2245results about How to "Improve targeting" patented technology

The invention provides a digital factory operation virtual simulation teaching method and system, and relates to the technical field of smart factories, and the method comprises the steps: collecting factory operation data, carrying out the standardization processing and correlation analysis, constructing a multi-dimensional data model, carrying out the feature extraction and semantic mining of the hierarchical data of each dimension, and constructing a multi-level digital twin factory model. Carrying out dynamic modeling, constructing a personalized knowledge graph, generating a learning demand list, matching the learning demand list with a digital twin factory model, and generating a multi-dimensional simulation environment; in the multi-dimensional simulation environment, performing analysis and intention recognition on an operation instruction of the learner, converting the operation instruction into a virtual operation, calculating a normative score of the virtual operation, generating corresponding feedback information based on the normative score and the personalized knowledge graph, updating model parameters based on a response of the learner to the feedback information, and performing simulation on the learner according to the updated model parameters. And completing iteration of the model.

The invention relates to the technical field of monitoring and early warning of power equipment, in particular to a monitoring and early warning method and system for substation power equipment. Comprising a data acquisition module, an intelligent diagnosis module, a risk assessment module, a collaborative early warning module and an interaction control module. The data acquisition module acquires equipment operation data including current, voltage, temperature and humidity and vibration signals. And the intelligent diagnosis module identifies equipment abnormity through the generative adversarial network and the graph neural network. The risk assessment module generates a risk assessment curve based on a fractional order differential model and a reinforcement learning algorithm. And the collaborative early warning module generates a graded early warning scheme by utilizing edge calculation. And the interaction control module displays a state and optimizes a control strategy through a human-computer interface. The intelligent monitoring and management level of the power equipment of the transformer substation is improved, the service life of the equipment is prolonged, and the operation and maintenance cost is reduced.

The invention provides a twin power station collision visual simulation method and system based on physical simulation, and relates to the technical field of data processing, and the method comprises the steps: obtaining a three-dimensional geometric model of a twin power station, carrying out space division, extracting geometric parameters, obtaining material data, constructing a material correlation model and a mechanical model, and carrying out fusion to obtain a physical simulation model; acquiring initial collision condition parameters as boundary conditions, performing local grid encryption, constructing a nonlinear kinetic equation of a collision process, performing time domain solution, determining equivalent stress distribution and equivalent plastic strain distribution, and generating a collision result; judging whether plastic deformation or fracture failure occurs, generating full collision process physical field data, generating a collision animation frame sequence, generating a stress distribution cloud picture and a plastic strain cloud picture, constructing a fracture special effect, and comprehensively generating a collision visual scene.

The invention relates to the technical field of environmental monitoring, in particular to a stored material controlled atmosphere maintenance early warning method and system based on environmental monitoring, and the method comprises the following steps: collecting real-time gas composition, temperature and humidity data, carrying out the time sorting of the collected data, recognizing the change trend of multiple parameters at each time point, and obtaining a parameter trend prediction result. According to the method, by combining data time sorting and change trend analysis, analyzing the relation between parameters and environment safety values and recognizing the variables exceeding the threshold value, accurate adjustment of gas, temperature and humidity is ensured, pertinence of parameter control is improved, early warning marking is carried out on the high-frequency fluctuation area through continuous monitoring and dynamic data classification, and the accuracy of the high-frequency fluctuation area is improved. The storage article quality guarantee condition monitoring capability is improved, so that article loss caused by environment change is reduced, a data analysis method and a real-time monitoring method are integrated, the operation logic of an environment controller is optimized, and the overall efficiency and the resource utilization efficiency of the system are improved.

The invention relates to the technical field of photovoltaic power station inspection, and provides a distributed photovoltaic power station unmanned aerial vehicle inspection method and system, and the method comprises the following steps: generating an inspection task list based on the multi-station distribution characteristics of a distributed photovoltaic power station; according to the inspection task list, performing scanning modeling on each photovoltaic sub-power station in sequence through a laser radar, and generating a photovoltaic power station three-dimensional map; dynamically planning an inspection path according to the characteristics of each photovoltaic sub-power station; according to the inspection path, performing multi-angle scanning on each photovoltaic module in different installation environments through a multi-source sensor, and obtaining photovoltaic module image data with position information in combination with the real-time position coordinates of the unmanned aerial vehicle; performing preprocessing, feature extraction and fault identification on the photovoltaic module image data by using a fault identification model, and establishing a fault feature library; and carrying out fusion analysis on the multi-source data, generating a fault detection report of each photovoltaic sub-power station based on the inspection task list, and formulating a corresponding maintenance scheme according to the fault detection report. According to the invention, multi-source data fusion analysis of the photovoltaic module image data, the fault feature library, the position coordinates and the three-dimensional map is realized, and the inspection efficiency and the fault detection accuracy of the distributed photovoltaic power station are improved.

The invention provides a wireless signal and thermal imaging multi-modal cooperative detection and directional interference method and system, and relates to the technical field of electronic countermeasures, and the method comprises the steps: carrying out the time domain synchronization and spatial domain registration of wireless signal data and infrared thermal imaging data, constructing a multi-modal feature fusion network, and carrying out the wireless signal and thermal imaging multi-modal cooperative detection and directional interference. And an attention mechanism and a recurrent neural network are adopted to extract time sequence features of the target, and position coordinates, motion states and behavior pattern information of the target are output. And then, based on a target state evaluation model and a reinforcement learning algorithm, an intelligent interference strategy is designed, and an interference beam is dynamically adjusted through an adaptive beam forming technology, so that accurate directional interference on the target is finally realized. The target detection precision and the interference efficiency can be effectively improved, the false alarm rate is reduced, and the target identification and interference capability in a complex environment is enhanced.

The invention provides an unmanned aerial vehicle autonomous flight path planning and image acquisition method and system, and relates to the technical field of unmanned aerial vehicle inspection. Firstly, through intelligent three-dimensional grid division and dynamic route planning, the coverage rate and efficiency of feature region monitoring are remarkably improved; secondly, due to the integration of real-time meteorological data and historical feature data, the pertinence and adaptability of acquisition are enhanced, and high-quality images can be obtained in a complex and changeable environment; through combination of real-time processing and ground deep learning analysis, the accuracy and efficiency of feature extraction are greatly improved; and on the basis of a self-adaptive supplementary sampling mechanism of the region of interest, quick response and accurate positioning of the suspected feature region are realized, and reliable data support is provided for subsequent detailed analysis and decision making. The method is not only suitable for identification tasks of various preset features, but also has good expansibility and flexibility, and can be adjusted and optimized according to different application requirements.

The invention discloses a terrain-level real-scene three-dimensional entity and element dynamic updating method, which comprises the following steps: S1, data acquisition and preprocessing: acquiring data of a target area by an acquisition mechanism based on entity and element type priorities, and preprocessing the acquired data to obtain model data of the target area; s2, change detection: comparing newly collected model data with historical model data, and identifying a change region and type; s3, entities and elements are extracted and updated, wherein the entities and the elements of the change area are processed to obtain updated models; s4, model fusion and optimization: fusing the updated entity and element model with the original model, and realizing efficient acquisition and preprocessing of target area data by using the multi-source surveying and mapping equipment and an acquisition mechanism based on entity and element type priorities; by dividing the small regions according to the region characteristics and correcting the acquisition frequency, the resource allocation is optimized, and the pertinence and efficiency of data acquisition are improved.

The invention discloses a knowledge and data fused chronic disease collaborative management method and system, and relates to the technical field of medical management. Comprising the following steps: generating a feature data set, processing the feature data set by using a feature gain modeling method, and generating an enhanced feature data set; dynamically generating a chronic disease comprehensive knowledge graph, performing node supplementation and weight optimization on the knowledge graph, and generating a specific knowledge sub-graph of the patient; carrying out multi-time sequence prediction by utilizing the specific knowledge sub-graph, and carrying out short-term and long-term trend prediction; a patient health track model is constructed through the state transition probability in combination with the prediction result; according to the dynamic risk labeling result of the health track model, the health state of the patient is comprehensively evaluated in combination with the specific knowledge sub-graph, and personalized management suggestions are generated according to the evaluation result. According to the collaborative management platform, cooperation between different medical institutions and medical staff can be promoted, information sharing and resource integration are realized, and the overall level of medical services is improved.

The invention relates to an intelligent water temperature control system and method based on machine learning. The method comprises the steps that water temperature, flow, pressure and environmental parameter data of a constant water temperature control system are collected, and a standardized time sequence data set is generated; constructing a time-varying dynamic model based on the standardized time sequence data set, and performing parameter identification by using a variable forgetting factor generalized subspace tracker to obtain a time-varying pseudo-modal temperature parameter; training a multi-branch long short-term memory network according to the time-varying pseudo-modal temperature parameters and the standardized time sequence data set to obtain an initial water temperature prediction model; performing system operation anomaly detection and prediction based on the initial water temperature prediction model to obtain an anomaly detection and prediction result; solving a control strategy based on the anomaly detection and prediction result to obtain an optimal water temperature control strategy; and executing water temperature control based on the optimal water temperature control strategy, and updating the initial water temperature prediction model to obtain a target water temperature prediction model. According to the intelligent water temperature control system, accurate control over intelligent water temperature is achieved.

The invention discloses an AI-driven abnormal transaction intelligent monitoring and analysis system and method, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining structured features and unstructured features, carrying out the feature fusion, and constructing an account feature vector; constructing a cross-domain heterogeneous graph, learning an embedded vector of an account node in the cross-domain heterogeneous graph based on a time sequence heterogeneous graph neural network, and generating an account portrait vector; training an abnormal transaction detection model, and predicting the abnormal probability of the current real-time transaction record of the account by taking the account portrait vector and the transaction record as input data; dividing all accounts into account groups based on the account portrait vectors, calculating a group abnormal transaction threshold value, and calculating an adaptive abnormal transaction threshold value based on the group abnormal transaction threshold value and the similarity between the account portrait vectors and the center vectors of the account groups to which the account portrait vectors belong; and if the abnormal probability is greater than a self-adaptive abnormal transaction threshold, marking the transaction of the account as an abnormal transaction, triggering risk control measures, and regularly updating the self-adaptive abnormal transaction threshold.

The invention discloses an ear-nose-throat nursing scheme intelligent recommendation system based on cloud computing, and relates to the technical field of big data analysis. The intelligent recommendation platform is in communication connection with a data acquisition and preprocessing module, a knowledge graph construction module, a patient portrait construction module, a nursing scheme recommendation module, an evaluation and adjustment module and a user interaction and feedback module. According to the intelligent recommendation system for the ear-nose-throat nursing scheme based on cloud computing, deep analysis and mining are carried out on real-time physiological data, ear-nose-throat related symptoms, wound healing conditions and function recovery progress of patients by utilizing the powerful data processing capability of a cloud computing platform, individual differences and rehabilitation requirements of the patients are accurately recognized, and the intelligent recommendation system for the ear-nose-throat nursing scheme based on cloud computing is provided for the patients. And personalized nursing schemes are customized for the patients, so that the pertinence and effectiveness of nursing are improved, and the prolonged rehabilitation time and the discomfort of the patients caused by the improper schemes are greatly reduced.

The invention relates to the technical field of medical care, in particular to an intelligent query method for a nursing knowledge base, which comprises the following steps of: performing multi-form standardized processing on a nursing problem input by a user, deeply analyzing a query request by utilizing a semantic understanding model, and obtaining an intelligent query result based on an inference algorithm; the method comprises the following steps: automatically selecting related literatures, clinical data and nursing experience data from a nursing knowledge base, generating a preliminary nursing scheme candidate set in combination with a nursing professional knowledge graph, and performing personalized screening and optimization on the scheme by using an intelligent recommendation model in combination with the current illness state, treatment progress and historical nursing data of a patient; the intelligent recommendation model is self-optimized through user feedback, and the nursing scheme recommendation precision is continuously improved. The nursing knowledge base automatically fuses newest medical research results and clinical nursing practice data. The problems that in the prior art, nursing scheme recommendation accuracy is low, updating is not timely, and the individuation degree is insufficient are effectively solved.

The invention relates to the technical field of artificial intelligence, and discloses an abnormal behavior real-time early warning method and system based on intelligent security, and the method comprises the steps: determining a monitoring environment feature set corresponding to a security monitoring region, and formulating a behavior early warning threshold value corresponding to security monitoring equipment; collecting dynamic behavior information of personnel in the security and protection monitoring area, analyzing the behavior modal analysis dimension corresponding to the security and protection monitoring equipment, and evaluating the area security situation corresponding to the security and protection monitoring area; analyzing physical feature attributes corresponding to the personnel in the security and protection monitoring area, analyzing action mode features corresponding to the personnel in the security and protection monitoring area, and calculating behavior risk entropies corresponding to the personnel in the security and protection monitoring area; analyzing the monitoring adaptation degree of the security and protection monitoring equipment in the security and protection monitoring area; and formulating an abnormal behavior early warning strategy corresponding to the security and protection monitoring area, and executing abnormal behavior real-time early warning in the security and protection monitoring area to obtain an early warning result. According to the invention, the real-time early warning efficiency of abnormal behaviors under intelligent security is improved.

The invention relates to the technical field of power system operation training, and discloses a virtual reality-based power grid fault simulation training system and method, and the system comprises a virtual scene modeling module which is used for constructing a three-dimensional model of power grid equipment and an operation environment thereof, and providing a vivid training environment for subsequent modules; and the interaction and operation module is connected with the virtual scene modeling module and realizes interaction between the trainee and the virtual environment by using a VR head-mounted display, a handle and a motion capture device. By adopting a high-precision three-dimensional modeling technology, PBR material rendering and an LOD optimization strategy, high simulation of power grid equipment and an operation environment is realized, students can experience a vivid visual effect and immersion in a virtual reality scene, and meanwhile, by combining a gesture recognition technology realized by motion capture equipment and a convolutional neural network, the real-time simulation of the power grid equipment and the operation environment is realized. Operation actions of trainees can be accurately captured, a natural and visual interaction mode is provided, and the authenticity and operation experience of the training system are greatly improved.

The invention discloses an operation and maintenance mode analysis model generation method and system, a medium and a program product, and relates to the field of electric digital data processing. Establishing an equipment basic life model based on the equipment fault time data and the non-fault working time data; calculating an environment correction coefficient according to the equipment operation environment parameter data and a preset environment influence factor, and combining the environment correction coefficient with the basic life model to obtain a corrected life prediction model; calculating the correlation degree of each equipment node based on the equipment topological structure, and constructing an equipment importance evaluation model; calculating equipment maintenance cost, replacement cost and shutdown loss according to a prediction result of the corrected life prediction model to obtain a cost loss model; and carrying out weighted fusion on an output result of the equipment importance evaluation model and a calculation result of the cost loss model to generate an operation and maintenance mode analysis model. The scientificity and accuracy of operation and maintenance mode analysis are improved.

The invention relates to the technical field of data synchronization, and discloses a distributed account book remote data synchronization method and system, and the method comprises the steps: carrying out the Hash mapping calculation of all nodes of a distributed account book system, and obtaining a distributed storage architecture; performing hierarchical network construction on the nodes, and setting an inter-region remote synchronization link and an intra-region local synchronization link to obtain a double-layer communication architecture; performing parallel compression coding, digital signature generation, transmission scheduling arrangement and consistency verification processing on the data blocks to obtain a node synchronous data set; calculating a correlation coefficient of node processing delay and network transmission delay to obtain a synchronous delay analysis model; based on a data block corresponding to the synchronous delay analysis model, adding a time sequence identifier and calculating an integrity check code, and generating a synchronous reliability guarantee mechanism; according to the method, the consistency and the traceability of the distributed account book data are ensured.

The invention provides a digital twinborn model and method for a coal mine disaster scene based on multi-modal data. The method comprises the following steps: acquiring original data in a mine; performing cleaning, normalization and de-noising preprocessing on the original data; fusing different types of preprocessed original data by using a data fusion algorithm, and constructing a comprehensive digital twinborn model; establishing a virtual mirror image of the mine by using a digital twinning technology, and mapping the mine in the real world into a digital twinning model; real-time mapping and simulation analysis are carried out based on the established digital twinborn model, and the disaster development trend is predicted by monitoring the internal environment and the equipment state of the mine; and according to a model analysis result, optimizing prevention and control measures of coal mine disasters, establishing a real-time monitoring and early warning system of the disasters, and taking measures in time when abnormal conditions are found. The system comprises a data acquisition module, a model construction module and a model analysis module. The pertinence and effectiveness of coal mine disaster prevention and control can be improved.

The invention discloses a cloud computer end-to-end fault root cause analysis method and system, and relates to the technical field of operation and maintenance data analysis, and the method comprises the steps: deploying data collectors on a virtual resource pool, a multi-stage cloud management platform and a cloud computer terminal, and monitoring and collecting various operation and maintenance data in real time; a unified operation and maintenance management center is introduced to complete the following work: providing management and configuration services of the data collector; receiving and summarizing operation and maintenance data; various AI models are accessed, operation and maintenance data from different sources are distributed based on the types of the AI models, the AI models perform deep analysis and diagnosis on the operation and maintenance data, and potential fault modes or abnormal behaviors are identified; customizing an alarm strategy, an alarm processing flow and an alarm notification mode; and introducing an AIOps service to generate an alarm and fault analysis report according to the analysis and diagnosis results of the AI model. According to the method, the service quality of the end-to-end full link of the cloud computer is monitored in real time, so that faults can be quickly positioned, early warning can be performed in advance, and the operation and maintenance cost and the fault risk are reduced.

The invention discloses a nerve regulation system for cognitive impairment, and the system comprises a cognitive behavior evaluation module which is used for recognizing a cognitive defect field which needs to be improved by a target object; the image data acquisition module is used for acquiring and preprocessing task state nuclear magnetic data and T1 weighted structure images of a target object; the brain region activation analysis module is used for determining a neural regulation potential target spot according to the preprocessed task state nuclear magnetic data; the brain network analysis module is used for identifying key nodes related to cognitive defects; the stimulation target screening module is used for determining an individualized stimulation target of the target object according to the nerve regulation potential target and the key node of the target object; the time domain interference electrical stimulation simulation and implementation module is used for performing electrical stimulation on the individualized stimulation target spot; and the dynamic feedback adjustment module is used for dynamically adjusting the stimulation parameters and enhancing the personalized regulation and control effect. By adopting the method and the device, the specific brain region directly related to the cognitive impairment can be determined, so that the targeting and the accuracy of treatment are enhanced.

The invention discloses a driving skill training method constructed based on a diversified virtual examination room, and relates to the technical field of data processing, and the method comprises the steps: constructing a system based on the diversified virtual examination room, constructing a virtual examination room scene to carry out the driving training of a training user, outputting a driving behavior data set in real time, and carrying out the scoring, and analyzing the data according to the driving score, generating a personalized training path in combination with historical data when the driving score does not reach the standard, and training the user to carry out training step by step according to the training path until a preset skill scoring target is achieved. The technical problems that in the prior art, a traditional driving training method cannot dynamically adjust a training path to meet the actual skill requirements of trainees, consequently, training content lacks pertinence and is low in efficiency are solved, the individuation and pertinence of driving skill training are improved, it is ensured that the training content is highly matched with the actual skill requirements of the trainees, and the driving skill training efficiency is improved. And the training efficiency and effect are improved.

The invention discloses a marketing data link abnormity diagnosis method, system and device and a storage medium. Relates to the technical field of power system data management. At present, the problems of multi-source data format difference, lack of real-time anomaly detection mechanism and low data management efficiency exist in anomaly diagnosis. The method comprises the steps that multi-source heterogeneous data of a marketing data link is collected in real time, and data cleaning, missing value filling and abnormal value processing are completed; extracting statistical characteristics of the link data, performing clustering analysis on the data, and generating a self-supervision label; constructing a support vector machine classification model, and detecting normal and abnormal data in the link; optimizing the anomaly detection model through a deep neural network; and realizing interpretability analysis and decision support of anomaly diagnosis by using a multi-classification result generated by the LSTM model and a self-supervised learning strategy. According to the invention, data link abnormity diagnosis is efficiently and intelligently realized, and data quality management, abnormity detection precision and service decision support capability are improved.

The invention relates to an emergency protection circuit device abnormal alarm identification method based on a large model, and the method comprises the following steps: obtaining and analyzing an abnormal alarm record of an emergency protection circuit device, and obtaining structured abnormal alarm data; constructing an abnormal alarm feature vector space; clustering the abnormal alarm data in the feature vector space, and identifying typical alarm modes in different fault modes; dynamically generating induction information aiming at a specific alarm mode in combination with circuit action logic and fault induction factors; screening out unique information with low semantic similarity as an induced action candidate; constructing an induction strategy reinforcement learning model, and finding an optimal induction strategy through iterative optimization; processing real-time abnormal alarms by applying an optimal induction strategy; evaluating a processing effect, and predicting a potential abnormal trend in combination with a maintenance period; and regularly performing incremental training on the large model. According to the method, the processing efficiency and accuracy of the abnormal alarm can be effectively improved, and the reliability and safety of the system are enhanced.

The invention discloses a retrieval enhancement-based large language model question and answer method, apparatus and device, and a medium. The method comprises the steps of obtaining a target question input by a user; retrieving in a pre-constructed knowledge base according to the target question to obtain an initial retrieval result; according to a first preset prompt word, calling a large language model to determine a first correlation score between the initial retrieval result and the target question, and filtering the initial retrieval result based on the first correlation score to obtain a filtered retrieval result; and according to a second preset prompt word, based on the target question and the filtered retrieval result, calling a large language model to generate a target answer. According to the method, the introspection type retrieval strategy and the correlation evaluation mechanism are introduced by means of the large language model in the retrieval stage, introduction of useless information is reduced, the pertinence and the accuracy of retrieval are improved, therefore, consumption of computing resources is reduced, the accuracy of content generated by the large language model is improved, the RAG technical potential is brought into full play, and the user experience is improved.

The invention relates to the field of image processing, in particular to a remote sensing image panchromatic sharpening method and a model training method and system. The training method comprises the steps that panchromatic-spectrum fusion features of a panchromatic image and a multispectral image and time information serve as prior information, and the prior information and a diffusion noise-added image are input into a diffusion model so that a fitting noise-added image can contain more panchromatic information and spectrum information; predicting the diffusion noise adding image and the panchromatic space-spectrum fusion feature through a Transform module so as to generate a reconstructed difference image in which complete panchromatic information and spectrum information are reserved; the method has remarkable advantages in the aspects of noise suppression and detail enhancement, and a multispectral image with more sufficient spectral information and spatial information can be generated.

The invention provides a cleaning worker work supervision method based on machine vision analysis, and relates to the field of machine vision application, and the method comprises the steps: carrying out the mining of similarity threshold distribution characteristics through employing a clustering analysis algorithm according to historical cleaning effect data in different scenes, and obtaining an initial adaptive threshold setting; aiming at key cleaning steps, a standard action library containing multi-dimensional information is established, the standardization of cleaning actions is evaluated in real time by adopting a computer vision technology and a dynamic time warping algorithm, and differentiated evaluation and guidance are realized by combining individual characteristics of cleaning personnel and adopting personalized threshold setting and feedback strategies; by continuously tracking action performance changes, dynamically adjusting an evaluation strategy and updating standard action library parameters to form a closed-loop optimization mechanism, the accuracy and pertinence of cleaning quality evaluation can be effectively improved, continuous improvement of cleaning quality is promoted, and the method adapts to complex and changeable actual cleaning scene requirements.

The invention relates to a GNSS-based water conservancy facility deformation monitoring and early warning method, system and device and a medium, and the method comprises the steps: obtaining GNSS monitoring network data of a target part of a water conservancy facility, and carrying out the real-time dynamic differential processing, and obtaining corresponding three-dimensional coordinate data; acquiring environmental factor data, and performing multi-source feature fusion on the environmental factor data and the three-dimensional coordinate data to obtain a corresponding deformation feature vector; performing prediction analysis on the deformation feature vector according to a preset whale optimization algorithm to obtain a corresponding deformation trend prediction result; setting a multi-level early warning threshold according to the deformation feature vector, and performing early warning analysis on a deformation trend prediction result to obtain a corresponding initial early warning level; and obtaining standard deformation characteristic information of the deformation rate and the acceleration of the water conservancy facility, and performing comprehensive evaluation on the standard deformation characteristic information based on a deformation trend prediction result to obtain a corresponding early warning index. Potential risks can be found and processed in time, and the possibility of hydraulic engineering accidents is reduced.

The invention provides a context understanding-based software operation prompt automatic optimization method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting the multi-dimensional context feature data of user software operation, carrying out the feature coding through a multi-modal feature fusion network, modeling the time sequence dependence through a bidirectional long-short-term memory network, and carrying out the feature coding through the bidirectional long-short-term memory network. And a context semantic representation vector is generated based on a multi-head attention mechanism, and a prompt generation strategy is continuously optimized in combination with reinforcement learning. According to the method, personalized customization of software operation prompts can be realized, the accuracy and timeliness of prompt contents are improved, and the software use experience of a user is enhanced.

The invention relates to the technical field of artificial intelligence, in particular to a model construction method for a GUI agent, a program product and a storage medium, and the model construction method for the GUI agent provided by the invention comprises the following steps: performing pre-training based on a general data set in the GUI field to obtain a base model; a user demonstration operation track is collected online, and a personalized task execution track is obtained; automatically labeling the task execution track to obtain a labeled track; performing task planning training on the base model based on the marked track to obtain a scene planner, and combining the base model and the scene planner to obtain a personalized model; based on the plug-in scene knowledge base, corresponding scene knowledge is retrieved as context supplement during personalized task action planning. The task execution track is automatically labeled, a large model is guided to actively label and understand thinking in human execution operation, the next behavior is further planned, and the adaptive capacity of a GUI intelligent agent to the personalized use environment of a user is greatly improved.

The invention discloses an automatic quality-supplementing correction method and system for the unbalance amount of a fan, and the method comprises the following steps: collecting geometric parameters and material characteristics in a static state of the fan, and constructing a mechanical distribution model of the fan; the method comprises the following steps: collecting vibration signals and airflow characteristics in real time in a dynamic operation state, calculating the amount of unbalance in operation and decomposing the amount of unbalance into a primary component and a secondary component; on the basis of the unbalance prediction trend, determining a quality supplementing range, carrying out multi-point quality supplementing operation through a dispensing technology, and monitoring a quality supplementing effect by using an optical fiber sensor; and if the residual unbalance amount after quality supplementation still exceeds the standard, real-time compensation adjustment is carried out through the electromagnetic torque regulation and control module. Full-process automatic correction from static state to dynamic state and from quality supplement to fine adjustment is achieved, the method has the advantages of being real-time, accurate and intelligent, vibration and noise in the fan operation process can be effectively reduced, the operation stability of equipment is improved, and the service life of the equipment is prolonged.