54 results about "Degree matrix" patented technology

The invention belongs to the technical field of pilot ability assessment, and particularly discloses a pilot ability assessment method based on dynamic time warping and hierarchical clustering, which comprises the following steps of: acquiring eye movement data of a tested pilot in a flight simulation task process, preprocessing the eye movement data, extracting behavior indexes of each stage of a flight task, and calculating a pilot ability assessment result; generating a fixation area number sequence according to the fixation point position; in the selection target evaluation stage, a dynamic time warping algorithm is used for carrying out nonlinear alignment on the gaze sequences of all the pilots, and an eye movement difference degree matrix between the pilots is generated; based on the difference degree matrix, adopting a hierarchical clustering algorithm to group the pilots; and outputting an ability evaluation result of the pilot according to the distribution of the pilot in the difference degree matrix and the deviation information of the pilot and the teacher watching sequence. According to the method, structured comparison and capability grade evaluation of complex cognitive behaviors can be realized, and an evaluation result has relatively high objectivity and interpretability.

The invention provides a method for intelligently extracting key geometric features of a target object through a three-dimensional laser scanner, and belongs to the technical field of actual measurement of an internal forming surface of a wind tunnel body. Constructing an association degree matrix by using a minimum spanning tree algorithm in a graph theory, calculating three clustering center values based on K-means clustering analysis, determining a boundary threshold value, starting a scanning precision adaptive strategy, dynamically adjusting scanning parameters through a feature extraction optimization model, extracting key geometric features by using a geometric feature recognition algorithm, and carrying out feature extraction on the key geometric features; spatial context information is automatically extracted by using a Transform attention mechanism, and finally a key geometric feature extraction result of the target object is output through sequential processing of six parallel computing units, so that the technical problem of insufficient geometric feature extraction precision of three-dimensional laser scanning point cloud data in a complex environment is solved.

This application discloses a data-driven energy dispatch fault diagnosis method, device, and medium, mainly relating to the field of fault diagnosis technology. It addresses the problems of existing solutions neglecting the multimodal distribution characteristics of energy data, failing to effectively capture the complex coupling relationships between the source-grid-load-storage links, lacking awareness of dispatch strategies, and being sensitive to noise interference. The method includes: obtaining a graph convolutional hidden representation matrix and then calculating a sparse dictionary matrix; optimizing the graph convolutional sparse coding objective function, solving for the sparse coding coefficients, and outputting a feature mining data matrix; calculating a dispatch strategy matching degree matrix based on the feature mining data matrix, using introduced dispatch plan data and real-time operational constraints; fusing the operational status classification vector and the dispatch strategy matching degree matrix to obtain predicted fault categories; and iteratively training a diagnostic model based on the predicted fault categories and labeled fault categories until a well-trained diagnostic model is obtained.

The invention discloses a geographic national condition comprehensive index monitoring method, and relates to the technical field of geographic national condition comprehensive indexes. The method comprises the following steps: collecting a geographic remote sensing image map, and segmenting the geographic remote sensing image map through a MaskR-CNN model instance to obtain a geographic semantic entity; reasoning through a causal discovery method based on an evolutionary algorithm to obtain a first causal intensity matrix; calculating a spherical distance between geographic semantic entities to obtain an entity distance matrix, generating an entity comprehensive influence degree matrix in combination with the first causal intensity matrix, and further constructing a geographic knowledge graph; inputting the geographic knowledge graph into the adversarial graph attention network model, and outputting a second causal intensity matrix; and based on the second causal intensity matrix, reversely traversing the geographic knowledge graph by using a breadth-first search algorithm to extract a change causal chain, calculating a feature contribution ratio of each geographic semantic entity in the chain, obtaining a geographic national condition comprehensive index, and realizing monitoring of the geographic national condition comprehensive index.

The application discloses a TBM tunneling parameter abnormal data identification method and system, and belongs to the technical field of data processing. The application constructs a polynomial chaos expansion regression model through polynomial chaos expansion, identifies abnormal data in TBM tunneling parameter data by using data clustering and polynomial chaos expansion regression error, depicts the correlation between TBM tunneling parameters through polynomial chaos expansion, compares the difference between data by using the correlation between TBM tunneling parameters, constructs a clustering objective function based on polynomial chaos expansion regression error, optimizes and solves the clustering objective function by using a Lagrange multiplier method, and obtains a TBM tunneling parameter membership degree matrix. Whether the data is abnormal is determined by using the TBM tunneling parameter membership degree matrix, and accurate identification of abnormal data of TBM tunneling parameters is realized.

A distributed photovoltaic cluster rapid clustering method, comprising: S1, extracting the historical meteorological data of the grid-connected point of the distributed photovoltaic power station and the operating characteristic parameter value of the distributed photovoltaic power station, and normalizing the same; S2, performing rapid filtering on the distributed photovoltaic power station based on the approximate k-means vector quantization technology, and obtaining representative typical distributed photovoltaic power stations; S3, screening out the distributed photovoltaic power stations with similar relations between each other through the KNN algorithm; S4, obtaining the adjacent matrix and degree matrix information of the typical distributed photovoltaic power stations by means of the Gaussian kernel calculation method, and constructing a Laplace graph; S5, adopting the "average cut" graph cutting method, obtaining the clustering result of the typical distributed photovoltaic power stations; S6, calculating the distance from each distributed photovoltaic power station to all typical distributed photovoltaic power stations, and distributing to a similar class according to the distance size, and completing the clustering. The scheme realizes rapid and accurate clustering of the distributed photovoltaic cluster.

The invention discloses a trademark batch retrieval method and system based on big data and AI assistance. The method comprises the steps that a batch to-be-retrieved trademark set and multiple trademark retrieval condition texts are obtained; utilizing the trained multi-modal trademark analysis model to respectively extract retrieval condition features of the retrieval condition text and graphic attribute features of the trademark main body to be retrieved; constructing a retrieval condition feature matrix and a graph attribute feature matrix, and calculating the multi-modal correlation degree in batches through matrix operation to obtain a batch correlation degree matrix; and determining a retrieval target according to the batch association degree matrix and generating a batch retrieval result containing association degree sorting. According to the method, efficient batch retrieval and accurate sorting of trademarks are achieved through multi-modal feature fusion and matrix operation, the retrieval efficiency and accuracy are effectively improved, and the actual application requirement is met.

The invention provides an equivalent circuit analysis method and system for soil resistance heating efficiency, and relates to the technical field of soil remediation. Resistivity distribution data and salt content distribution data of a pile space are obtained; calculating the ionic conductivity according to the salt content distribution data, and calculating the target conductivity of each grid unit; constructing a topological graph, and constructing a weighted adjacent matrix based on the topological graph; constructing a degree matrix according to the degree of each graph node to obtain a feature value sequence and a feature vector corresponding to each feature value; extracting a second small feature value from the feature value sequence as a connectivity index, and marking a mutation position as a weak connection interface; the blocking factor is determined by counting the number of graph nodes located at the weak connection interface, the equivalent circuit transmission efficiency representing the soil resistance heating efficiency is calculated based on the negative correlation between the connectivity index and the blocking factor, and accurate quantitative evaluation of the heterogeneous soil resistance heating efficiency is achieved.

The invention discloses a space-time enhanced aviation network flight delay prediction method and system, and belongs to the technical field of data mining. The method comprises the following steps: constructing an aviation network dynamic congestion degree matrix; processing a congestion degree matrix by adopting a graph embedded network of an encoder-decoder structure, and extracting a dynamic congestion mode through short-term time enhancement; extracting a spatial dependency relationship through long-term spatial enhancement by using the hidden state of the encoder and the static characteristics of the airport; fusing short-term and long-term features to generate node embedding, and constructing an adaptive adjacency matrix for graph convolution; multi-step prediction is performed based on an encoder-decoder framework in combination with time attention and graph convolution. According to the method, the implicit relationship of delay propagation between airports can be effectively captured, the space-time modeling capability is enhanced, and the accuracy and practicability of flight delay prediction are improved.

The application discloses a heterogeneous network node representation method and system based on biased walk of edge information entropy, and comprises the following steps: receiving an input heterogeneous network containing multiple types of nodes and edges, obtaining an adjacency matrix and a degree matrix, and calculating an edge information entropy matrix; for each target node, normalizing the edge information entropy between the target node and different types of neighbor nodes; determining multiple meta-paths according to the semantic information composition of the heterogeneous network nodes; for each target node, obtaining the next node type according to the node sequence set by the meta-path, and performing biased sampling according to the normalized edge information entropy; taking the next node as the target node after obtaining the next node, and repeating the above steps until the set path length and walk times are reached, so that a walk path set of the node is finally obtained; finally, inputting the obtained node walk path set as the context semantic association sequence of the target node into a classical Skip-Gram model for training, so that the vector representation of each target node is finally obtained.

The invention provides an automatic polishing roughness control method and system for the inner wall of a fire extinguisher tank. The method comprises the following steps: acquiring three-dimensional point cloud data of the inner wall of a fire extinguisher tank body, generating a local height deviation characteristic value and a curvature gradient characteristic value through curvature analysis, and quantifying to obtain a surface concave-convex degree matrix; the scanning frequency and angle of a rotating laser contour scanner at the front end of the polishing rod are adjusted based on the matrix; scanning the inner wall in the polishing process to generate a real-time morphology thermodynamic diagram for identifying a geometric mutation area; in combination with the surface concave-convex degree matrix and the thermodynamic diagram, a pressure correlation value of the inner wall geometrical characteristics and the polishing pressure is calculated, and a polishing pressure correlation vector corresponding to the geometrical mutation area is determined; and the axial path and the rotating speed of the polishing head are adjusted based on the vector, and the roughness difference of the geometric mutation area of the inner wall is eliminated. Dynamic elimination of the roughness difference of the wall of the inner tank body of the fire extinguisher is achieved, the polishing uniformity is improved, and the machining efficiency is improved.

The application discloses a cold-rolling friction coefficient prediction method based on a physical graph topology and a graph convolutional neural network, and comprises the following steps: defining a graph topology structure establishment rule for friction coefficient analysis in plate strip cold continuous rolling; selecting analysis parameters according to plate strip cold continuous rolling process characteristics and production experience, determining a node set, a physical relationship function set and an edge set in the graph topology structure; constructing an adjacency matrix and a corresponding self-adjacency matrix of the graph convolutional network with physical weights; introducing a degree matrix to perform normalization processing on the self-adjacency matrix to generate a normalized self-adjacency matrix; constructing a physical feature graph convolutional neural network based on the above settings and a basic form of the graph convolutional network; selecting cold-rolling product samples, obtaining analysis parameters and friction coefficient prior values, and training the physical feature graph convolutional neural network; and adopting a determination coefficient, a mean square error, a mean absolute error and a mean absolute percentage error to evaluate the performance of the physical feature graph convolutional neural network.

The invention provides a science popularization content intelligent recommendation method and system based on deep learning. The method comprises the following steps: acquiring science popularization image / video data, performing space-time decoupling processing to generate a multi-scale space-time feature tensor, and constructing multi-level feature representation of a local scene, a dynamic process and an overall context; utilizing a multi-head cross-modal attention network to calculate a semantic association degree matrix of the features and knowledge graph entities; a time sequence causal chain extraction module is introduced to generate a causal path constraint vector, a dynamic semantic alignment constraint is formed through matching with a knowledge graph relation path, and a semantic incidence matrix is optimized; and generating a uniform space-time semantic fusion vector by adopting an adaptive mapping decoder, and outputting a structured semantic tag set through a deep semantic classifier. According to the method, the limitation of traditional shallow recommendation is broken through, understanding of deep semantics and causal logic of scientific contents is realized, and the accuracy, semantic depth and interpretability of science popularization content recommendation are remarkably improved.

The application relates to the technical field of computers and discloses an AI monitoring method for performance prediction and scheduling of a multi-core CPU on a MODT mainboard. The method comprises the following steps: collecting multi-core running states and mainboard physical topology data, and constructing a communication delay-dynamic power consumption joint feature map; performing space-time modeling through a graph neural network to generate a multi-core state embedding vector; fusing task features to calculate a task-core matching degree matrix; establishing a multi-objective optimization model with the minimum communication delay, balanced power consumption and controllable temperature as constraints, and solving the model by an reinforcement learning agent to output optimal scheduling instructions. The application reduces the standard deviation of communication delay and temperature rise and improves the energy efficiency ratio through physical perception and AI collaborative scheduling, and application code does not need to be modified.

The invention provides a fault-tolerant processing method and device for incomplete data, and the method comprises the steps: recognizing the incomplete data with errors and missing, and determining an abnormal data sample set containing errors and non-random missing in the incomplete data; determining error distribution and missing probability density distribution of data key feature dimensions in the abnormal data sample set; determining a dynamic association degree matrix of characteristic variables between the financial association data and the incomplete data, and determining an adaptive characteristic weight vector of the incomplete data according to the dynamic association degree matrix, the error distribution and the missing probability density distribution; determining reconstructed complete data of the incomplete data in combination with historical financial core data related to financial risk perception; and performing distributed fault-tolerant verification on the reconstructed complete data, performing homomorphic encryption processing on a fault-tolerant verification result, and transmitting the fault-tolerant verification result to a financial risk perception data storage end. By adopting the scheme of the invention, fault-tolerant processing can be carried out on the data in combination with errors and non-random missing of the data.

The application discloses a kind of methods for determining reposition frame, device, vehicle and storage medium.The method comprises: obtaining feature map;Determine the image key frame of current image, according to the global feature of the image key frame and the global feature of the map key frame, determine current difference degree matrix;According to the current difference degree matrix, determine reposition mark according to preset dynamic programming algorithm;Based on the reposition mark, determine target reposition frame in the feature map.The technical scheme of the embodiment of the application is smaller in memory resources occupied by the established feature map, solves the problem that great computing resources are consumed in searching reposition frame in the global range of semantic map, is suitable for the scene with high scene similarity and poor communication signal, improves the accuracy and robustness of reposition frame.

The invention discloses a protection action curve visualization engine based on an IED (Intelligent Electronic Device) model difference atlas, which relates to the technical field of relay protection teaching, training and testing of a power system and comprises an IED model difference atlas construction module and a WebGL (Web Graphics Library) visualization engine module. According to the technical scheme, data are analyzed and a JSON equation is constructed based on a to-be-processed SCD file through an IED model difference atlas construction module, a boundary gradient vector is calculated based on the JSON equation to obtain a difference degree matrix, and a protection action curved surface is constructed and rendered in a unified parameter space based on the difference degree matrix through a WebGL visualization engine module. And a visual result of the protection action curve is displayed, so that students can understand protection action conditions and critical regions more visually, and the teaching efficiency and the practical operation conversion rate are remarkably improved.

The invention provides a yield prediction method and device of a produced product, a storage medium and a program product, and relates to the technical field of data processing, and on the basis of obtaining reference product information of each reference product and target product information of a target product, clustering processing is performed on each reference product to obtain at least two reference product clustering sets; and for each reference product cluster set, performing multi-head self-attention fusion processing to generate a corresponding product relation degree matrix. And matching a corresponding target reference product cluster set according to the target product information of the target product, and determining the target reference product. In each production time window, training the initial yield prediction model to obtain a target yield prediction model; inputting the product relation degree matrix corresponding to the target reference product cluster set, the target product information of the target product and the future time feature vector into a full-connection neural network layer, and outputting a target predicted yield; the problem of inaccurate yield prediction of newly developed products is solved.

The invention discloses an intelligent supply chain network abnormal node detection method. Firstly, an input intelligent supply chain network node graph structure is analyzed, and a degree matrix of the intelligent supply chain network node graph structure is calculated; then, node embedding features of the graph are extracted through the graph convolutional network; on the basis, the structural feature representation of the nodes is generated by combining the embedded representation of the nodes and the embedded representation of the adjacent sub-graphs, and an adjacent matrix of the original graph is reconstructed according to the structural feature representation of the nodes. Furthermore, based on the embedded representation of the nodes, the graph convolutional network is applied again to obtain the attribute feature representation, and the attribute feature representation is combined with the structural feature representation to cooperatively reconstruct the feature matrix of the original graph. And finally, using the reconstruction distance in the convergence state of the method as a quantitative index for evaluating the abnormal degree of the node. The method has the remarkable advantages that the topological structure of the graph and the attribute characteristics of the nodes are cooperatively reconstructed, interaction information of the graph is fully utilized, and the abnormal nodes of the graph can be accurately detected through the method.

The application belongs to the technical field of power consumption prediction, and discloses a fuzzy power consumption prediction method and system based on multi-scale double supervision driving, which comprises the following steps: multi-scale feature reconstruction is performed on data samples, reconstruction error is calculated, sample structure guide indexes are obtained by aggregating the reconstruction error, and the samples are screened in combination with structure guide indexes and entropy contribution; the screened samples are subjected to fuzzy division, the membership degrees of all samples are arranged in order to obtain a fuzzy membership degree matrix; structure supervision signals and target supervision signals are fused, and the membership degree matrix is adjusted by using the fused guide signals; the membership degrees in the new membership degree matrix are used as weights to perform weighted summation on the prediction results of each local regression model to obtain the final prediction result. The application designs a fuzzy division method combining a multi-scale structure adaptive mechanism with structure and target double supervision signals, and improves the modeling accuracy of the model for complex energy consumption data, the system adaptive ability and the sample utilization efficiency.

The application relates to the technical field of knowledge graphs, and discloses a reasoning method for semantic association and logical rules based on a knowledge graph, which comprises the following steps: acquiring a first data set across functional departments, and constructing a cross-department knowledge graph; extracting index nodes from the cross-department knowledge graph, identifying semantic conflict indexes, generating an index semantic conflict list, and constructing a cross-department knowledge graph after semantic mapping based on the index semantic conflict list; acquiring a second data set across functional departments, obtaining a fused cross-department knowledge graph and a semantic association degree matrix based on the second data set and the cross-department knowledge graph after semantic mapping; dynamically adjusting the weights of each node and edge of the fused cross-department knowledge graph according to the semantic association degree matrix, and generating a cross-department collaborative knowledge graph; and generating cross-department collaborative decision-making suggestions based on the cross-department collaborative knowledge graph; and the application significantly improves the efficiency and quality of cross-department collaborative decision-making.

The present application provides a kind of railway along line settlement space-time prediction method and device.The prediction method includes: based on the monitoring data obtained by monitoring along railway, unstable target area is identified;Obtain the time series settlement data of each monitoring point in unstable target area, and utilize optimal denoising model to carry out denoising processing, obtain the time series settlement data of each monitoring point after denoising processing;Based on the distance between each two monitoring points in unstable target area and the distance threshold value of pre-set, obtain adjacency matrix and degree matrix;Based on the time series settlement data of each monitoring point after denoising processing, adjacency matrix and degree matrix, utilize GCN-LSTM prediction model, adopt rolling prediction method to carry out lead prediction to the time series settlement data of each monitoring point, obtain the lead prediction set of each monitoring point.The present application is by constructing the GCN-LSTM prediction model of "space-time" coupling feature to carry out lead prediction to the time series settlement data of monitoring point, with the advantages of high prediction accuracy.

The invention relates to the technical field of artificial intelligence and knowledge base construction, and discloses a nationality knowledge base construction method based on a declarative multi-AI agent architecture. The method comprises the steps of obtaining declarative configuration template data and analyzing to generate a structured task demand description, performing vectorization processing on analysis dimensions to generate a dimension semantic dependency graph, generating an agent task execution scheduling plan by utilizing a topological sorting algorithm, identifying a country group by utilizing a graph clustering algorithm and generating a sharing degree matrix, and performing task execution scheduling on the agent task execution scheduling plan. The method comprises the steps of extracting a source country argumentation structure chart and generating an argumentation topology template, evaluating the similarity between a target country and a source country to generate a template applicable dimension list, instantiating the argumentation topology template into a specific argumentation structure of the target country, and cooperatively generating target country knowledge base content and an analysis report.

The invention relates to the technical field of data processing, and discloses a graphic data labeling method and system based on artificial intelligence, and the method comprises the steps: constructing N recognition feature sets according to M initial recognition features, determining a target feature set from the N recognition feature sets according to the recognition accuracy, constructing Q initial feature map networks based on the target feature set, determining a corresponding degree matrix and an adjacent matrix based on the initial feature map networks, obtaining a correlation coefficient according to the degree matrix and the adjacent matrix, and finally determining an optimal feature map network from the Q initial feature map networks based on the correlation coefficient and a preset intelligent optimization algorithm, according to the method, the optimal target feature set is screened out from the M initial recognition features, so that the problems of calculation complexity and interference caused by excessive auxiliary features are avoided; and the Q initial feature map networks are optimized and screened, so that the defect of lack of feature screening and optimization in the prior art is overcome.

The invention discloses an energy scheduling fault diagnosis method and device based on data driving and a medium, and mainly relates to the technical field of fault diagnosis. The method and the device are used for solving the problems that an existing scheme neglects the multi-mode distribution characteristic of energy data, cannot effectively capture the complex coupling relation among all links of source-network-load-storage, lacks the perception capability for a scheduling strategy and is sensitive to noise interference. Comprising the following steps: obtaining an image convolution hidden representation matrix, and calculating a sparse dictionary matrix; optimizing a graph convolution sparse coding objective function, solving a sparse coding coefficient, and outputting a feature mining data matrix; based on the feature mining data matrix, calculating a scheduling strategy matching degree matrix by using introduced scheduling plan data and real-time operation constraints; fusing the operation state classification vector and the scheduling strategy matching degree matrix to obtain a predicted fault category; and according to the predicted fault category, marking the fault category, and iteratively training the diagnosis model until a trained diagnosis model is obtained.

The invention relates to the technical field of environment monitoring data processing based on a large model, and discloses an environment monitoring data intelligent analysis method and analysis system based on the large model. Spatial modeling is carried out on a field by constructing a two-dimensional coordinate system, and sensors are arranged in grids, so that standardized acquisition and vectorization processing of soil moisture content data are realized, and large model input is adapted. And constructing an adjacent matrix, a degree matrix and a graph Laplacian matrix based on the spatial relationship between the nodes, and accurately depicting a network structure. And extracting a global trend signal by using graph smoothing filtering, and calculating a local residual error to identify an abnormal node and a sub-block thereof, thereby realizing automatic division of a local risk region. And finally, performing soil moisture content estimation on any position based on a graph structure and trend information, and completing effective completion of non-monitoring points.

The invention relates to an intelligent distribution management method and system, and the method comprises the following steps: S1, based on multi-source heterogeneous data collection, employing an optical character recognition and natural language processing fusion algorithm, automatically extracting the basic information of a person through a self-adaptive template matching technology, building a person-reaching capability evaluation model through employing a knowledge graph construction method, and carrying out the recognition of the person-reaching capability; s2, on the basis of the Databan digital portrait library, an improved collaborative filtering recommendation algorithm is adopted, and a commodity-Databan matching degree matrix is constructed through a commodity labeling classification engine. The method has the advantages that the multi-source heterogeneous data collection and optical character recognition and natural language processing fusion algorithm is combined with the self-adaptive template matching technology, high-precision automatic extraction of the basic information of the driver is achieved, the data collection efficiency is remarkably improved, and the driver ability assessment model established by the knowledge graph construction method has the advantages of being high in reliability and high in reliability. And the effect of integrating multi-dimensional features such as social influence and historical conversion rate is achieved.

The application discloses a power distribution network dynamic reconstruction method and device based on decision-oriented time period division, and a medium, wherein the method comprises the following steps: constructing a power distribution network dynamic reconstruction model; designing a multi-time decision mutual degree calculation method of the power distribution network dynamic reconstruction problem, completing consistency evaluation of each time decision, calculating a decision optimal solution deviation value between each time under the premise of considering time sequence through single-time reconstruction at each time, and constructing a similarity matrix; introducing a spectral clustering algorithm through the obtained similarity matrix, fusing decision consistency and time continuity, obtaining a corresponding degree matrix and Laplacian matrix, and realizing a decision-oriented time period division method. The application ensures that the segmentation can be reasonably divided according to load balancing requirements and improves the calculation speed, and through the calculation of the optimization result similarity matrix between each time period, the spectral clustering algorithm is used to aggregate the high similarity into a time period, so that the application can be widely applied to the field of power system power distribution network reconstruction technology.

The invention discloses a method and a device for optimizing a scenario simulation scheme. The method comprises the following steps: S1, acquiring a factor sequence set corresponding to a preset scenario simulation file; s2, performing stratified sampling processing on the factor sequence set to obtain a selected tuple set and a residual tuple set; s3, based on the selection tuple set, performing simulation processing on the scenario simulation file to obtain a selection performance result set; s4, optimizing a preset prediction model based on the selection tuple set and the selection performance result set to obtain an agent model; s5, analyzing and processing the residual tuple set by utilizing the proxy model to obtain a residual performance matrix and Q contribution degree matrixes; and S6, performing optimal analysis on the residual tuple set, the residual performance matrix and the Q contribution degree matrixes to obtain an optimal scheme matrix. According to the method, scheme optimization can be efficiently and accurately completed in a complex high-dimensional scenario simulation scene.

The application discloses an interactive question and answer method and system based on artificial intelligence, relates to the technical field of interactive question and answer, and comprises the following steps: converting a user input text question into a vector representation, combining a dependency relation tree of a text entity to construct a relation graph, capturing the dependency relation in the question as an edge weight value, composing an adjacency matrix to construct a node degree matrix, determining a normalized graph Laplacian matrix, performing feature decomposition, determining an optimal clustering number, clustering language phrases of the text question, and determining a task fragment set of different clusters. The method disclosed by the application not only has semantic association between language phrases by constructing a dependency relation graph, but also integrates syntax relation, ensures the integrity of text structure information, takes the degree of a node as a quantitative index of local strength in the graph, the information directly supports subsequent normalization processing of the Laplacian matrix, provides a uniform scale, and avoids the problem of uneven data range.