization on the risk identification factor to obtain an optimal risk identification model. The invention further provides a risk identification factor mining device, computer equipment and a storage medium. In addition, the invention also relates to a block chain technology, and the text data and the numeric data can be stored in a block chain. According to the invention, the automatic identification of the insurance risk can be better realized, and the accuracy of risk identification is improved.

The invention provides a historical building bare brick wall degradation characteristic evaluation method and equipment, and the method and equipment achieve the automatic recognition and precise evaluation of the historical building bare brick wall degradation damage characteristics based on a target detection algorithm through the fusion application of deep learning and computer vision technologies and the combination of a transfer learning optimization neural network architecture. According to the method, a bare brick wall degradation characteristic sample database is established, a PP-PicoDet algorithm is selected to carry out model training and characteristic increment superposition training, rapid and accurate automatic identification of damage types, positions and degrees is realized, and compared with a traditional manual investigation mode, the operation efficiency and the result accuracy are greatly improved; and a novel intelligent efficient investigation tool and method are provided for historical building protection and repair.

The embodiment of the invention discloses a small unmanned aerial vehicle identification method and equipment based on micro-Doppler feature enhancement, belongs to the technical field of unmanned aerial vehicle identification, and solves the problem of low identification accuracy of a small unmanned aerial vehicle. Comprising the following steps: constructing an unmanned aerial vehicle rotating blade dynamic echo signal model based on blade length and rotating frequency parameters corresponding to an unmanned aerial vehicle; feature extraction is carried out on the unmanned aerial vehicle rotating blade dynamic echo signal model, and differential transformation is carried out according to the extracted unmanned aerial vehicle body echo signal and the rotor blade echo signal; based on differential transformation, micro-Doppler components are separated, and a micro-Doppler feature map is constructed according to the micro-Doppler components; matching the blade length and the rotor frequency in the micro-Doppler feature map with preset target values corresponding to the unmanned aerial vehicle, and enhancing the micro-Doppler energy based on a matching result to obtain a feature enhancement map; and constructing a convolutional neural network based on the feature enhancement graph, so as to recognize the to-be-detected unmanned aerial vehicle through the convolutional neural network.

The present invention provides an adaptive RS232 and RS485 interface circuit, including a connector, a communication switching module, an identification module, an active control selection module, an RS232 interface communication module, an RS485 interface communication module, and a logic control circuit. The connector is arranged at a physical interface for accessing an external communication device, the identification module is used to identify the physical interface type of the external communication device, and control the communication switching module to switch the interface communication module according to the identification result, the communication switching module is respectively connected to the RS232 interface communication module and the RS485 interface communication module, and the channel is selected by an analog switch to complete the automatic switching of the RS232 or RS485 communication mode, and the logic control circuit is respectively connected to the RS232 interface communication module and the RS485 interface communication module using a logic and gate chip. The present invention can realize the automatic identification and automatic switching of RS232 and RS485 communications, and has the advantages of high automation, low technical risk, low cost, domestic controllability, flexible control, high reliability, etc.

The invention discloses an operation risk management and control method and device based on image recognition, electronic equipment and a storage medium. The method comprises the steps that an operation site video of a current operation site is acquired; inputting the operation site video into a preset operation risk type identification model, so that the operation risk type identification model extracts image frames of the operation site video, sequentially performing image feature extraction on the image frames, and performing identification on the extracted image features according to the identification result of the operation site video; comparing the operation risk characteristics with operation risk characteristics of different operation risk types in a preset image characteristic library one by one, and when the operation risk characteristics consistent with the image characteristics are detected, taking the corresponding operation risk type as the operation risk type of the current operation site and outputting the operation risk type; and matching a corresponding operation risk management and control scheme according to the output operation risk type, and then performing risk management and control on the current operation site according to the operation risk management and control scheme. According to the invention, the operation risk management and control efficiency can be improved.

The invention discloses a picture resource identification method and a related device, and relates to the technical field of picture identification, and the method comprises the following steps: responding to a picture resource identification trigger instruction, and identifying a picture resource from a resource file name under a directory structure of an iOS project; screening out all first picture resource file names meeting a preset picture resource file extension name requirement to obtain a first array, determining second picture resource file names having a reference relationship with the code files from the code files under the directory structure of the iOS project to obtain a second array, and comparing the first array with the second array to obtain a first picture resource file name and a second picture resource file name; and searching the target picture resource file names which exist in the first array and do not exist in the second array, and determining the picture resources corresponding to all the target picture resource file names as the identified useless picture resources. According to the method and the device, the useless picture resources in the iOS project are automatically identified, the consumed time is short, the efficiency is high, and the useless picture resources can be accurately identified.

The invention relates to the technical field of soft package carrying, and discloses a high-speed intelligent feeding system and method.The high-speed intelligent feeding system comprises a 3D visual perception module, a 2D image recognition and positioning unit, a control decision unit, an execution mechanism unit, a bag breaking and shaking processing module, a material bag recycling module, a data processing and analyzing unit and a system integration and management unit; according to the invention, by combining 3D photographing and 2D photographing technologies, efficient and accurate material identification and positioning are realized, in the 2D photographing process, the system can determine the center point coordinates of N bags at the same time, and only one-time 3D and 2D photographing is needed in the same plane, so that the process period is greatly saved, the whole feeding process is quicker, and the production efficiency is improved. The 3D photographing technology provides three-dimensional information of materials, the 2D photographing technology provides two-dimensional image information of the materials, through combination of 3D data, the system can achieve accurate positioning of the materials, and the system can adapt to materials of different shapes, sizes and numbers and can flexibly process various complex material conditions.

The invention discloses a PCB marking positioning system based on machine vision, and the system comprises an image collection assembly which is used for collecting image information in a visual field and outputting a control command according to the image information; the bearing plate is arranged on the marking machine and located below the image acquisition assembly, and the bearing plate is used for bearing the circuit board placed on the bearing plate so that the circuit board can be located in the visual field of the image acquisition assembly; the four push plates are movably arranged on the bearing plate and located on the four sides of the bearing plate correspondingly, and all the push plates work independently; the invention also provides a positioning method. According to the invention, a machine vision automatic matching mode is adopted, the image acquisition assembly is arranged to acquire the information of the circuit board on the bearing plate to automatically match the information of the preset circuit board, and corresponding control commands are output to control the four push plates to independently act on the bearing plate, so that the circuit board is clamped and pushed to a preset position in the information of the preset circuit board; and automatic identification and automatic positioning marking of circuit boards of multiple specifications are realized.

The invention discloses a deep learning-based question and answer knowledge graph construction method and system, and the method comprises the steps: collecting multi-dimensional question and answer data of a target domain from a plurality of data sources, carrying out the cleaning and standardization processing of the question and answer data, so as to eliminate noise information, and generating a preliminary data set; performing semantic analysis on the question and answer data by using a deep learning model, and generating a context embedding representation of each question and answer text in the question and answer data; knowledge entities and relationships among the entities are identified from the context embedding representation, and a preliminary knowledge triple is constructed; and based on the knowledge triad, constructing a preliminary question and answer knowledge graph for the identified entities and relationships, and allocating a unique identifier to each node in the preliminary question and answer knowledge graph to generate a structured question and answer knowledge graph. By utilizing the embodiment of the invention, the question and answer knowledge graph construction efficiency and the semantic understanding capability can be remarkably improved, and the application of an intelligent question and answer system in a complex scene is promoted.

The invention discloses a steel box girder bridge apparent disease assessment method and system based on unmanned aerial vehicle inspection. The method comprises the following steps that an unmanned aerial vehicle airport and an unmanned aerial vehicle are deployed on a steel box girder bridge site; the method comprises the following steps: planning a photographing route in an unmanned aerial vehicle flight control system, acquiring a steel box girder picture by adopting an unmanned aerial vehicle matched with an aerial survey camera, and performing three-dimensional reconstruction on the acquired picture to form a three-dimensional'coarse model 'of the steel box girder; calculating the relative flight height, the camera view width and height, and scale factors in the width and height direction; planning a patrol route; the patrol route is imported into an unmanned aerial vehicle flight control system, and an unmanned aerial vehicle is matched with an aerial survey camera to collect apparent coating pictures of steel box girder webs and bottom plates; coating disease photos of various steel box girders are collected, a target detection network model is constructed, and coating disease types and areas are identified based on a target detection algorithm; according to the invention, automatic identification of the apparent coating diseases of the steel box girder is realized, the deterioration degree of the coating can be automatically evaluated, a detection report can be automatically generated, the detection quality is ensured, and the detection efficiency is improved.