422 results about "Data modeling" patented technology

The invention relates to the technical field of electric energy meter metering, and discloses an electric energy meter metering anomaly analysis method and system, and the method comprises the steps: collecting data, such as voltage waveforms, to generate a metering feature vector set, and constructing an anomaly detection rule base; setting a scene parameter type set, and establishing an abnormal association judgment model; dynamically correcting the threshold value by combining the model, and generating an optimized error threshold value set and an abnormal triggering condition set; and updating a metering analysis strategy to generate an abnormal judgment scheme, and correcting data verification sequential logic. The system comprises a data acquisition module, an abnormal rule base construction module, a scene parameter configuration module, a correlation model training module, a dynamic threshold optimization module, a strategy updating module and a time sequence correction module. Through multi-dimensional data modeling, scene-based threshold configuration and dynamic time sequence calibration, the accuracy and adaptability of electric energy meter measurement anomaly detection are improved, and the method is suitable for measurement anomaly analysis of diversified power consumption scenes in a smart power grid.

The invention relates to the technical field of slope catastrophe intelligent early warning and data modeling, and particularly discloses a strip mine high and steep slope multi-source monitoring and early warning method based on a graph neural network and Transform, and the method comprises the following steps: S01, carrying out the data preprocessing and disturbance variable construction of monitoring data; s02, constructing a heterogeneous space diagram structure by taking the monitoring points as nodes and taking geography, lithology and dynamic response relationships as edges; s03, constructing a space-time end-to-end multilayer coding framework based on the graph attention network and the integrated deep neural structure; s04, on the basis of graph coding and time sequence output, introducing a disturbance variable embedding mechanism, and designing a joint attention fusion structure; and S05, generating a deformation trend prediction value of the slope in a future period of time and performing corresponding risk grade judgment. The invention aims to solve the key technical problem of weak adaptability and interpretability of an early warning system.

The invention relates to the technical field of silver paste preparation, in particular to a silver paste conductivity data modeling and formula optimization system based on machine learning, which comprises a data acquisition and storage module, a preprocessing module, a characteristic influence analysis module, a formula optimization module, a simulation verification module and the like. The method comprises the following steps: acquiring original data of a silver paste formula, preprocessing, calculating influence coefficients of all components on target performance by utilizing a machine learning model, and identifying high and low influence components; the formula optimization module is combined with component content constraints and adopts a multi-objective optimization algorithm to generate candidate formulas; and the simulation verification module verifies the performance of the formula through sintering simulation and process adaptation, and feeds back optimization. According to the invention, the full-process intelligentization of the silver paste formula from data processing to optimization verification is realized, the conductivity and other performances of the silver paste are accurately improved, the research and development cost is reduced, the period is shortened, the suitability of the formula process is enhanced, and the research and development and industrial upgrading of the silver paste are promoted.

The invention discloses a three-normal-form automatic modeling method and system, electronic equipment and a storage medium, and the method comprises the steps: constructing a structured domain knowledge base, and injecting three-normal-form design experience for an RAG framework; business semantics are clarified in real time in combination with user demand input and multi-round dialogue interaction of model questions; a double-stage AI recommendation engine is adopted to match user requirements and knowledge base semantic vectors, a high-precision model change scheme is generated, automatic normal form optimization is conducted on a recommendation scheme, DDL scripts, ER diagrams, data migration schemes and the like conforming to the normal form are dynamically output, integration is conducted in a sandbox environment, and finally closed-loop automatic modeling of'requirement-design-verification 'is achieved. The method is used for solving the problems that traditional data modeling is low in efficiency and high in error rate and cost rate, the problem that model knowledge updating needs full-amount or increment fine tuning, and the cost is high, and the problem that business semantic understanding is insufficient in three-normal-form modeling is solved.

The invention relates to the technical field of informatization system development, in particular to a natural language-based complex data model generation method, which comprises the following steps of receiving business requirement input in a natural language form, preprocessing and normalizing input contents, processing ambiguity and incompleteness of requirements through a multi-round dialogue complementation mechanism, and generating a complex data model. Obtaining a complete and clear business demand description; and carrying out deep semantic analysis on the normalized business requirements by adopting a large language model. Aiming at the pain points that an existing data modeling technology is high in threshold, low in efficiency, difficult in quality guarantee, weak in integration adaptation and the like, the method has the remarkable advantage of multiple dimensions, non-technical background personnel can directly input service requirements through natural language interaction and deep semantic analysis on the premise of reducing the technical threshold, database knowledge and SQL specifications do not need to be elaborated, and the method is suitable for large-scale popularization and application. The cognitive gap of business and technology is spanned, the dependence on professional design talents is reduced, and the learning cycle of green hands is shortened.

The invention relates to the field of constructional engineering, and discloses a dynamic risk prediction system, which generates space-time alignment input through multi-source data fusion, adopts tensor field modeling to embed contract constraint to construct a risk dynamic model, and solves and outputs a continuous risk field through a partial differential equation; a propagation path is analyzed in combination with asymmetric causal analysis, model parameters are adjusted in real time through a dynamic optimization algorithm, and closed-loop optimization of a risk field is achieved; and finally, through four-dimensional thermodynamic diagram interaction early warning and resource intelligent scheduling, a whole-process closed-loop system of data modeling-causal analysis-dynamic optimization-visual management and control is formed. According to the method, dynamic optimization of risk field parameters is realized through adjoint equation back propagation, and the modeling precision of a complex scene is improved; a four-dimensional space-time thermodynamic diagram rendering technology is innovated to solve the problem of fragmentation of multi-modal information expression, and risk disposal response is accelerated; key task resource supply is guaranteed by combining video memory preemption and containerization scheduling strategies, and the system stability bottleneck in a high-load scene is overcome.

The invention relates to the technical field of risk identification, and provides a risk identification system and a risk identification method. According to the risk identification system, by introducing the scene perception module, the data alignment module and the multi-modal analysis module, automatic acquisition and fusion of multi-source heterogeneous data, including images, videos, voices, sensor data, operation information and the like, of a construction site are realized, and the comprehensive perception ability of the system to the site state is effectively improved. Through a data alignment mechanism guided by structured data, multi-dimensional alignment of time, space and task semantics can be realized based on a historical schedule, B I M parameters, a construction plan and the like, the problem that multi-source data is difficult to fuse in a traditional method is solved, and the accuracy and consistency of data modeling are improved. A pre-trained multi-modal risk identification model is adopted, the cross-modal analysis capability is achieved, images, texts and behavior data of a construction site can be comprehensively understood, and then risk identification is accurately carried out.

The invention provides a multi-modal data joint query analysis method and system supporting natural language interaction, and relates to the technical field of data query analysis. Historical operation data, audio data and text data of a user on an intelligent search platform supporting natural language interaction are collected; modeling the historical operation data to obtain a user preference vector, performing voice recognition and text standardization processing on the audio data to obtain standard query data, and integrating the standard query data and the text data into context information; an attention mechanism-based algorithm is used for semantic understanding and intention recognition to obtain an intention feature vector, and the intention feature vector is fused with a user preference vector to obtain a classification result; and finally, based on the result, querying in a preset multi-modal database through a collaborative filtering algorithm to obtain a joint query result, so that personalized accurate query of the multi-modal data under natural language interaction can be realized, and the result fits the intention and long-term preference of the user.

The invention discloses a multi-source unmixing analysis method and system for a geological source-sink system based on a dzmix inverse Monte Carlo model, relates to the technical field of tectonic sedimentology and data modeling crossing, and collects and arranges zircon U-Pb chronological data of a target horizon mixed sample in a research area and zircon U-Pb chronological data of a basin peripheral material source area. Establishing a multi-source area big data chronology database of the research area; and establishing standard stratum characteristics in combination with regional sedimentary characteristics and petrology characteristics. According to the method, the contribution proportion of the multi-source substances in the geological source-sink system is quantitatively recovered, the defects that a traditional source-sink analysis method depends on priori end member selection and is easily influenced by personal errors are overcome, the inverse Monte Carlo model is used for carrying out iterative simulation for multiple times, the simulation effect is gradually optimized, the accuracy and reliability of a de-mixing result are ensured, and the method is suitable for large-scale popularization and application. And a more scientific and accurate technical means is provided for geological research and resource exploration.

The invention discloses a distributed environment multi-modal intelligent monitoring system, which belongs to the technical field of environment monitoring and comprises a sensing node module, a sensing control module, a communication synchronization module, an acquisition fusion module, a data modeling module, a modal analysis module, a simulation maintenance module, a visual decision module and a safety protection module. According to the method, the time precision of cross-node data transmission and event association is ensured, network self-healing and continuous operation can be maintained when part of nodes fail or communication is interfered, long-term autonomous operation is realized, the maintenance cost is reduced, and a monitoring network can adapt to different working conditions and structure changes.

The invention discloses a method for monitoring the heat dissipation performance of a module in a salt mist environment, and belongs to the technical field of material performance monitoring, and the method comprises the steps: carrying out the continuous spectrum data collection of the heat dissipation surface of the module in the salt mist environment, obtaining original multispectral data, carrying out the background correction, generating multispectral imaging data, and recognizing an action region; analyzing the spectral response attribute of the action area, obtaining a characteristic spectral fingerprint, carrying out physical parameter inversion, obtaining heat dissipation related physical parameters, and combining heat flow distribution data during the operation of the synchronous acquisition module to establish a related mapping relationship; and carrying out quantitative evaluation on the influence degree and the degradation trend of the salt mist environment on the heat dissipation performance of the module by combining the related mapping relationship to obtain a performance evaluation report. According to the method, the technical means of combining multispectral imaging analysis and heat flow data modeling is adopted, and quantitative diagnosis and trend prediction of heat dissipation performance degradation can be achieved.

The invention relates to the technical field of data analysis, and discloses a low-code data analysis platform and method based on multi-source data real-time access, and the platform comprises a data access module, a modeling module, a rendering engine and an early warning module. The method corresponds to the platform. According to the method and the device, the problems of real-time integration and standardization of the multi-source heterogeneous data are solved by obtaining the standardized data entity, and a high-quality data basis is provided for subsequent analysis; a dynamically constructed knowledge graph and a graph embedding technology are deeply fused into a data analysis process, so that semantic association among data entities is intelligently understood, an optimized query statement is automatically generated, intelligent recommendation and rationality verification are provided for establishing a data association relationship for a user, and the technical threshold of data modeling is reduced; a second-level response closed loop from data access to visual presentation is formed based on intelligent chart recommendation of data features and early warning rules and instant calculation and triggering in a real-time data stream.

The invention relates to a fault prediction method and system for parameter fine tuning and adaptive structure pruning based on business influence driving, and belongs to the technical field of artificial intelligence, time series data analysis and intelligent operation and maintenance. Comprising the following steps: S1, business influence data modeling: integrating multi-source operation and maintenance data and historical business fault event data, and constructing a business influence quantitative model; s2, efficient fine tuning of service influence guide parameters: loading the pre-training fault prediction model, and performing efficient fine tuning of the parameters on the basis of service influence signals; s3, business influence driven adaptive structure pruning; S4, dynamic reasoning and alarm generation: realizing a dynamic reasoning mechanism of a pruned fault prediction model, and generating a structured and business value oriented fault prediction alarm according to a reasoning result; and S5, performing closed-loop optimization and continuous evolution. According to the invention, the configuration accuracy of the operation and maintenance resources is improved.

The invention discloses an intelligent monitoring method and device based on thermal power plant shutdown energy-saving management. Aiming at the problems of alarm flooding, static prompt, dependence on artificial experience and the like existing in a traditional DCS alarm mode, shutdown related equipment is divided into 40 functional modules, historical operation data are modeled by combining a multivariate regression and multivariate state estimation method, parameter deviation conditions are monitored in real time, and a real-time monitoring result is obtained. And abnormal identification is realized through three types of functions of a fluctuation value, a reference value and a predicted value. Each module is provided with state judgment and fault diagnosis logic, and stop reminding and expert processing suggestions are automatically triggered according to conditions such as current, rotating speed and MFT signals. According to the invention, man-machine cooperative intelligent disk monitoring is effectively realized, potential risks are early warned in advance, energy-saving operation is guided, the operation and maintenance cost is remarkably reduced, and the safety, economy and automation level of the unit in the shutdown stage are improved.

The invention relates to the technical field of laboratory information management systems, and discloses an LIMS (Laboratory Information Management System)-based full-category detection data integration and quality tracing management system, which comprises a data modeling module for automatically generating domain ontology extension by adopting a method of combining ontology modeling and natural language processing; the data processing module is used for acquiring original data of the multi-source heterogeneous instrument data, and performing format recognition and semantic mapping on the original data by adopting a full-category detection data unified model; the block chain traceability module is used for storing traceability standardization detection data in a classified manner and establishing a layered framework; the quality prediction and early warning module is used for constructing a quality influence factor library and generating a prediction result based on the quality influence factor library; the cross-system integration module is used for obtaining a cross-system integrated data management platform by adopting a containerization technology and an event traceability architecture; according to the invention, the quality tracing query response time is shortened, and the credibility and timeliness of quality management are improved.

The invention discloses a business data modeling method and system based on metadata, and relates to the technical field of business data management.The method comprises the steps that a standard field list is created; creating a business object; extracting table structure metadata from the database to obtain a physical table field; establishing a field mapping matrix between the physical table field and the standard field list; and generating a business data model based on metadata according to the business object and the field mapping matrix. According to the scheme of the invention, the business model is constructed on a unified standard field, and scattered, disordered and difficult-to-understand physical data in an enterprise can be systematically converted into high-quality data assets which are clear in responsibility, unified in meaning, clear in relation and traceable.

The invention discloses a temperature drift cooperative compensation control system of a photoelectric detector. A sensing module collects temperature distribution data of a sensitive element array and state data of a surface temperature-sensitive phase change coating; the modeling module receives multi-source data, processes the multi-source data through a digital twin model, and outputs a coating compensation contribution value, an electronic compensation demand coefficient and a performance drift prediction parameter; the decision module calculates cooperative execution parameters of the coating and electronic compensation based on a dynamic weight distribution algorithm; the compensation module comprises a temperature-sensitive phase change coating unit and an electronic compensation unit which are respectively used for carrying out physical compensation from a source and carrying out rear-end electronic compensation according to the collaborative parameters; and the feedback module compares a performance measured value with a predicted value, and drives self-optimization updating of the model and the parameters. According to the invention, dual-channel cooperative temperature compensation from a physical level to a circuit level is realized, and the gain stability, the time sequence precision and the energy resolution of the photoelectric detector in a wide temperature range are effectively improved.

The invention is suitable for the field of multi-modal data analysis and target identification, and provides a multi-modal time series data reasoning method based on a thinking chain, a three-layer reasoning state architecture is designed, hierarchical abstraction and time alignment of multi-modal data are realized through a gating circulation unit and a time modulation mechanism, and the multi-modal time series data reasoning efficiency is improved. Converting the multi-modal features into a unified time sequence semantic representation; designing a multi-step reasoning controller, and dynamically focusing key information and iteratively optimizing a reasoning state by adopting a modal exclusive attention mechanism and a gating circulation unit; in order to explicitly capture a cross-modal and cross-time complex dependency relationship, multi-modal time sequence dependent graph structure modeling is carried out, multi-modal time sequence data is modeled into a directed graph, and structured information transmission is realized through a graph neural network; according to the method, deep understanding and accurate prediction of military target behaviors are realized, the reasoning process can be visually explained through state evolution, attention weight, graph structure dependency and the like, and reliable technical support is provided for intelligent decision making in a complex scene.

The invention relates to the technical field of image processing, in particular to a method and a system for extracting an algae microscopic image contour. The method comprises the following steps: acquiring a multi-view image flow of algae cells under a microscope, and carrying out frame-level scheduling and semantic splicing to obtain a multi-angle fusion image unit; constructing a topological contour tensor graph for the multi-angle fusion image unit; performing multi-scale positive and negative contour comparison training on the topological contour tensor diagram to obtain a contour embedded spectrum; holographic algae sample matching back-pushing is carried out on the contour embedded spectrum, and a candidate matching spectrum set is obtained; analyzing an edge feature contribution degree according to the candidate matching spectrum set, and carrying out dynamic fusion on the edge feature contribution degree and the multi-angle fusion image unit to generate an edge saliency heat map; screening independent algae samples by utilizing an edge significance heat map; and carrying out data modeling on the independent algae samples, and synchronizing a data modeling result to an algae sample library. According to the invention, the image contour extraction precision and efficiency can be improved.

The invention provides a path planning method, system and equipment for underwater rock drilling operation of a high-frequency breaking hammer, and relates to the technical field of underwater rock drilling. A multi-source data modeling technology and a position indicator area positioning technology are fused, microscopic details of a rock drilling target are complemented through optical data, equipment motion constraints are calibrated through position indicator data, and three-dimensional environment modeling of a macroscopic operation area in combination with the microscopic rock drilling target and the equipment motion constraints is achieved; a multi-objective optimization model is constructed, and an objective function for aggregating the path length, the path fluctuation, the energy consumption and the breaking hammer slip rate is a composite cost function; solving a global optimal operation path corresponding to the composite cost function by adopting IPSO; obtaining the global optimal path through speed updating mechanism optimization, adaptive inertia weight adjustment, asynchronous change learning factor setting and natural selection population iteration; the data volume and the calculation complexity of environment modeling are reduced, and the accuracy and the practicability of environment perception and modeling are improved.

The invention discloses a data processing system and method for big data modeling, and belongs to the technical field of data processing.The method specifically comprises the steps that feature tree operation records, geometric grids and constraint solving logs are collected in a computer aided design environment and combined into an initial data packet, and a design number and a time stamp are bound; respectively converting the three types of data into a topological sequential sequence, a graph data structure and a constraint conflict trajectory sequence, and unifying the topological sequential sequence, the graph data structure and the constraint conflict trajectory sequence into a sample unit format; generating a geometric semantic slice sequence and bidirectional index mapping on the graph data structure according to a topological time sequence, generating a multi-view rendering result for the slice, synthesizing a tensor, and keeping an index relationship from pixels to topological entities; performing time sequence alignment based on the multi-view rendering tensor, the topology time sequence and the constraint conflict trajectory sequence, generating a geometric sample index table, and performing fragmentation storage; and finally, exporting a uniform-format data packet containing a graph data structure, a time sequence and image features from the index table for direct reading of a big data modeling processor.

The invention discloses a coal flotation oil atomization effect evaluation system adopting data modeling, and relates to the technical field of coal flotation process intelligent control of mineral processing engineering.The coal flotation oil atomization effect evaluation system comprises a data acquisition module used for obtaining physical characteristic parameters and flotation process parameters of atomized oil drops in the coal flotation process in real time; and the hybrid model construction module is connected with the data acquisition module and is used for constructing an atomization effect evaluation model based on a mechanism model and a data driving model. According to the coal flotation oil atomization effect evaluation system adopting data modeling, by constructing a multi-source data sensing network and mechanism data hybrid driving model, accurate quantitative evaluation on the dispersion state of atomized oil drops is achieved. According to the method, a dual heterogeneous verification mechanism is adopted, through cross mutual verification of process correlation analysis and result inversion verification, it is ensured that an evaluation result has high reliability and traceability, and the technical problem that the atomization effect cannot be objectively quantified due to the fact that a traditional method depends on experience judgment is effectively solved.

The present application relates to the technical field of aquaculture, and particularly relates to an improved PSO-based water quality parameter prediction method and system for aquaculture, which comprises collecting water quality parameters at different positions and depths in a breeding pond; training an improved radial basis function (RBF) neural network using training set data; and optimizing the parameters of the improved RBF neural network model using an improved particle swarm optimization (PSO) algorithm. The present application introduces a mixed Gaussian function and an abnormal S-shaped function into the radial basis function of the traditional RBF neural network, thereby solving the problem of weak capability of the model in nonlinear data modeling. Furthermore, the present application improves the inertia factor and the learning factor in the traditional PSO algorithm, thereby solving the problems of slow parameter convergence speed and poor global search capability in the RBF neural network.

The invention discloses a power distribution network equipment fault root cause analysis data modeling method, relates to the technical field of power distribution network fault analysis, and aims to solve the technical problems of low fault root cause analysis accuracy and slow response under high-frequency topology dramatic change and edge terminal computing power fluctuation of an existing power distribution network. Comprising the following steps: S1, acquiring equipment operation data and real-time topology information by a heterogeneous edge terminal of a power distribution network, constructing a dynamic lightweight time sequence diagram model with online self-adaptive capability according to an edge terminal computing power high-frequency dynamic topology dramatic change scene, and outputting a fault root cause coarse positioning result; s2, the heterogeneous edge terminal uploads topology increment information and a coarse positioning result in a grading manner based on topology change intensity, wherein the topology increment information is structured data of local topology change of the power distribution network; and S3, the cloud platform updates the global time sequence diagram according to the topology change intensity in a grading manner. The method has the advantages of improving the fault root cause analysis accuracy and the response speed.

The invention discloses a psychological experiment task-oriented subject response data modeling method and system, and belongs to the technical field of psychological experiment task data modeling, and the method comprises the following steps: collecting subject response data; performing reaction flow serialization, converting original data into a continuous time sequence, and recognizing a cognitive state transition point through a multi-scale recursive segmentation method based on dynamic entropy perception; dynamic cognitive model construction: adopting an improved drift diffusion model combining dynamic parameter decomposition and hierarchical Bayesian inference to obtain a dynamic cognitive analysis model reflecting cognitive strategy switching, fatigue accumulation and learning effect; and reaction data modeling: establishing a causal relationship among a state label, a cognitive parameter and a reaction behavior, and realizing quantitative modeling and prediction of a psychological experiment task. According to the scheme, fine modeling and dynamic analysis of the multi-dimensional psychological reaction process can be realized, and the interpretability and the application value of psychological experiment data are improved.

The invention discloses a cognitive link diagram modeling and visual expression method, device and system, and belongs to the field of user behavior data modeling visualization, and the method comprises the steps: building a diagram expression and a traceable path of a causal structure based on a user behavior data modeling result; wherein the logic relevance and evolution directivity between entities in the graph are enhanced through a semantic annotation mechanism of nodes and edges of the graph, and the user cognition evolution process in the user behavior data is presented. According to the method, path-traceable graph structure visual expression is supported, and the cognitive evolution process of the user can be presented more finely.

The invention relates to the technical field of big data, and particularly discloses a natural language and semantic mapping-based business data model automatic construction method, which comprises the following steps of: performing structured analysis on a natural language demand input by business personnel, and extracting a dimension entity, a measurement index and a user intention; performing semantic matching on the business terms and the metadata fields by using a Sentence-BERT sentence vector model to generate a field mapping list; constructing a data consanguinity map based on a historical SQL, and reasoning an optimal multi-table association path through a shortest path algorithm by taking a center table as a root node; automatically generating a target wide table structure definition and a complete SQL (Structured Query Language) code by combining a template engine; and performing grammar and logic consistency verification on the output statement. According to the method, full-automatic, high-precision and interpretable end-to-end modeling from natural language requirements to executable wide tables can be realized, the data modeling efficiency and accuracy are remarkably improved, and the participation threshold of business personnel is reduced.

The invention relates to the technical field of power systems and energy management, in particular to a source network load storage collaborative interaction optimization system for high-proportion new energy. Comprising a multi-source information sensing data acquisition module used for monitoring various objects and an external environment in real time; the data modeling prediction analysis module is used for constructing a system parameter model and carrying out prediction analysis; the source network load storage collaborative optimization decision-making module is used for realizing multi-time-scale and multi-main-body optimization scheduling; according to the invention, the multi-source information sensing data acquisition module, the data modeling prediction analysis module, the source network load storage collaborative optimization decision module, the execution control instruction issuing module and the like are organically combined, so that the multi-source information sensing data acquisition module, the data modeling prediction analysis module, the source network load storage collaborative optimization decision module and the execution control instruction issuing module are integrated; omnibearing perception and prediction of new energy output, load demand, energy storage operation and power grid state are realized.

The invention discloses a spatial interpolation method based on an FC-ResNet neural network model, and the method comprises the steps: training a neural network model through sample point data, enabling the model to learn a mapping relation between an interpolation attribute value and a coordinate, and recovering continuous distribution characteristics of a two-dimensional space and even a three-dimensional region from sparse observation data, and spatial continuous field reconstruction is realized. By introducing the residual block, the expression ability of the deep network is enhanced, the model training stability is improved, and gradient disappearance and network degradation are avoided, so that two-dimensional and three-dimensional space interpolation tasks are adapted; a physical information regularization constraint is fused into a loss function, so that the interpolation result is ensured to have spatial smoothness and physical consistency (such as geologic body continuous gradual change characteristics), and the phenomena of'block artifacts' and the like which do not conform to actual rules are reduced; finally, accurate reconstruction of space structures (such as submarine topography and oilfield porosity distribution) is realized, and an efficient tool is provided for complex space field data modeling.

This invention relates to the field of three-dimensional parametric modeling and precise measurement of the foot, and discloses a method and system for measuring and extracting foot parameters based on a parametric model. The method includes: acquiring foot depth and color images from multiple perspectives and calibrating the camera; reconstructing multi-view point clouds and fusing them into a complete point cloud, converting it into a triangular mesh model; achieving mesh standardization through NICP and ARAP algorithms, and constructing a measurement mapping matrix by combining local extremum detection; extracting principal components of adolescent foot types based on PCA and constructing a parametric model; and employing a multi-head attention network that integrates geometric priors to output foot anthropometric indicators end-to-end from single-view color images. This invention is based on adolescent data modeling, adaptable to both adolescent and unhealthy foot types, with small measurement errors, high batch measurement efficiency, and low hardware costs. It can support adolescent foot health assessment and personalized footwear customization, and has significant practical applications.