612 results about "Data identification" patented technology

The invention discloses a bridge construction abnormity monitoring data identification method and system based on big data, and relates to the technical field of bridge construction monitoring, the system comprises a collection module, an analysis module, a process matching module and an execution module, the collection module collects construction data, transmits the construction data to the analysis module, carries out linkage verification on the construction data through an analysis unit, and carries out process matching on the construction data; identifying and outputting abnormal data, transmitting the abnormal data to a process matching module, constructing a judgment standard for dynamic matching through a construction process, comparing the abnormal data with the judgment standard, outputting a preliminary judgment result, transmitting the preliminary judgment result to an execution module, executing multi-stage cross validation on the preliminary judgment result, and outputting a final abnormal judgment result. By responding to multi-source data, missed judgment is prevented, a space-time linkage verification mechanism is constructed to improve anomaly recognition accuracy, a dynamic judgment standard adapts to risks of all stages, false anomalies are filtered through three-stage verification, the efficiency is improved through full-process automation, hidden danger early warning is assisted, accidents are avoided, and bridge construction quality and safety are guaranteed.

The invention discloses an AI-based regulation and control abnormal data identification and correction method, system and device and a medium, and belongs to the technical field of power system regulation and control, and the method comprises the steps: obtaining multi-source data of a main distribution network, carrying out the preprocessing, and constructing a power grid topology knowledge graph; the multi-source data comprises full voltage class model data, real-time measurement data and equipment state data. According to the method, a three-layer detection system of a statistics-density mixed detection layer, a graph neural network association detection layer and a time sequence Transform detection layer based on an LOF algorithm and a 3 sigma principle is constructed, deep association analysis of multi-source data is realized in combination with a power grid topology knowledge graph, and an intelligent correction module is used for matching a differentiation correction algorithm for different types of anomalies; the correction weight is dynamically adjusted based on reinforcement learning, and the problems that a traditional method depends on artificial experience to set a threshold value, the recognition capacity of a single algorithm is limited, a correction strategy lacks adaptability, and multi-source data association analysis cannot be achieved are solved.

The present invention relates to the technical field of intelligent out-of-distribution fault detection for construction machinery, and discloses an out-of-distribution fault detection method and system based on energy propagation and graph learning, and the method includes: acquiring vibration acceleration signals in typical fault states, carrying out similarity calculation to obtain an adjacency matrix composed of the maximum mutual information coefficients, and taking the adjacency matrix as input in a graph neural network; carrying out feature extraction on the adjacency matrix through adopting a GraphSage graph convolution method, and generating each node representation; calculating an energy score of each node, and distinguishing between in-distribution data and out-of-distribution data; and enhancing out-of-distribution data confidence estimation for each node, and carrying out out-of-distribution data identification and out-of-distribution data detection under different working conditions of a rolling bearing.

The invention provides an energy efficiency prediction and energy-saving scheduling optimization system and method for a food cold chain system, and relates to the technical field of cold chain system energy-saving scheduling, and the system comprises a data recognition module which is used for recognizing cold chain loading state data, and analyzing the space influence characteristics of the loading state data of a cold chain loading space; the strategy obtaining module is used for carrying out energy efficiency optimization on cold chain energy supply according to the space energy efficiency relation between the cold chain space and the link energy supply parameters and the space influence characteristics; the state chain establishment module is used for carrying out loading state dynamic analysis based on the cold chain vehicle path and predicting a path switching node; and the optimization strategy obtaining module is used for carrying out path state node scheduling optimization according to the cold chain path state chain by taking a space energy efficiency strategy as an initial parameter based on the vehicle energy supply coupling relationship and the space energy efficiency relationship of the cold chain system. The technical problem of energy consumption waste in cold chain transportation in the prior art can be solved, and the technical effect of reducing cold chain energy consumption is achieved.

The invention discloses an inspection report generation method and device, equipment and a storage medium. The method comprises the following steps: determining abnormal inspection data and a report object of data center equipment; determining structured inspection data according to the abnormal inspection data, a preset equipment knowledge graph and a historical case library; determining a report constraint condition according to the report object and a preset report generation rule; and inputting the structured inspection data and the report constraint condition into a pre-trained large language model, and generating an inspection report oriented to the report object. According to the technical scheme, the preset equipment knowledge graph and the historical case library are constructed in advance, the fault linkage effect and the historical similar cases across the equipment are identified based on the inspection data, the inspection reports facing different report objects are dynamically generated, and the generation efficiency, the flexibility and the comprehensiveness of the inspection reports are improved.

The invention relates to a sensitive data identification and desensitization method and system based on an AI large model, and belongs to the technical field of data security processing and artificial intelligence. The method comprises the following steps: receiving a multi-source data processing request, establishing a sensitive data identification framework, analyzing elements of sensitive data, and extracting a sensitive data feature vector through a natural language processing algorithm; classifying the multi-source data, dynamically adjusting an identification threshold value of the sensitive data identification framework through a sensitive data feature vector, and generating a self-adaptive sensitive data identification strategy; establishing a terminal desensitization verification model, performing desensitization verification on the identified sensitive data, performing mask replacement or generalization processing according to privacy requirements, and outputting a desensitization retry processing scheme; the sensitive data is subjected to block desensitization, a large data set is divided into small data sets for independent desensitization, replaceable entities in information are removed according to data attributes, and the desensitized data is further subjected to secondary desensitization.

The invention discloses a carbon emission abnormity traceability method and device, a medium and equipment, and belongs to the field of carbon emission, and the method comprises the steps: receiving a traceability request containing a to-be-verified data identifier, positioning target link data from a block chain storage, and executing signature verification and Hash consistency verification, thereby guaranteeing the authenticity and consistency of the data. And if the verification of the target link data is passed, verifying the inclusion relation of Merkle tree root hash of each link upwards layer by layer to confirm the integrity of the full-chain data. And if verification failure of any level is found, the feature data of the level is combined with an anomaly detection model based on an isolated forest algorithm, and an abnormal data node is positioned. And then, according to the signature information of the abnormal data node and the preset tracking secret key, a group signature verification and private key derivation process is applied, the responsibility participant is traced, and the tracing process of the carbon emission abnormity is completed, so that the problem that the carbon emission abnormal point cannot be accurately and efficiently traced in the prior art is effectively solved.

The invention discloses a distributed block storage method and device, electronic equipment and a storage medium. The load index is calculated by collecting the multi-dimensional performance indexes of the storage nodes in real time, and the data fragment storage position is dynamically adjusted according to the load. The self-adaptive multi-dimensional load sensing model can accurately adapt to various service scenes, real-time balance of loads between nodes is achieved, hot nodes are effectively avoided, and the overall performance of the system is improved. And when the load index exceeds the preset threshold value, hot data identification, node affinity evaluation and migration income calculation modes are started to perform data fragmentation migration, so that the utilization rate of mixed medium resources is improved, a high-performance storage medium is reasonably utilized, and the data access efficiency is improved while the storage cost is reduced. Through cooperative work of load monitoring, fragmentation decision making, migration execution, metadata management and the like, a fragmentation strategy is automatically optimized according to input and output characteristics of different service types, and the overall performance under different service scenes is improved.

The invention relates to a sensitive information protection method and device, a storage medium and electronic equipment. The method comprises the following steps: executing structured field identification and general sensitive data identification processing on original input data to identify all sensitive data fragments; performing identification calculation and integrity signature processing on each sensitive data segment to generate a corresponding placeholder, and storing a mapping relationship between each sensitive data segment and the placeholder thereof in a mapping table; according to the mapping relation, replacing each sensitive data segment in the original input data with a corresponding placeholder to obtain replacement input data, and inputting the replacement input data and the output rule into the target large model to enable the target large model to output the original output data; and according to the mapping relationship, replacing each placeholder in the original output data with the corresponding sensitive data fragment to obtain final output data. The technical problem that sensitive data desensitization is prone to misoperation is solved.

The invention relates to a circuit board defect identification method and system based on multi-dimensional image data, and belongs to the technical field of data identification processing, and the method comprises the following steps: obtaining synchronous image data of a circuit board to be detected in a plurality of imaging modes; performing space-spectrum joint registration on each modal image to generate a multi-dimensional image cube with a unified coordinate system and pixel alignment; inputting the multi-dimensional image cube into a pre-trained multi-branch heterogeneous fusion neural network; generating a pixel-level defect probability graph by utilizing a defect sensing context decoder, and performing geometric constraint optimization on the probability graph by combining prior information of a circuit board design layout; outputting defect types, positions and confidence coefficients, and establishing an interpretable defect fingerprint database according to the multi-dimensional response characteristics of the defects; the method has the beneficial effects that false defect signals generated by image noise and circuit board surface texture interference can be effectively inhibited, the omission ratio and the false detection ratio are greatly reduced, and pixel-level accurate defect positioning is realized.

The invention relates to the field of wastewater treatment, and discloses an intelligent monitoring and regulation system for metal surface treatment wastewater based on Internet of Things, comprising: a wastewater data acquisition and purification unit for performing real-time acquisition of wastewater parameters through a sensor array to obtain multi-dimensional wastewater original data; performing abnormal data identification and noise filtration on the multi-dimensional wastewater original data to obtain a purified wastewater basic parameter set; according to the method, the real-time data of the wastewater are acquired through the sensor array of the Internet of Things, and the accuracy and reliability of the data are ensured by adopting an advanced anomaly detection and noise filtering algorithm; the system can adjust the wastewater treatment process in real time according to environmental factors and production line operation loads, multi-objective optimization is achieved through a deep reinforcement learning algorithm, and it is ensured that the wastewater treatment process can be efficiently operated under various complex environmental conditions.

The invention discloses an intelligent regulation and control method and system for temperature and humidity data of a logistics warehouse, and relates to the technical field of data identification, and the method comprises the steps: collecting the spatial and temporal distribution data of a temperature and humidity field in the warehouse through a multi-source sensor network; processing the data by adopting a multi-source time sequence data alignment algorithm and a feature extraction method; constructing and updating a spatio-temporal evolution prediction model; generating a coordinated regulation and control instruction sequence; a regulation and control instruction is issued, and closed-loop feedback is formed. The system comprises an environment sensing module, a data fusion and feature extraction module, a dynamic prediction modeling module, a multi-target optimization decision module and an instruction execution and feedback control module. According to the method, the spatial-temporal heterogeneity of the temperature and humidity field can be captured at high resolution, the temperature and humidity evolution trend in a future time window can be accurately predicted, the environmental safety and the energy consumption efficiency are comprehensively considered, the stability of the storage environment is remarkably improved, and energy consumption optimization is realized on the premise that the cargo storage safety is guaranteed.

The invention provides a ramp energy-saving control method based on off-line speed planning and dual-mode model prediction tracking, and aims to solve the problems of insufficient precision of ramp driving energy consumption and safety cooperative control and frequent mode switching of an automatic driving vehicle. The method comprises the following steps: firstly, identifying a key road section based on high-precision road gradient data, and generating an optimal energy-saving reference speed matched with gradient characteristics in an off-line manner by adopting a dynamic planning and sequential quadratic planning hybrid optimization strategy; secondly, when the vehicle runs, relevant information is loaded after confirmation of a driver, the system takes over the longitudinal control right, two control modes are dynamically switched based on the front vehicle distance, and frequent mode switching is avoided through a hysteresis threshold value; and finally, taking the slope-fused vehicle longitudinal dynamics model as a prediction model, solving an optimal control instruction online by adopting a model prediction control algorithm, performing closed-loop execution, monitoring intervention operation of a driver, and immediately returning the driving right after the intervention operation is detected. According to the method, offline planning and online dual-mode tracking technologies are integrated, the method has the advantages of high energy consumption optimization precision, stable mode switching and good safety adaptability, and energy-saving and safe driving of the automatic driving vehicle in a ramp scene is realized.

The invention provides a safety detection method and device for cross-border data, equipment, a storage medium and a program product. The method comprises the following steps: acquiring transmission data of a cross-border network environment; performing cross-border data extraction processing on the transmission data to obtain cross-border session data; performing protocol analysis processing on the cross-border session data to obtain a protocol analysis result of the cross-border session data; performing dual-channel privacy data identification processing on the protocol analysis result to obtain a privacy data identification result; generating a security detection result according to the protocol analysis result and the privacy data identification result; performing data desensitization processing on the privacy data according to the security detection result to obtain desensitized privacy data; establishing a secure communication link according to the desensitized privacy data; and sending the desensitized privacy data to a preset compliance decision subsystem through the secure communication link to determine a compliance evaluation result of the desensitized privacy data. The accuracy of safety detection can be improved.

The invention discloses a regional power grid-oriented new energy power prediction deviation factor identification method and platform, and belongs to the technical field of data processing. The method comprises the steps of collecting new energy historical power station data of a target regional power grid; constructing a deviation index double-layer identification system; performing power deviation data identification and influence factor extraction on the new energy historical power station data according to the prediction deviation amplitude and the prediction deviation reason to obtain a new energy power deviation data set and a power deviation influence factor set; based on the new energy power deviation data set, deviation weight distribution is carried out on the power deviation influence factor set, and a deviation influence factor weight factor set is determined; and performing key factor identification on the power deviation influence factor set based on the deviation influence factor weight factor set to obtain a new energy power prediction deviation factor set. The technical problem of incomplete and inaccurate new energy power prediction deviation factor identification in the prior art is solved, and the technical effect of accurately and comprehensively identifying the prediction deviation factor is achieved.

The present application discloses a sensitive data identification method and apparatus, a device, and a computer storage medium. A text mining technology is used to mine a plurality of sensitive data rules from a data security specification file of a target industry to form a sensitive data rule base, the rule base is continuously augmented by using technologies such as NLP and NER, and after data to be identified of the target industry is obtained, a sensitivity class and a sensitivity level of the data to be identified can be identified by matching the sensitive data rules in the sensitive data rule base corresponding to the target industry with the data to be identified.

The invention discloses a sensitive data identification method, system and device based on rule matching and LLM deep semantic analysis, a medium and a product, and relates to the field of artificial intelligence, the method comprises the following steps: preprocessing data in an information data set; the information data set comprises multi-industry corpora, personal information and safety knowledge; the multi-industry corpora cover structured data format features and unstructured text semantic scenes; according to the preprocessed data, a LoRA technology is adopted to carry out field adaptation fine tuning on the large language model; the large language model comprises a rule matching layer and an LLM depth recognition layer; the rule matching layer screens and identifies the structured data; the LLM depth recognition layer recognizes unstructured data and implicit sensitive data; performing semantic recognition on the to-be-tested data according to the fine-tuned large language model, and outputting sensitive data; the sensitive data comprises information such as an identity card number, a home address and a mobile phone number, and the sensitive data can be accurately recognized.

The invention discloses a redundant data identification method, device and equipment, a medium and a product. The redundant data identification method comprises the following steps: analyzing a structured query language (SQL) code snippet to generate an abstract syntax tree; based on the abstract syntax tree, performing blood relationship analysis on fields in the SQL code snippet to obtain a blood relationship between the fields, and determining candidate redundant fields according to the blood relationship; and obtaining metadata of a data table to which the candidate redundant fields belong, and performing redundancy judgment on the candidate redundant fields according to the blood relationship of the candidate redundant fields and the metadata to obtain potential redundant data. According to the technical scheme provided by the embodiment of the invention, redundant data can be efficiently identified.

The invention provides a measurement completion method, device and equipment serving panoramic transparency of a power distribution network, and the method comprises the steps: constructing a power distribution network graph model integrating a power grid topological structure, electrical parameters and measurement configuration information, carrying out bad data identification and cleaning on the original measurement data uploaded by the acquisition terminal to obtain a real-time measurement data set; for lines, buses, distribution transformers and circuit breakers in a power distribution network, missing electrical measurement values are obtained through classification certainty deduction calculation by using electrical network topology constraints, conservation laws and forward-back substitution load flow calculation so as to realize measurement completion; and performing quality evaluation on the complemented measurement data, and performing closed-loop feedback optimization based on an evaluation result. According to the scheme, high-precision complementation of the missing electrical quantity can be realized by depending on the measurement data acquired in real time, and the data storage and computing resource overhead is reduced.

The invention discloses a power data network wide area synchronous transmission system based on APN6 intelligent slicing, and relates to the technical field of power system communication, the service type of current transmission data is obtained through an identification embedding module, and a structured APN6 identifier is embedded in a Hop-by-Hop option header of an IPv6 extension header; the slice creation module judges whether retransmission is carried out or not according to CRC verification, dynamically creates multi-level slices according to time delay levels, and calculates an optical fiber refraction compensation value according to topological path coding; when the phase compensation module monitors that a line fault or a node is overloaded, different strategies are executed for slices of different levels, and transmission phases of slices around a fault area are adjusted through the signal modulation module; and when the slice capacity expansion module detects that the new energy cluster oscillates, bandwidth directional capacity expansion is executed according to the slice resource elastic scheduling framework. According to the method and the device, the data identification accuracy and the slice resource adaptability are improved.

The invention relates to the technical field of intelligent data identification, in particular to a wetland ecological drought condition identification method based on multi-source data. According to the technical scheme, the method comprises the following steps: data acquisition: acquiring a multi-source data set of a target wetland region in a preset time sequence; the multi-source data set at least comprises a remote sensing reflectivity data set, a surface temperature data set, a meteorological reanalysis data set and an on-site monitoring hydrological data set; and data processing: sequentially carrying out space-time registration, denoising and missing value interpolation processing on the multi-source data set to generate a standardized space-time data cube. According to the method, multi-source data can be integrated to generate a standardized spatio-temporal data cube, each ecological drought index threshold value is dynamically determined based on the background of the historical wet season of the wetland, the comprehensive drought intensity is calculated in a weighted mode according to the wetland type, and accurate wetland ecological drought spatio-temporal distribution, grade sequence and early warning information are output after multi-scale verification. And a basis is provided for wetland ecological protection and water resource regulation and control.

The invention belongs to the technical field of oil and gas reservoir rock data identification, and particularly relates to a three-dimensional multi-mineral digital core modeling method. According to the method, a 2D-3DGAN algorithm is provided, a three-dimensional data volume can be generated only by using a single two-dimensional picture, the advantages of a 2D-3DGAN method and an AMICS method are combined, a modeling method of 'AMICS + 2D-3DGAN' is provided to establish a multi-mineral, high-precision and efficient three-dimensional multi-mineral digital core, the representative two-dimensional ore scanning image is obtained by using the 2D-3DGAN method, and the three-dimensional data volume can be generated only by using a single two-dimensional picture. And generating a three-dimensional multi-mineral digital image by using the obtained two-dimensional mine scanning image as a training image. The built model not only contains multiple minerals, but also gives consideration to accuracy and economical efficiency, can represent reservoir rocks, and provides a firm basis for subsequent diagenesis simulation based on multi-mineral digital cores and research on electrical, acoustic and mechanical properties of reservoirs.

The invention discloses a data identification method and system based on data high-dimensional feature deconstruction. The method comprises the following steps: decoupling multi-modal time series data into independent implicit factors with clear physical meanings through a domain knowledge constrained depth generation model; based on the implicit factor sequence, using time sequence causal discovery and anti-fact intervention to construct a causal graph and generate a causal effect vector; constructing a differentiable identification strategy network taking the implicit factor and the causal effect as input, and optimizing system meta parameters through a meta learner according to feedback; robustness loss feedback optimization is generated through causal consistency verification and abnormal injection, meanwhile, a structured identification graph is output, and an incremental model library is established. The system correspondingly comprises four function modules. According to the method, the problems that the features cannot be explained, the causal mechanism is missing and the model adaptability is insufficient are solved, and intelligent data identification which can be explained and is robust and has the sustainable evolution capacity is achieved.

The invention provides an aero-engine test process data processing method and system, and belongs to the technical field of data processing, and the method comprises the steps: training a deep learning model based on sample test process data and a corresponding sample label, and obtaining a test process data processing model; the method comprises the following steps: acquiring multichannel original data in an aero-engine test process, and preprocessing to obtain preprocessed test process data; identifying the preprocessed test process data by adopting a test process data processing model to obtain an engine test data identification result; the test process data, the recognition result, the test item information corresponding to the recognition result and the test item progress form structured data and are stored in blocks; when the structured data is accessed, decryption is carried out, and a visual data model is generated and displayed. According to the invention, the data processing efficiency, the data utilization efficiency, the test efficiency and the data analysis capability in the test process of the aero-engine are improved.

The invention belongs to the technical field of building progress management, and particularly discloses a multi-modal data-based identification and acquisition method and system, and the method comprises the steps: detecting the process progress deviation of a current working face in a building construction process in real time, and recognizing a cross risk through combining with the subsequent process plan time when the progress deviation exists, therefore, a multi-dimensional rule-driven necessity evaluation mechanism is constructed, quantitative, objective and traceable evaluation on the feasibility of the cross operation is realized, and a feasible time window and a space authorization boundary of the cross operation are defined on the current working face while the cross operation is judged to be necessary. And then, monitoring a motion track of a subsequent process in an authorized area, synchronously predicting completion feasibility of a previous process in a feasible window period, and carrying out space-time two-dimensional compliance judgment, so that real-time perception and risk identification of cross operation are realized by depending on multi-modal data fusion, and anomalies such as border crossing operation or progress lag can be actively discovered. And regulation intervention is triggered in time.

The application discloses a kind of based on privacy protection's e-commerce user portrait design method, belong to computer technology field, including: after obtaining the user data of e-commerce platform, the user data of e-commerce is handled, including data grading, sensitive data classification and sensitive data identification;Sensitive data is desensitized and handled, and different desensitization rules are used according to different hierarchical labels, including static desensitization and dynamic desensitization;Drive the modeling of federated learning model of cross-platform user portrait, including horizontal federated learning and vertical federated learning;Enhance privacy protection mechanism through large model, including large language model and federated large model training;Output final privacy protection user portrait.The e-commerce user portrait design method based on privacy protection of the application can effectively protect the sensitive information of user from being disclosed, and has higher practical significance.

The invention relates to the technical field of thermal power plant abnormal data processing, in particular to a thermal power plant production monitoring system network security data set abnormal data identification and cleaning method, which comprises the following steps: mapping a spatial-temporal feature vector to a preset thermal power plant multi-level causal graph to obtain a data causal graph; performing information propagation and node updating on the data causal graph, and calculating an abnormal score of each node in a preset thermal power plant multilevel causal graph; identifying abnormal data according to the abnormal score and the network security data set; and cleaning the abnormal data according to the abnormal type and a preset data cleaning strategy. According to the method, correlation modeling of data on time and a system topological structure is realized through a multi-level cause and effect graph; an abnormal score is calculated through information spreading and node updating, and an abnormal event in the network security data can be accurately identified; the abnormal data is cleaned based on the preset data cleaning strategy, redundant, wrong and abnormal data can be effectively removed, and meanwhile key risk information is reserved.

The present invention provides a system for dynamically registering plugin with an Enterprise Performance Management (EPM) system. The system provides a database module operationally coupled to a repository for storing information on registered enterprises, one or more user devices mapped to the registered enterprises, and a set of rules corresponding to each user device. The system further comprises a data identification module which is configured to receive data from one or more user devices and a converter framework comprising a converter module and a plugin module for conversion of data from a user device. The system further provides a registration module which is operationally coupled to said data identification module and the database module and is configured to receive a plugin registration request from a user device including a plugin, identify the user device and its data type, and determine if the plugin is already registered with the repository. Based on determining that the plugin is not already registered with the repository, update the repository to add the plugin and configuration information of said user device. Further, the system provides an access control module operationally coupled to database module to provide to the user device, an access to edit the configuration of added plugin.

The invention relates to a coal mine monitoring data visualization method and system, and aims to solve the problems that the existing two-dimensional monitoring system is split in data presentation, lacks spatial relevance and is low in emergency disposal efficiency, the underground multi-modal monitoring data is collected and preprocessed in real time, a three-dimensional space model fusing geological information and a roadway network is constructed, and the real-time monitoring of the underground multi-modal monitoring data is realized. The method comprises the following steps of: processing data, dynamically mapping the processed data to corresponding sensor space coordinates in a model, representing real-time data by utilizing a dynamically changeable visual data identifier, and realizing visual angle control, roadway roaming, click query and historical data backtracking through a man-machine interaction instruction; multi-dimensional alarm and focusing display is automatically triggered, a collaborative analysis view is generated, and a historical trend, peripheral data and an equipment control interface are displayed in a linkage manner, so that data exceptions are placed in spatial and logical contexts of the data exceptions for comprehensive analysis. According to the invention, the intuition, situation awareness and intelligent decision-making level of coal mine safety monitoring are obviously improved.

The invention provides anti-shake tableware based on dual-mode stability and a control method thereof, and the anti-shake tableware comprises a handle module which is provided with a connecting part, a supporting part and a holding part in the length direction; the tableware head part is detachably connected to the connecting part; the first stabilizing module is arranged between the supporting part and the holding part, and a stabilizer is arranged in the first stabilizing module; the second stabilizing module is arranged in the supporting part and comprises a balancing weight and three executing mechanisms, and the three executing mechanisms and the balancing weight are fixed in a magnetic attraction mode; the multifunctional integrated board is arranged in the supporting part and is integrated with an inertial measurement unit, a control module and a power module, posture motion data are obtained through real-time detection of the inertial measurement unit, and the control module is used for obtaining a jitter mode of a user through recognition according to the posture motion data; and on-off of the stabilizer and operation states of the three execution mechanisms are controlled based on the jitter mode. The method has the beneficial effects that multi-type and multi-dimensional tremor can be efficiently suppressed at the same time, the system integration degree is high, and the functionality can be flexibly expanded at the same time.