192results about How to "Make up for limitations" patented technology

The invention discloses a photovoltaic cleaning robot based on automatic path planning and an operation method thereof, relates to the technical field of robots, and solves the problem of cleaning blind spots in an existing cleaning robot and the endless loop risk of a path planning algorithm. According to the invention, the surface information of the photovoltaic panel is accurately captured through the multispectral acquisition module, a high-resolution and high-definition comprehensive image is generated through the data fusion processing module, then dirt is accurately identified on different scales by using a multi-scale pyramid structure and an adaptive feature fusion mechanism, and an attention mechanism and environmental perception data are combined, so that the real-time performance of the system is improved. The recognition threshold is dynamically adjusted, and misrecognition and missing detection are reduced; and finally, enabling the robot to autonomously learn in a complex environment and optimize an obstacle avoidance strategy through a dynamic obstacle avoidance algorithm based on deep reinforcement learning. The intelligent level and the cleaning effect of an existing photovoltaic cleaning robot are greatly improved.

The invention discloses a ship dynamic path adjusting method combining visual navigation and radar data. The ship dynamic path adjusting method comprises the following steps: S1, collecting data; s2, carrying out pretreatment; s3, performing data fusion to generate an environment perception model; s4, combining the generative adversarial network and the space-time diagram neural network to construct an environment prediction model; s5, performing initial path planning by using a heuristic search algorithm to generate an initial path; s6, refining and optimizing the path by using a fast extension random tree algorithm to generate an optimal path; s7, generating future possible environment change according to the environment prediction model, and calculating a coexistence reserve path for each prediction scene in combination with the environment perception model; s8, when the current path is predicted to have risks in the future, switching to a preset standby path in advance; and S9, automatically generating a navigation control instruction, and transmitting the instruction to a ship automatic driving system. According to the invention, intelligent optimization of the ship path is realized through a multi-sensor fusion and environment prediction method.

The invention provides an online learning energy concentration degree evaluation method combined with formability evaluation, and belongs to the technical field of online education, and the method comprises the steps: capturing eye movement data of a learner in an online learning process, carrying out feature extraction and time sequence analysis, and combining formability evaluation data to construct a deep neural network energy concentration degree evaluation model. And performing real-time dynamic evaluation on the energy concentration state of the learner by using multi-dimensional indexes such as attention continuity, visual concentration degree and cognitive input degree. Through a sliding time window technology and a specially-designed evaluation equation, the score of the energy concentration degree of each learning stage can be accurately calculated, and finally the overall energy concentration level of the learner is comprehensively output, so that data support is provided for personalized learning. According to the method, learning energy concentration degree monitoring and analysis support is provided, and the problem that it is difficult to continuously, objectively and comprehensively monitor the attention state of a learner on the premise that learning activities are not affected in the prior art is solved.

The invention discloses a chip defect visual detection method, and relates to the technical field of chip defect detection.According to the chip defect visual detection method, real-time correction of optical path deviation is achieved in the image acquisition stage through a multi-angle shooting strategy and a self-adaptive optical adjustment mechanism, and comprehensiveness and consistency of image data are enhanced; meanwhile, a deep denoising network based on a convolutional auto-encoder CAE is introduced, feature distribution of a noise-free image is learned, random noise in the collected image is specifically removed, important detail features of a welding spot region are reserved, a low-contrast region is optimized in combination with an adaptive enhancement technology and histogram equalization in an enhancement stage, and a high-resolution image is obtained. The edge characteristic of the welding spot is more prominent, and the visual definition and the characteristic visibility of the image are remarkably improved; in the feature extraction stage, a multi-scale convolutional network is adopted to capture the edge change of a welding spot crack and the texture characteristics of material degradation, and meanwhile, the detail change of a potential defect area is focused through an attention mechanism, so that the accuracy and efficiency of feature extraction are improved.

A multi-dimensional hydropower station control panel cabinet working condition abnormity monitoring method based on sound recognition is characterized in that a sound pickup, a mutual inductor, an infrared image monitor, a switch node sensor and the like are installed at different positions of a control panel cabinet to acquire multi-dimensional data including voiceprint, voltage, current, temperature, images and switch displacement signals; the voiceprint signals are subjected to pre-emphasis, framing, FFT transformation, Mel frequency filter bank application, MFCC feature extraction and the like, and feature vectors are extracted by using UBM, GMM and MAP algorithms. A PLDA algorithm is adopted for data analysis and fault judgment, multi-dimensional data comprehensive scoring is fused, the fault type is determined, alarm information and processing measures are output, and the system has the advantages of comprehensive multi-dimensional data acquisition, advanced signal processing technology, scientific and accurate fault judgment, high practicability and the like.

The invention discloses a method for collecting orchard ecological environment information, and the method comprises the steps: collecting soil parameters, space environment parameters, insect pest parameters and fruit parameters of an orchard in real time through deploying a plurality of collection devices, and carrying out the collection to form an orchard ecological basic data set; a backstepping model is constructed to indirectly calculate key ecological parameters including soil nutrients, fruit quality and insect pest diffusion trend, and an optimization result is corrected through experimental verification and the model; comparing a backstepping result with an orchard target value to analyze a deviation source, and establishing a macroscopic cause chain through data matching and a visual tool; according to the deviation analysis and the cause chain result, determining an executable regulation and control measure matched with the regulation and control direction; and monitoring the effect after the implementation of the regulation and control measures, verifying the regulation and control effect by comparing the data before and after the implementation of the regulation and control measures, and applying feedback data to iterative optimization of the backstepping model. The method is scientific and efficient and can be used for improving orchard production benefits and ecological environment quality.

The invention discloses a lithium battery surface defect detection method based on deep learning multi-channel fusion. The method comprises the following steps: acquiring a grayscale image and a depth image of a lithium battery surface with surface defects; performing preprocessing, data enhancement and defect labeling on the grayscale image and the depth image to obtain an image data set; training and testing the YoLov8 neural network model according to the image data set to obtain a lithium battery surface defect detection model; and performing lithium battery surface defect detection by using the lithium battery surface defect detection model. According to the invention, through a deep learning method, the efficiency and accuracy of lithium battery surface defect detection are effectively improved; by means of multi-channel fusion of depth information and gray information, the limitation of the gray information is made up, and the learning ability of the model for defect features is enhanced; through data enhancement and application of a complex network structure, the model has better generalization ability and higher applicability.

The invention provides a fixed underground coal mine rock wall vibration monitoring and alarming device and method, and belongs to the field of mine vibration monitoring and early warning. The problems that the mine environment is complex, most collected signals are noisy signals, the monitoring accuracy of a conventional linear fusion algorithm is poor, and full early warning cannot be performed under the condition that obvious crack propagation does not occur are solved. Based on a multi-sensor fusion technology of a linear frequency modulation continuous wave radar and an acoustic emission piezoelectric micro-vibration sensor, through a micro-vibration monitoring system and a ground receiving end, real-time monitoring is carried out on deformation displacement, micro-vibration frequency and energy and seismic source information of a rock mass in combination with multiple sensors; fusion processing is carried out on data of multiple sensors by means of a prediction filtering algorithm, interference of environmental factors on monitoring results is reduced, and efficient and comprehensive monitoring and early warning are achieved.

The invention relates to the field of electrical equipment fault diagnosis, in particular to a switch cabinet defect diagnosis method based on multi-information fusion and a related product, and the method comprises the steps: detecting a switch cabinet by adopting multiple detection methods, and extracting a feature vector from a detection signal; constructing different defect diagnosis models for different detection methods by using the feature set after dimension reduction; obtaining a to-be-detected sample of a to-be-detected switch cabinet through multiple detection methods, and inputting the to-be-detected sample to the corresponding defect diagnosis model; obtaining a basic distribution probability, fusing to obtain a final comprehensive distribution probability, and determining a final prediction result; according to the invention, through combination of multiple detection means, limitation of a single detection method is made up, multiple defect types in the switch cabinet can be identified more comprehensively and accurately, outputs of different defect detection models are fused, and robustness and accuracy of diagnosis are significantly improved.

The invention discloses an intelligent data acquisition and optimization control system applied to a mine filling system, and relates to the technical field of computer automatic control, the system comprises an ore body stress analysis unit, a filling slurry solid phase mass analysis unit, a filling body physical property analysis unit and a filling control and analysis unit; the ore body stress analysis unit is used for establishing a three-dimensional ore body geometric model according to an ore body geological exploration result, dividing the three-dimensional ore body geometric model into finite element grids and calculating the solid phase mass concentration of filling slurry; the filling body physical property analysis unit is used for establishing a rheological model of the filling slurry according to the solid phase mass concentration of the filling slurry; and the filling control and analysis unit is used for calculating the filling stability according to the three-dimensional stress tensor field of the ore body and the pore water pressure of the filling slurry to obtain a stability coefficient. The filling speed can be intelligently controlled, the construction stability is evaluated in real time, and the safety and high efficiency of the filling construction process are ensured.

The invention relates to the technical field of temperature and humidity control, in particular to an intelligent temperature and humidity control method and system for a low-temperature fresh-keeping metal granary. The method comprises the following steps: firstly, acquiring various original data of the metal granary, predicting short-term environmental data in the granary in combination with a TFT model, and providing an accurate prediction basis for temperature and humidity control; secondly, multi-source data fusion is carried out on insect body monitoring images and audio frequency, image and audio frequency information is comprehensively analyzed, and the comprehensiveness and multi-dimensional analysis capability of insect pest monitoring are improved; finally, the accuracy and sensitivity of pest monitoring are improved through a multi-source data recognition model, a temperature and humidity control strategy is optimized in combination with a DQN reinforcement learning model, automatic and intelligent temperature and humidity adjustment is achieved, the environmental conditions in a granary are guaranteed, and the grain storage period is effectively prolonged.

The invention discloses a shallow sea environment intelligent monitoring system and method using multi-buoy combination, and relates to the technical field of marine environment monitoring. The monitoring system comprises an equipment combination module, a response area division module, an area change tracking module, an area correction module and an area detection module, and is technically characterized in that a buoy is divided into a plurality of gradient intervals according to the distance between the buoy and the nearest coast as the standard; then, according to the change condition of the concentration of the detected object along with time in the same gradient interval or different gradient intervals, the movement direction and the movement speed of the detected object are analyzed, so that the diffusion position of the detected object is predicted in advance, a basis is provided for capturing aquatic products or treating the environment, and the variability of the marine environment is adapted; and on the basis of calling the historical diffusion trend of the detection substances with the same or similar concentration from the database, the diffusion trend of the detection substances is corrected, so that the analysis accuracy of the diffusion trend of the detection substances is ensured.

The embodiment of the invention provides a personnel behavior detection method based on multi-modal data and related equipment, and is applied to the technical field of image recognition processing. A to-be-processed video is acquired, and a to-be-processed image frame is extracted from the to-be-processed video. And extracting multi-modal data from the to-be-processed image frame by using a target detection algorithm, a target tracking algorithm and a human body posture estimation algorithm, wherein the multi-modal data at least comprises a personnel detection frame, a personnel image and a personnel posture feature map. And inputting the personnel detection frame, the personnel image and the personnel posture feature map into a pre-constructed abnormal behavior detection model to obtain a behavior detection result output by the abnormal behavior detection model. Image data is obtained from the video data, the personnel action has continuity, and the image data is close to an actual website scene; a multi-modal data fusion abnormal behavior detection model is used to make up for the data limitation and fusion suitability among the personnel image, the detection frame and the attitude feature, so as to improve the behavior abnormality recognition accuracy.

The invention discloses a visual question and answer method based on environmental perception and a knowledge base, and aims to realize an accurate visual question and answer function through a reasoning technology of integrating field specific environmental information and knowledge base information. The method comprises the following steps: firstly, extracting image features by utilizing a ResNet model in visual feature extraction, extracting text features by utilizing a BERT model in text feature extraction, and comprehensively processing the features and context information acquired by an environment perception module through multi-modal fusion; and then, on the basis of the fused multi-modal features, through combination of a Wikdata knowledge base and Seq2Seq, an answer is output in a text form, and visual feedback can be provided. Through environment perception, the system can adjust answers in real time to ensure that the system highly adapts to the current scene, and is applied to the fields of intelligent assistants, aided driving, household robots and the like.

The invention relates to a deep learning framework based on multi-modal data fusion and adaptive learning, which comprises a multi-modal data fusion module, an adaptive learning module and a deep learning model module, fusing in different stages of feature extraction by adopting a plurality of fusion strategies to obtain fused features; the deep learning model module is used for performing feature extraction on data of different modalities according to different depth models, performing prediction according to fusion features obtained by the multi-modal data fusion module, and outputting a prediction result; and the adaptive learning module is used for dynamically adjusting hyper-parameters of the depth model by adopting a learning mechanism. Compared with the prior art, the method has the advantages of providing more comprehensive information representation, self-adaptive learning ability, wider application prospect and the like.

The invention provides a radar monitoring intelligent early warning method and system suitable for forest fire prevention, and relates to the technical field of forest fire prevention. The method comprises the steps of establishing a three-dimensional map, and dividing a to-be-detected area; acquiring forest fire factor data; a forest fire risk assessment model based on the convolutional neural network is constructed, hyper-parameters of the model are optimized by using a Hereum algorithm, and risk grading is performed on the to-be-detected area; fixed radar monitoring is carried out on the high-risk-level area; generating a mobile monitoring path of the low-risk level area; and constructing a prediction model to carry out fire early warning. According to the method, the detection area is finely divided, the high-risk-level area is continuously monitored by the fixed monitoring radar, and the low-risk area is regularly patrolled by the mobile radar, so that the deployment number of the fixed radar is greatly reduced, and the forest fire early warning cost is reduced. And meanwhile, comprehensive monitoring of the whole target forest is realized, and the limitation of a single monitoring means is made up.

The invention relates to the technical field of vehicle detection and identification, and discloses an expressway vehicle detection and identification method based on distributed optical fiber sensing. The method comprises the steps that when a vehicle runs on a detection road section, a distributed optical fiber sensor collects a sensing signal, and first data is generated after preprocessing; dividing all the extended feature information into a plurality of threshold categories based on a multistage binarization technology, marking the threshold categories for the extended feature information, and summarizing based on type labels to generate a feature data table; summarizing all the third data based on the type labels to generate a driving data table; performing data fusion on the feature data table and the driving data table to generate a comprehensive data table, and identifying the foundation type of the detected road section; and constructing a detection and identification model, inputting the extended feature information of the to-be-monitored vehicle into the detection and identification model, outputting vehicle information of the to-be-monitored vehicle, and completing detection and identification of the to-be-monitored vehicle. According to the invention, high precision, high efficiency and high reliability of highway vehicle detection and identification are realized.

The invention discloses an urban street annual green vision rate calculation method based on multi-temporal streetscape images, and the method comprises the steps: generating streetscape sampling points according to road network data, collecting a plurality of temporal streetscape images of each streetscape sampling point covering all seasons of the whole year, carrying out the semantic segmentation of the streetscape images through a deep learning model, and obtaining the annual green vision rate of a city street. And extracting a vegetation region in the streetscape image, and performing mathematical expectation calculation on the green vision rates under different time phases to obtain the annual green vision rate of the urban street. According to the method, annual street view data are accurately collected and processed, and an effective means is provided for scientific evaluation of urban street greening by combining a deep learning technology and an image segmentation technology. According to the method, the urban planning department can be helped to know the greening condition more accurately, important decision support can be provided for subsequent urban greening improvement and street landscape optimization, and meanwhile, the method is high in automation degree and suitable for practical application of large-scale urban greening evaluation.

The invention discloses an aromatherapy intelligent margin calculation method based on vehicle body data dynamic perception. The method comprises the following steps: S1, generating an initial data set; s2, inputting the initial data set into a multi-channel variational encoder, and outputting hierarchical feature representation; s3, inputting the hierarchical feature representation into a spatio-temporal context sensing module to generate spatio-temporal feature representation; s4, inputting the spatial-temporal feature representation into a heterogeneous feature mapping layer to generate a unified data representation; s5, inputting the unified data representation into a dynamic prediction regulation and control module, and generating an optimized feature representation; s6, inputting the optimized feature representation into an aromatherapy residual amount prediction model, and performing residual amount prediction by using a Gaussian mixture process; s7, inputting an aromatherapy residue prediction result into a feedback integrator, and carrying out self-supervised learning; and S8, integrating to a vehicle-mounted system, displaying an aromatherapy allowance state and sending a personalized notice. According to the method, accurate prediction and calculation of the vehicle-mounted aromatherapy allowance are realized by utilizing multi-channel variational coding, spatio-temporal context perception, a Gaussian process and the like.

The invention discloses a permanent magnet generator air gap eccentricity fault identification method and system, relates to the technical field of permanent magnet generators, and uses wavelet transform to extract time-frequency features and generate multi-band feature vectors, so that the system can more sensitively identify subtle features of air gap thickness deviation. And the extraction and analysis precision of characteristic signals of different frequency bands is effectively improved. And secondly, analyzing the air gap thickness deviation condition based on the feature vector, constructing an eccentricity degree index, and quantifying the eccentricity degree, so that the severity of the air gap eccentricity fault of the permanent magnet generator can be intuitively judged. And when the eccentricity degree exceeds a set threshold value, the system automatically sends a fault type checking instruction, so that the fault detection process is more intelligent. Afterwards, abnormal changes of all positions are analyzed through infrared thermal data and temperature gradients, air gap foreign matter faults possibly causing air gap eccentricity are further recognized, and the limitation of single signal analysis in traditional detection is made up.

The invention discloses a plug-in-based real-time acquisition and manual analysis method for webpage data without a fixed format. Real-time integrated operation of data acquisition, labeling and uploading is realized through a browser plug-in. A user selects target data through a floating window interface, and a plug-in automatically extracts content, identifies a platform source, performs quick labeling in combination with a preset analysis label and uploads the data to a background. According to the method, the flexibility of manual judgment and the high efficiency of an automation technology are fused, and the method can adapt to multiple platforms including high-protection dynamic webpages without developing a customized tool for a target website. The floating window supports operations such as dragging and zooming, so that the user experience is improved; the labeling is completed by data acquisition, so that the processing chain is effectively shortened, and the efficiency and accuracy are remarkably improved. The system supports authority management, encrypted transmission and real-time statistical analysis, and ensures data security and efficient utilization.

The invention discloses a production optimization method and system for animal blood-made protein powder, particularly relates to the technical field of production monitoring, and aims to solve the problem that the existing method is difficult to effectively identify the potential hidden danger of the cavitation effect caused by ultrasonic waves in the production process of the animal blood-made protein powder. The method comprises the following steps: capturing harmonic characteristics of ultrasonic signals, and identifying an acoustic energy dense region in combination with a spectrum analysis algorithm; constructing a turbulence disturbance intensity graph model, and analyzing the distribution characteristic change of the dissolved gas in combination with a graph embedding learning algorithm; determining a cavitation potential risk area based on the identified first and second potential risk areas; in the cavitation potential risk area, the comprehensive influence of the bubble group synergistic effect and the heat effect is evaluated by analyzing the complexity of bubble interaction energy distribution and the diffusion degree of local high temperature; and finally, determining a cavitation hidden danger caused by ultrasonic waves by calculating a cavitation influence coefficient, and optimizing production process parameters according to a determination result.

The invention discloses a real estate registration-oriented business data integration method and system, and relates to the technical field of real estate registration data integration processing. The real estate registration-oriented business data integration method comprises the following steps of: obtaining identification information, property proving information, land use information and transaction record information of a real estate to be registered, and establishing a real estate initial registration data table; acquiring current state information of the real estate to be registered, analyzing a terrain development index, a land area development index, an environment quality index, an infrastructure convenience index, a regional market economic index and a comprehensive development index, and fusing and storing the indexes into a real estate initial registration data table; according to the method, the comprehensive development index is constructed by calculating multiple indexes such as the terrain development index, the land area development index, the environment quality index, the infrastructure convenience index and the regional market economic index, the development potential of the real estate is systematically quantified, and the comprehensive value and the development potential of the real estate can be reflected.

The invention relates to a monitoring index prediction method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: collecting current monitoring data of the distributed storage system; performing position coding processing on the current monitoring data to obtain processed monitoring data; inputting the processed monitoring data into a first monitoring index prediction model in pre-trained monitoring index prediction models to obtain a first monitoring index prediction result of the distributed storage system, and inputting the current monitoring data into a second monitoring index prediction model in the pre-trained monitoring index prediction models to obtain a second monitoring index prediction result of the distributed storage system, obtaining a second monitoring index prediction result of the distributed storage system; and obtaining a target monitoring index prediction result of the distributed storage system according to the first monitoring index prediction result and the second monitoring index prediction result. By adopting the method, the monitoring index prediction accuracy can be improved.

The invention discloses an electroencephalogram multi-index network standardized modeling method which comprises the following steps: S1, adopting a multi-country electroencephalogram cross-spectrum data set based on a large-scale full life cycle as original electroencephalogram data, calculating a cross-spectrum matrix of the original electroencephalogram data, and preprocessing the original electroencephalogram cross-spectrum matrix; s2, constructing a weighted undirected network by using the preprocessed original electroencephalogram cross spectrum matrix to serve as a brain function network; s3, calculating network features of three dimensions of brain network function integration, function separation and centrality of the brain function network, and establishing an evolution trajectory of the network features; and S4, designing an interpretable lightweight neural network regression model, and reconstructing upper triangular elements of the brain function network to obtain a complete brain function network, namely a normalized brain function network corresponding to the age. The invention further discloses an electroencephalogram multi-index network standardized modeling system. The principle of the brain function network can be reflected more accurately.

The invention discloses a three-dimensional visual monitoring method for the underground water level of a deep foundation pit. The method comprises the steps that a three-dimensional underground enclosure wall of the deep foundation pit is generated; automatically generating and updating a pit inside and outside water level fitting three-dimensional curved surface diagram in the three-dimensional underground enclosure wall of the deep foundation pit; automatically identifying and marking the highest point and the lowest point of water levels inside and outside the pit; marking the burial depth of the underground safe water level of the deep foundation pit; the three-dimensional position of the relief well in the open state is automatically generated and updated; and three-dimensional visual monitoring is conducted on the underground water level of the deep foundation pit according to the three-dimensional curved surface graph fitted by the water levels inside and outside the pit, the highest point and the lowest point of the water levels inside and outside the pit on the three-dimensional curved surface graph and the three-dimensional position of the in-pit decompression well in the open state. According to the method, the underground water level of the deep foundation pit can be visually monitored, and the comprehensiveness, accuracy and timeliness of monitoring are improved.

The invention relates to the technical field of data processing, in particular to a construction method and system for a neural rehabilitation evaluation model. The method comprises the following steps: acquiring multi-modal data of a neurological rehabilitation patient; performing feature extraction according to the multi-modal data of the neurological rehabilitation patient to obtain multi-modal feature data of the neurological rehabilitation patient; performing data classification on the multi-modal feature data of the neurological rehabilitation patient to obtain multi-modal feature classification data; and marking the multi-modal feature data of the neurological rehabilitation patient by using the multi-modal feature classification data to obtain multi-modal feature marking data of the neurological rehabilitation patient so as to carry out neurological rehabilitation evaluation model construction auxiliary work. According to the method, the model capable of comprehensively and objectively evaluating the rehabilitation progress of the neurological rehabilitation patient is constructed in an auxiliary manner, so that a scientific basis is provided for rehabilitation treatment.

The invention relates to a coal slime flotation froth three-dimensional model classification method based on a Pointnet network, and aims to solve the technical problem that the current two-dimensional froth image cannot process the states of three-dimensional froth space fluctuation and the like and the internal relationship of the space, and the technical scheme is as follows: expanding a data set; designing a foam characteristic network architecture; extracting a high-dimensional feature lambda 1 by using a point cloud feature extractor f theta; projecting the high-dimensional feature lambda 1 into a low-dimensional space by using a feature projection head # imgabs0 # to obtain a low-dimensional feature lambda 2 of the single-groove foam point cloud; splicing and fusing the single-groove foam point cloud features by using the feature fusion function yf to obtain an overall feature gamma; classifying the overall feature gamma through a multi-layer perceptron (MLP) and a Softmax function, and outputting a classification result; evaluating and analyzing. According to the method, the foam three-dimensional point cloud models of a plurality of flotation cells are used as input, the limitation of a single-cell data source is made up, the generalization ability and stability of the model are improved by using the flotation machine overall feature training network, and the performance of the model is optimized.

The invention relates to the technical field of separation layer micro-crack analysis, and provides a separation layer micro-crack analysis system based on a material point method.The method comprises the steps that firstly, a data acquisition module is used for acquiring data such as stress, strain, displacement and acoustic emission signals from a carbonaceous shale sample; the preprocessing module preprocesses the collected data to ensure the accuracy of subsequent analysis; the material point modeling module constructs a discrete material point model according to the processed data, and simulates the mechanical behavior of the carbonaceous shale sample; the micro-crack identification module is responsible for analyzing crack characteristics in the material point model and identifying geometric morphology and spatial distribution of micro-cracks; the crack evolution analysis module further perfects the crack network model by calculating the crack expansion and convergence process; the bed separation judgment module evaluates whether the sample has bed separation or not by combining the change of damage degree and complexity based on the evolution characteristics of the fracture network; and finally, the result output module summarizes and outputs various analyzed result data. Finally, the method is only the preferred embodiment of the invention and is not used for limiting the method, and any modification, equivalent replacement, improvement and the like made within the spirit and principle of the method should be included in the protection range of the method.

The invention provides a man-machine collaborative program repairing method based on a large language model, relates to the technical field of automatic program repairing, and remarkably improves the accuracy and success rate of program repairing. According to the method, a large language model is guided through preliminary analysis of manual teaching, errors in a program can be more accurately positioned and repaired by combining a repairing process of multiple iterations and more information introduced step by step, misjudgment and omission are reduced, and the program repairing efficiency is greatly improved. Compared with a traditional method, blind exploration of a large language model on complex problems is avoided through a man-machine cooperation mode, time and computing resources are saved, and adaptability of program repair is enhanced. According to the method, program defects of various types and complexity can be handled, and simple grammar errors or complex logic errors can be effectively handled through a step-by-step deep repair process.