1093results about How to "Accurate analysis" patented technology

The invention provides a method and system for enhancing wafer detection in a semiconductor manufacturing process, and relates to the technical field of wafer detection, and the method comprises the steps: transmitting dual-frequency laser to the surface of a wafer to form a controllable overlapping region, and collecting a beat frequency signal to obtain initial height information; carrying out adaptive filtering processing on the beat frequency signal, reconstructing a three-dimensional contour of the surface of the wafer, and generating an initial defect distribution diagram; and determining a secondary detection area according to the initial defect distribution diagram to perform orthogonal scanning, identifying and rejecting pseudo defect signals, extracting defect features, and determining defect cause types. According to the invention, the accuracy and efficiency of wafer defect detection are improved, and the semiconductor manufacturing quality can be improved.

According to the multi-energy complementary power distribution system data analysis method based on deep learning, firstly, preprocessing and feature extraction are carried out on multi-source heterogeneous sensor data, and key indexes reflecting the health state of equipment are obtained; and obtaining globally consistent equipment state representation through a spatio-temporal data fusion technology. And then a multi-fault mode knowledge base is constructed, and a multi-label classification algorithm of deep learning is adopted to identify fault types. And finally, establishing a mapping relation between an equipment topological structure and a fault propagation path by using an attention mechanism and a graph convolutional network, and reasoning a specific position of equipment damage through fault traceability and influence analysis. The robustness and generalization ability of the model are improved by adopting methods of data enhancement, transfer learning and the like, and real-time and reliable fault location is realized through edge calculation. According to the method, the equipment fault in the multi-energy complementary power distribution system can be accurately positioned, and the reliability and safety of the system are improved.

The invention provides a power anomaly detection method and system based on multi-mode special collaborative causal thinking chain reasoning, and relates to the technical field of power anomaly detection. Comprising the following steps: acquiring an embedded representation of multi-modal data in power equipment, inputting the embedded representation into a general model, and generating a framework of a causal chain; the power exclusive model is based on a framework of a causal chain, each node of the causal chain is refined layer by layer, detail information is supplemented, key factors are filled, and a causal graph is obtained; inputting the causal graph into a hypergraph neural network, mining high-order association in data through multi-layer convolution operation, and updating embedded representation of nodes in the causal graph to obtain an updated causal graph; and on the basis of the embedded representation of the nodes in the updated causal graph, calculating the potential risk influence of the nodes, and determining abnormal nodes. According to the method, a general model and an electric power exclusive model are combined, efficient and accurate abnormal causal chain reasoning is realized by integrating multi-modal data, and the accuracy and effectiveness of electric power anomaly detection are improved.

The embodiment of the invention discloses a bridge bolt monitoring image recognition method and system based on deep learning, and belongs to the technical field of bridge image processing. The method comprises the following steps: acquiring a multi-angle monitoring image set of a bridge bolt part through an image acquisition device, and preprocessing the monitoring image set to generate a standardized target image sequence; positioning a bolt monitoring area for each image frame in the target image sequence based on a pre-trained positioning model, and generating an area coordinate set containing bolt position information; inputting the region coordinate set into a state recognition model, extracting structural state features of each bolt monitoring region, and generating a looseness degree prediction result of the bolt part according to the structural state features; according to a matching result of the looseness degree prediction result and a preset safety threshold range, a bolt state abnormity alarm signal is output; and associating the bolt state abnormity alarm signal to the corresponding monitoring image frame, and generating a monitoring report containing a visual mark.

The invention provides a power distribution network symbiotic simulation system and method based on digital twinning. The system comprises a power distribution network digital twinning simulation platform, a cloud edge hierarchical deployment collaborative architecture and a power distribution network terminal. The digital twinborn simulation platform for the power distribution network comprises a data layer, a model layer, a service layer and an application layer which are covered in sequence by taking a cloud platform as a bottom, and the cloud edge hierarchical deployment collaborative architecture performs hierarchical deployment according to different service functions of the power distribution network. According to the invention, through the constructed full-attribute isomorphic power distribution network digital twinborn simulation platform and the cloud edge hierarchical deployment collaborative architecture, the fusion demand of multi-scene multi-service flow is fully considered, through the symbiotic simulation technology, dynamic feedback and collaboration between the simulation system and a real system are realized, and the highly integrated and collaborative simulation system has the advantages of high simulation efficiency and high reliability. Various changes in the power distribution network can be quickly responded, and a solid guarantee is provided for safe and efficient operation of the power distribution network.

The invention relates to the technical field of medical image analysis, in particular to a tumor partition recognition method and system based on multi-scale image analysis, and the method comprises the following steps: based on an input medical tumor partition image, defining the gray value distribution range of pixel blocks, dividing pixel block groups according to a fixed size, and calculating the neighborhood gray values of the pixel blocks, and determining a distribution change set through accumulation of gray difference values of the pixel block groups, and generating a multi-scale gray distribution diagram. According to the invention, by calculating the gray value distribution and the gray difference value of the pixel block group, enhancing the image detail identification of the tumor area, improving the tumor boundary analysis capability, analyzing the texture feature difference of the boundary area, quantifying the gray gradient difference value and the connection characteristic, improving the geometric characteristic analysis precision, and combining the space geometric expansion data and the texture characteristic, the tumor boundary analysis precision is improved. Partitioning precision and image analysis accuracy are improved, misrecognition of a boundary fuzzy region is effectively avoided, and a finer tumor heterogeneity research basis is provided.

The invention discloses a coal mine dust diffusion intelligent monitoring method based on a distributed sensing network, and relates to the technical field of coal mine dust diffusion intelligent monitoring, and the method comprises the following steps: deploying a plurality of sensing nodes in a coal mine, each node having a function of collecting environmental data, a distributed sensing network is formed through a wireless or wired communication module, and when all nodes are started, a unique node identifier is issued through a central controller, and self-inspection is carried out. Through bidirectional delay calculation and a progressive fine tuning strategy, high-precision time synchronization is achieved, and it is ensured that timestamps of data such as dust concentration and airflow are accurate and reliable. And data jump caused by large correction is avoided through gradual fine adjustment, data continuity is guaranteed, and the precision of dust diffusion analysis and an early warning model is improved. A redundant node management and automatic switching mechanism improves the fault processing capability of the system, avoids a monitoring blind area, accelerates maintenance response through fault information reporting, and ensures stable operation of a monitoring network.

The invention discloses an intelligent security and protection monitoring method and system based on image recognition. The method comprises the following steps: S1, acquiring multi-modal data; s2, performing preprocessing to generate complete target information; s3, performing real-time detection on the generated complete target information, and performing primary processing on a conventional scene; s4, based on an improved visual SLAM technology, obtaining three-dimensional information of multiple cameras; s5, when the edge device detects a potential abnormal condition, performing abnormal behavior analysis on the data by using a Swin Transform model, and optimizing a detection result in combination with the three-dimensional information of the multiple cameras; s6, performing adaptive learning on historical data by using a depth deterministic strategy gradient algorithm, and dynamically adjusting a threshold value of abnormal behavior detection; and S7, after an abnormal condition is detected, processing data through differential privacy protection and an end-to-end encryption technology, automatically controlling security and protection equipment, and giving a real-time alarm. According to the invention, image recognition and deep learning technologies are fully utilized, and accurate real-time monitoring in a complex scene is realized.

The invention relates to the technical field of hydrological data analysis, in particular to a dynamic hydrological coupling data analysis method and system for a complex watershed. The method comprises the following steps: acquiring historical meteorological data, historical hydrological data and historical remote sensing data, and performing hydrological cycle simulation analysis to generate a rainfall-evaporation-permeation-runoff hydrological cycle simulation model; performing drainage basin gridding processing on the rainfall-evaporation-permeation-runoff hydrological cycle simulation model to generate a hydrological cycle gridding model; obtaining actually measured meteorological data and actually measured hydrological data, and carrying out space-time simulation division and hydrological space-time correlation analysis to obtain a hydrological change space-time correlation correlation relationship among the sub-partitions of each drainage basin; and performing drainage basin space-time coupling early warning processing on the hydrological cycle gridding model to generate a hydrological change space-time coupling early warning response result corresponding to the complex drainage basin. The method can accurately analyze and predict the hydrological change and the mutual coupling relation thereof in the complex watershed.

The invention provides a smart park optimization method and device based on digital twinning and BIM, and the method comprises the steps: collecting the actual information of a park, and carrying out the preprocessing; based on the configured basic BIM model, integrating the basic BIM model by using actual information; constructing a three-dimensional digital twinborn model, and fusing the integrated BIM model with the three-dimensional digital twinborn model; and analyzing and processing the park operation data by using the current fused three-digit digital twinborn model so as to realize park optimization. The digital mirror image of the smart park is constructed by integrating digital twinning, BIM, Internet of Things, big data, cloud computing, GIS and other frontier technologies, and comprehensive perception, accurate analysis, intelligent decision and efficient management of the park are realized. According to the scheme, the intelligent level, the operation efficiency and the sustainable development capability of the park are improved, and convenient, efficient and intelligent service experience is provided for park managers, settled enterprises and individual users.

The invention discloses an event analysis method, system and device based on task generation and multiple modes, which are used for quickly and accurately mastering the development trend of an event. The method comprises the steps that structured event information is generated through multi-modal data, and an event relation is obtained; constructing an event graph; extracting a multi-modal feature, and obtaining a multi-modal emotion relationship vector by using a cross-modal attention mechanism; based on a preset graph neural network, combining the event graph to obtain an emotion feature vector; calculating a comparative learning loss value, and obtaining a target emotion feature based on the comparative learning loss value; generating a target event atlas by using a cross-modal attention mechanism; extracting relation characteristics, and combining the attention weight and a preset time sequence model to obtain an event prediction map; extracting a causal chain and reasoning, and obtaining a trigger condition and an emotion factor after reasoning; and combining the event prediction map and the target event map with the node feature sequence, the trigger condition and the emotion factor to obtain an event analysis result.

The invention provides a heart multi-mode digital twinning simulation method and system, electronic equipment and a medium, and belongs to the technical field of digital twinning. The method comprises the following steps: S1, collecting multi-modal data of a heart; s2, preprocessing the acquired multi-modal data to obtain heart digital data; s3, based on the heart digital data, constructing a multi-modal digital twinborn model of the heart and optimizing the multi-modal digital twinborn model; s4, performing real-time simulation on the electrophysiological activity of the heart by using the optimized multi-modal digital twin model and using a Runge-Kutta method in combination with a PSO (Particle Swarm Optimization) algorithm; s5, based on the optimized multi-mode digital twinborn model and the simulation result, simulation and planning of virtual cardiac surgical treatment are carried out; and S6, dynamically evaluating the multi-modal digital twin model, and monitoring the state change of the heart in real time. According to the heart multi-mode digital twinborn simulation method and system, the electronic equipment and the medium, efficient simulation and real-time monitoring of the heart state can be achieved.

The invention relates to the technical field of optical signal processing, in particular to an optical signal processing algorithm based on biological agent fluorescence detection, which comprises the following steps: S1, collecting fluorescence signals with different wavelengths emitted by each probe, and generating a multi-channel fluorescence spectrum data set; s2, carrying out spectral de-mixing on the fluorescence signals in the fluorescence spectrum data set, separating a plurality of overlapped fluorescence signals, and decoupling the fluorescence signals with different wavelengths; s3, for highly overlapped fluorescence signals, carrying out secondary overlapping separation treatment on the fluorescence signals by using a nonlinear optimization method; s4, extracting the intensity, wavelength and time change characteristics of each fluorescent probe signal, and constructing a multi-dimensional fluorescent signal characteristic vector; and S5, by amplifying the characteristic peak value of the weak fluorescence signal, it is ensured that the signal is not covered by strong signals of other probes in multi-probe detection. According to the invention, the resolution of fluorescence detection is improved, so that the high-precision detection effect can be maintained under complex experimental conditions.

The invention discloses a power business scheduling method and system based on 5G communication grading and classification, and relates to the technical field of 5G slicing. According to the method, the prediction model and the real-time monitoring data are utilized to effectively predict the network flow and dynamically adjust the network resources according to different levels of power business requirements, so that the power business with high priority can quickly obtain necessary network support, the quality of the overall network service and the operation efficiency of the power business are improved, and the network flow is effectively predicted. And network resource allocation is optimized through the graph neural network, accurate analysis and response to power service grading are realized, predictability and stability of the network are enhanced, and more complex power service application is supported.

The invention relates to an electric power meteorological disaster risk early warning method and system based on artificial intelligence. The method comprises the following steps: cleaning and preprocessing basic meteorological data including temperature, humidity, wind speed and precipitation to obtain a cleaned basic meteorological data set; on the basis of satellite cloud picture or radar image data, meteorological changes are modeled through a neural network model, assimilation features are obtained, and the basic meteorological data and the assimilation features are spliced to form a joint feature vector; and constructing a comprehensive disaster risk assessment model based on the meteorological factors, the power grid factors and the geographic information, carrying out training and multi-objective optimization on the comprehensive disaster risk assessment model, and carrying out real-time electric power meteorological disaster risk early warning by using the optimized comprehensive disaster risk assessment model. According to the invention, meteorological data, power grid equipment states and geographic information can be monitored in real time, meteorological disasters possibly suffered by power equipment can be accurately warned, and the safety and stability of a power system are improved.

The invention relates to the technical field of fan blade detection, and provides a wind power plant fan blade detection method and system based on three-dimensional point clouds, and the method comprises the following steps: carrying out the multi-angle scanning of a fan blade through a laser scanner, and obtaining the three-dimensional point cloud data of the fan blade; performing registration processing on the three-dimensional point cloud data, and unifying the three-dimensional point cloud data into the same coordinate system to obtain registered point cloud data; performing block acceleration processing on the registered point cloud data by adopting an octree partitioning algorithm to obtain block acceleration point cloud data; performing feature extraction and feature segmentation on the block acceleration point cloud data to obtain a key feature region of the fan blade; performing defect identification analysis on the key feature region based on a point cloud network enhancement model to obtain a defect detection result, the defect detection result comprising a defect position and a defect type; and generating a detection report containing the defect position and the defect type, and visually displaying the detection report. According to the invention, the integrity of data acquisition and the precision of defect identification are improved, and the efficiency of fan blade detection is improved.

The invention relates to the technical field of fermentation control, in particular to an intelligent optimization control system of an aroma-enhancing compound leavening agent, which comprises a strain culture selection module, a fermentation process monitoring module, an environment optimization adjustment module and a fermentation effect evaluation module. According to the method, accurate analysis and optimization of microbial reaction in the fermentation process are realized, the selection efficiency of the strain culture combination is improved, the fermentation process can be carried out under the optimal condition, the efficiency of biological reaction is remarkably improved, potential risks and behavior abnormalities can be recognized in time through analysis of time sequence data, and the safety of the fermentation process is improved. The fermentation control process is optimized by dynamically adjusting key parameters, environmental parameters are adjusted through a nonlinear regression model and monitored in real time, the environmental stability is enhanced, it is ensured that the fermentation process is continuous and efficient, data of the whole process are comprehensively analyzed, the fermentation effect is accurately evaluated, multiple performance indexes are quantified, and the quality of a leavening agent is improved.

The invention relates to the technical field of artificial intelligence and the field of financial science and technology, and discloses a service content generation method based on emotion recognition, and the method comprises the steps: collecting voice data, extracting voiceprint features, and building a user voiceprint file; extracting Mel frequency cepstrum coefficient features and Mel energy difference coefficient features, and inputting the extracted features into an emotion classification model for emotion classification recognition to obtain an emotion state of the user; the current emotional state is compared with a historical normal emotional state, emotional fluctuation is analyzed, and whether the emotional state of the user is abnormal or not is judged; and when it is detected that the emotional state is abnormal, target service content is determined from the personalized service library in combination with the emotional state and the user voiceprint file. According to the method, the voice features are extracted and the user voiceprint file is established, so that the emotion fluctuation of the user can be accurately analyzed, whether abnormity exists or not is judged, accurate recommendation service is provided in combination with the personalized features and historical behavior data of the user, and the intelligent and personalized degree of vehicle-mounted voice interaction is improved.

The invention relates to the technical field of robots, in particular to a user intention alignment robot task planning method based on a large language model, and the method comprises the steps: firstly receiving human task voice, carrying out the textualization processing of the voice, carrying out the human instruction ambiguity elimination through combining with a robot task environment, and generating a feasible instruction candidate set; and then calling the maintained user feature memory module by the large language model, and further screening the candidate instructions in combination with human user preferences. And finally, the large language model decomposes and plans the reserved task instruction, guides the robot to execute the task, collects human feedback information in the task process, and is used for optimizing and updating the user feature memory module and guaranteeing the task planning continuity of the large language model driven by reflection feedback. According to the method, when the service robot based on the large language model carries out task planning, the instruction intention of the human user is analyzed and aligned more accurately, and customized services are better provided for the human user.

The invention provides an electronic evidence correlation analysis method which comprises the following steps: analyzing and standardizing heterogeneous data of electronic evidences, extracting timestamp information according to data source characteristics, and uniformly converting data of each time precision into millisecond-level timestamps; extracting space information, including a physical space and a virtual space, according to the timestamp, and performing format unification and coordinate system conversion on the extracted information to obtain a comprehensive data set containing a standardized time sequence and multi-scale space information; constructing a space-time association graph model based on the electronic evidence group, setting the weight of an edge in combination with the space-time association distance between nodes, mapping the high-dimensional space-time association feature to a low-dimensional vector space, and obtaining the space-time association feature vector of the electronic evidence; and performing similarity calculation on the space-time association feature vectors, calculating the space-time association degree between different electronic evidences, and screening out associated electronic evidences as electronic evidence pairs according to a similarity threshold to form an association relationship network.

The invention discloses an intelligent financial question and answer system based on a large language model, and relates to the technical field of financial question and answer, the system solves the problems of financial term ambiguity and context ambiguity through cooperative work of a plurality of modules, and the system comprises the following modules: a context recognition module, a query module and a query module, a natural language processing algorithm is combined with a context analysis technology in the financial field to automatically extract context clues in user questions; and a financial term knowledge base module. According to the method, context recognition and a financial term knowledge base are combined, and the accuracy of understanding the term ambiguity and the complex context is improved through the graph neural network. And the intelligent recommendation module dynamically provides personalized financial suggestions by using collaborative filtering and content recommendation algorithms in combination with user history and market data, and performs real-time adjustment. The risk assessment and prompt module assesses risks through a Bayesian network and a logistic regression model, and the adaptive learning module continuously optimizes risk prediction and helps users to avoid financial risks.

The invention provides an ultrafast laser heat dissipation state real-time monitoring system based on cloud computing, and relates to the technical field of laser heat dissipation, and the system comprises a laser monitoring module which is used for transmitting ultrafast laser and is internally provided with a temperature sensor so as to monitor the working temperature of a laser in real time; the data acquisition module is used for being connected with the laser monitoring module, acquiring temperature data and key parameters, including laser power and working current, of the temperature sensor in real time, and uploading the temperature data and the key parameters to the cloud server; and the cloud analysis module is used for receiving and analyzing the temperature data and the key parameter data, identifying an abnormal temperature mode, predicting a potential overheating risk and calculating heat dissipation efficiency to obtain an analysis result. According to the invention, comprehensive, real-time and intelligent management of the heat dissipation state of the laser is realized, the operation stability and safety of the laser are effectively improved, the overheating risk is reduced, the heat dissipation efficiency is optimized, and remote monitoring and data analysis services are provided for users.

The invention relates to the technical field of television image communication, in particular to a user information input method and system in an intelligent television all-in-one machine. The method comprises the following steps: collecting a user image, carrying out white balance correction and focusing processing, generating a moving object focusing image, carrying out identification and attention tendency analysis on a character in the focusing image, obtaining character tendency data, analyzing a historical interaction image, identifying an interaction mode and constructing a user intention prediction model, and obtaining a user intention prediction result. And when the tendency data shows that the user preferences the television content, intention drilling and auxiliary adjustment are performed on the current image based on the prediction model, predicted user input information is generated, logic conflicts in the predicted information are detected, feedback optimization is performed, and final user input information is output. According to the invention, a more accurate and more flexible user information input method is realized.

The invention particularly relates to a data analysis method and system. The method comprises the steps of extracting original data corresponding to a target service from a target data source according to a pre-configured data extraction strategy of the target service, loading the original data to an operation data storage layer of a data warehouse, and storing the original data; operating a data storage layer to output the original data to a detail data layer; the detailed data layer performs data preprocessing on the original data to obtain basic data and outputs the basic data to the summarized data layer; the summarizing data layer performs aggregation processing on the basic data according to a current data processing task corresponding to the target business, obtains structured data corresponding to the target business, and outputs the structured data to the application data service layer; and the application data service layer performs data analysis on the structured data according to the service configuration information corresponding to the current data processing task, and outputs a corresponding data analysis result. According to the scheme, efficient and accurate data management and analysis can be realized.

The invention discloses a big data read-write adaptive method based on a decision algorithm and a big data read-write system, and belongs to the technical field of intelligent decision of a data center, high-speed read-write operation of data is processed in real time in a service system, and a data read-write strategy and resource allocation are dynamically adjusted by analyzing a data access mode and a system load condition; data are preloaded through an intelligent prefetching strategy, and the storage and access paths of hotspot data are optimized, so that the waiting time of a user and the consumption of system resources are reduced. According to the method, data management can be simplified, data access efficiency can be improved, data consistency and security can be enhanced, the problem of multi-database management and query complexity faced by enterprises can be effectively solved, and more efficient and more consistent data access and management experience can be provided for the enterprises.

The invention discloses a user social behavior-based public opinion propagation prediction method and system. The method comprises the following steps of S1, perfecting and dividing data set categories according to data set forms and contents; s2, performing sentiment analysis according to the content of the comments forwarded by the user, and performing preliminary clustering on themes of the tweets forwarded by the user; s3, fusing with user theme features, and performing feature construction; s4, constructing a feature module of the user node, and pruning the whole social network according to the propagation condition; s5, calculating the credibility degree and the susceptibility degree of the user according to the historical forwarding data to construct a mask matrix, and performing similarity evaluation on the propagation network of the specified event; and S6, constructing a propagation prediction result evaluation index. According to the method, the dependency and independence of the user are combined, the user topic features are combined, the user node features with more practical significance are obtained, and compared with traditional public opinion analysis and prediction, the method has higher accuracy.

The invention, which relates to the technical field of network security protection, discloses a photovoltaic power station 5G network security protection device comprising the following components: a data acquisition module, an intelligent fusion analysis and verification system and a protection mechanism triggering module. According to the invention, by integrating an intelligent fusion analysis and verification system, multi-dimensional data such as photovoltaic power station operation data, 5G network characteristic parameters, external environment factors and personnel operation behaviors can be comprehensively collected and deeply analyzed, and a potential association relationship and a mutual influence mechanism among different factors can be accurately mined; meanwhile, a dynamic association rule self-adaptive updating mechanism can adjust the association rule in real time according to newly collected data and a mined new association relationship, the accuracy and timeliness of an analysis result are ensured, the credibility of the data is improved, and network security risks can be found and coped with in time.

The invention relates to an electrochemical impedance acquisition method based on a time sequence model and an electrochemical impedance model. The method comprises the following steps: constructing an experimental test matrix taking a battery material system, temperature, SOC and the like as variables; performing charging and discharging test on the battery according to the experimental test matrix; after the battery stands, current excitation is applied through an electrochemical workstation, real electrochemical impedance spectroscopy data are obtained, parameter identification is carried out, and a model training label is extracted; extracting features of the process data of the charging and discharging test, and constructing an electrochemical impedance data set; based on a time sequence pre-training basic model, training by utilizing the electrochemical impedance data set to obtain an electrochemical impedance model; and predicting the electrochemical impedance spectrum of the battery to be detected by adopting the trained electrochemical impedance model. Compared with the prior art, the method has the advantages that the time sequence large model and the electrochemical impedance model are combined, efficient acquisition and accurate analysis of the electrochemical impedance spectrum are realized, and the method has wide application potential in real-time monitoring and dynamic application environments.

The invention discloses a multi-modal emotion prompting method and system for an online auxiliary voice dialogue scene, and relates to the technical field of artificial intelligence, voice signals in the voice dialogue scene are input into a trained multi-modal emotion prompting large model, and emotion labels and voice emotion prompting information are output; the training process of the multi-modal emotion prompt large model comprises the following steps: acquiring original voice data of a real dialogue scene to construct a training data set for emotion recognition; performing feature extraction on the original voice data in the training data set to obtain an original voice feature vector; inputting the original voice feature vector into a sparse bridging Transform module, and outputting a fusion feature; inputting the fusion features into a large language model, generating coherent voice emotion prompt information through text decoding, and associating with corresponding emotion tags; according to the multi-mode emotion prompting method and system, accurate analysis and prompting of voice emotion in an online auxiliary voice dialogue scene are realized.

The invention relates to the technical field of ring piece rolling, and discloses a large special-shaped ring piece rolling forming process analysis method which comprises the following steps: (1) forge piece and blank design: designing different types of blanks; (2) material characteristic modeling: establishing a material model meeting rolling conditions; (3) finite element model establishment: establishing a geometric model of a rolling process by utilizing finite element analysis software; (4) rolling process scheme design: designing a plurality of rolling process schemes; (5) process simulation and defect prediction: analyzing strain, stress, temperature field and metal flow conditions in the simulated rolling process, and analyzing defect generation conditions; and (6) real-time monitoring and feedback control: monitoring changes of stress, strain and temperature in real time, and automatically adjusting process parameters. And through dynamic material characteristic modeling, a self-adaptive grid division technology and multi-physical field coupling analysis, the analysis accuracy of the rolling process is improved, so that defect prediction is more accurate, and the quality of finished products is improved.