2094 results about "Cluster analysis" patented technology

The invention discloses a risk assessment and early warning method and system applied to water conservancy project construction, and belongs to the technical field of water conservancy project construction safety. Multi-source data of a construction area is collected, and a multi-dimensional construction information flow set divided according to time, procedures and work points is constructed; constructing a space-time risk causal map based on the construction units, and expressing time sequence association and risk propagation paths among the construction units; mapping the information flow to a graph structure, training a multi-task graph neural network model, and obtaining a risk score and a future risk evolution trend of each construction unit; performing clustering analysis on the risk state, identifying a high-risk work point set, and identifying a risk linkage chain based on a causal map; when the risk score exceeds a dynamic threshold value or a closed propagation structure exists, a grading early warning signal is triggered; according to the method, dynamic identification, trend prediction and intelligent early warning of complex construction risks are realized, and the intelligent level of construction safety management is improved.

The invention relates to the technical field of cable asset management and fault prediction, and discloses a cable fault positioning method based on deep learning clustering analysis test waveform characteristics, and the method comprises the steps: collecting waveform and environment data in a cable operation period, and constructing a historical feature library comprising waveform, environment and position features; a self-adaptive detection model is adopted, and parameters are dynamically adjusted to adapt to different working conditions; multi-dimensional feature fusion and matching analysis are combined; a fault point distance is calculated through a signal propagation model and a time difference positioning algorithm, precise positioning is realized by fusing environment compensation and multi-point cross validation, and a three-dimensional geographic coordinate is generated by combining a laying path; and after multiple verifications, a structured report containing a fault type, a risk level, a prediction position, confidence and operation and maintenance suggestions is generated. According to the system, intelligent monitoring, fault risk prediction, asset optimization management and operation and maintenance decision support of a cable operation state are realized, and scientificity and economy of cable management in a complex environment are improved.

The invention relates to an intelligent decision-making method, system, equipment and medium for sewage medicament addition, and the method comprises the following steps: detecting and preprocessing sewage water quality parameters, extracting feature vectors, and carrying out clustering analysis to obtain water quality categories. Historical dosing data is retrieved and subjected to statistical analysis, and an initial dosing scheme is generated; a water quality change curve is obtained by simulating the scheme, and then the optimal dosing scheme is obtained through optimization. And finally, generating and issuing an agent adding control instruction, and executing treatment, so that the technical problems that the traditional agent adding mode mostly depends on artificial experience or simple automatic control, and is difficult to cope with the complex working condition of dynamic change of water quality and water quantity, so that the agent adding is inaccurate, and the agent waste is possibly caused are solved.

The invention discloses a distributed photovoltaic power prediction method, system and device based on a Gaussian mixture model and a medium, and belongs to the technical field of photovoltaic power prediction.The distributed photovoltaic power prediction method comprises the steps that a time sequence vector is collected, principal component analysis is carried out on the time sequence vector, low-dimensional feature representation is obtained, and a power feature vector of each photovoltaic power station is formed; performing clustering analysis based on a probability model on the power feature vector to generate a plurality of photovoltaic power station clusters; for each cluster, acquiring meteorological input data through a set data source priority rule and a completion mechanism; and constructing a neural network power prediction model based on the accumulated power data in the cluster and the corresponding meteorological features, and outputting a future power generation power prediction value of the photovoltaic power station in the corresponding cluster. According to the invention, N photovoltaic power stations in a region are divided into M clusters through a GMM clustering method, so that the design is simplified; and the power prediction of the whole area is realized.

The invention provides a patient vital sign anomaly detection method based on an artificial intelligence technology, and relates to the technical field of data processing, and the method comprises the steps: collecting original sign data of a patient; calculating multi-dimensional characteristic parameters; establishing an individual baseline model, and determining a comprehensive reference interval in the model; the vital sign features monitored in real time are constructed into multi-dimensional feature vectors, the multi-dimensional feature vectors are input into the individual baseline model, and the deviation degree of the real-time multi-dimensional feature vectors in the comprehensive reference interval is calculated; performing a clustering analysis to identify an anomalous aggregation region; performing trend analysis, calculating change direction consistency and continuous change amplitude of the multi-dimensional feature vector, and generating a trend analysis result; calculating an accumulated change index in a continuous time window according to a trend analysis result to obtain a dynamic confidence score; when the dynamic confidence score continuously exceeds an adaptive threshold value, determining that a vital sign abnormal event exists; the autonomy and accuracy of the method for detecting the vital sign abnormity of the patient are improved.

The invention discloses a tunnel rockburst type prediction method and system based on multi-dimensional mechanism fusion and a medium. Relates to the technical field of tunnel rockburst. Dynamically acquiring multi-dimensional basic information in a tunnel construction process; inverting first proportions of different fracture modes of the micro-seismic event according to the micro-seismic information fusion moment tensor, and performing energy evolution on the acoustic emission information to obtain second proportions of different fracture modes of each acoustic emission event; the dynamic failure weights of different fracture modes are comprehensively obtained; spatial clustering analysis is carried out based on the dynamic damage weight and the multi-dimensional basic information, rockburst type probability models of different rockburst types are constructed, and the probabilities of different rockburst types are predicted; according to the scheme, the rockburst type probability model is constructed in combination with real-time multi-dimensional basic information, dynamic judgment and prediction of rockburst types are achieved, and technical guarantee is provided for deep tunnel construction safety.

The invention relates to the technical field of disease prediction, in particular to an intelligent risk prediction method based on a neural network, and the method comprises the steps: collecting blood glucose and body mass index data, carrying out the clustering analysis, and constructing a multi-risk group feature; a risk transfer track before attack is recognized by combining a historical index change path and time sequence analysis; and calculating an individual risk coefficient by using deep learning, and comparing the individual risk coefficient with a risk threshold to generate early warning information, thereby realizing dynamic accurate evaluation. According to the method, by collecting the blood glucose level and body weight index data and conducting standardization processing, risk group division based on health index clustering can be achieved, a group recognition system with health feature differentiation is constructed, and the structured understanding of the individual health trend is enhanced. And on the basis of the clustered group, extracting a fluctuation path of individual historical indexes by means of a time sequence mode, identifying key transfer characteristics before disease attack, and enhancing the traceability of the disease formation process.

The invention provides a cooperative early warning method, system, equipment and medium for deformation stress of soft soil around a pile, and relates to the technical field of underground engineering, and the method comprises the steps that monitoring data of the soft soil around the pile are obtained based on monitoring points, and the monitoring points comprise pile body monitoring points and soil body monitoring points; feature extraction is conducted on the monitoring data, and monitoring indexes reflecting pile periphery soft soil deformation and stress evolution are obtained based on information contribution degree difference and sensitivity selection; performing model construction based on the monitoring data and the monitoring indexes, and obtaining a deformation-stress collaborative map of the soft soil around the pile by considering risk assessment and spatial heterogeneity; and on the basis of the deformation-stress collaborative atlas, abnormal recognition of the soft soil around the pile is carried out, an abnormal area is obtained through embedded learning and clustering analysis, graded early warning is carried out according to the abnormal area, and an early warning result of the soft soil around the pile is obtained. The problem that an existing early warning method for the soft soil around the pile lacks dynamic sensing and combined early warning in the pile-soil interaction process is solved.

The invention provides an automatic data management method and system based on a multi-modal large model, and the method comprises the steps: collecting multi-source heterogeneous industrial data, and carrying out the standardization processing, and forming standardized multivariable time series data; constructing a process knowledge base, and performing semantic embedding coding on a process knowledge text and storing the process knowledge text; constructing and finely tuning a KTSF multi-modal large model, and fusing process knowledge semantics and multivariable time sequence data through a cross-modal attention mechanism to generate joint semantic representation; based on prediction of a KTSF multi-mode large model, outputting a residual error with actual data, and dynamically identifying abnormal data; performing attribution analysis; based on an attribution result, calling a KTSF multi-mode large model to generate a repair value, and performing intelligent correction on the abnormal data; the design quality evaluation and feedback learning module is used for calculating a data quality score and driving incremental updating of the model; and the design rule self-learning module is used for automatically extracting the governance rule through clustering analysis and updating the knowledge base.

The invention relates to the technical field of performance testing, and discloses a multi-parameter insulating sleeve aging performance testing method and system, and the method comprises the steps: carrying out the multi-parameter detection signal collection of an insulating sleeve, and obtaining standardized signal data; inputting the standardized signal data into a coupling recognition network for feature analysis to obtain a classification recognition result; performing aging factor threshold adjustment on the rising edge slope of the discharge pulse of the insulating sleeve based on the classification identification result to obtain a dynamic separation parameter; performing feature space matching and differential identification on the partial discharge signal according to the dynamic separation parameter to obtain feature classification data; phase clustering analysis and step response characteristic analysis are carried out based on the characteristic classification data to obtain the aging state variable coefficient of the insulating sleeve, the problem that the recognition precision of a traditional fixed parameter method is reduced in different aging states is solved, and high recognition accuracy and anti-interference robustness can still be kept in a complex electromagnetic environment.

The invention discloses an asphalt pavement base crack identification method and device based on a ground penetrating radar, and belongs to the technical field of road engineering pavement maintenance. The method comprises the following steps: 1) carrying out crack image identification on a radar slice map through a YOLOv8n model; 2) based on an identification result, extracting A-scan signals of a crack area, and classifying time-frequency features by using a Light GBM model; and 3) clustering classification results through a'multi-segment clustering + PCA 'analysis method, and filtering false detection cracks. The device is used for executing the method. According to the method, the map and the time-frequency characteristics are fused, the problem that the false detection rate is high due to subjective labeling or objective interference of a single identification method is solved, experiments show that the false detection rate is reduced to 2.8% from 11.2%, and the accuracy and engineering applicability of crack identification are improved.

The invention relates to the technical field of fault equipment detection, and discloses a power equipment fault detection method and system based on high-precision temperature measurement, and the method comprises the steps: scanning the surface temperature of power equipment through a high-precision temperature measurement device, obtaining a temperature distribution image, processing the temperature distribution image, and obtaining a temperature distribution matrix; carrying out gradient analysis and temperature difference identification on the temperature distribution matrix to obtain a hot spot candidate area; performing clustering analysis on the hot spot candidate region to obtain an initial hot spot region, and generating a static boundary by adopting a boundary tracking algorithm; correcting the static boundary according to the temperature change of each boundary point to obtain a hot spot area; and performing fault risk assessment according to the load data of the power equipment and the temperature data of the hot spot area. According to the invention, through temperature data analysis and region boundary correction, the hot spot region can be accurately identified, and in combination with a machine learning algorithm, the accuracy of power equipment fault risk assessment is improved, and safe and stable operation of a power system is ensured.

The invention discloses an algorithm method for large-model long context reasoning, which relates to the technical field of large language models and comprises the following steps of: dividing an input long text sequence into a plurality of initial text blocks; a semantic abstract is generated based on the initial text blocks, clustering analysis is conducted on the semantic abstract, the initial text blocks with similar semantics are combined into semantic hyperblocks, and a context organization structure with semantic representativeness is formed; the method comprises the following steps: generating key value cache data of each token in a large model preprocessing stage, grouping the key value cache data by taking semantic hyperblocks as logic boundaries, and establishing a mapping table for recording storage positions and states of the semantic hyperblocks; on the basis of semantic hyperblocks, semantic representative vectors of the semantic hyperblocks are combined, correlation scores between query vectors and the semantic hyperblocks are calculated, a block importance prediction model learns on the basis of context dependency features, high-order semantic prior is provided for subsequent attention screening, and key information omission caused by position offset is avoided.

The invention relates to the technical field of multi-sensor identification, in particular to a coal gangue detection and classification method and system based on multi-sensor fusion discrimination, and the method comprises the following steps: obtaining visible light and infrared images, calculating brightness and intensity judgment feature conditions, executing edge detection to extract gray segments, and fusing textures and a thermal field to generate a vector set. And performing clustering analysis to finish classification judgment, and outputting a coal gangue detection classification result. According to the method, a precise trigger mechanism is established through brightness and thermal radiation double-feature screening, boundary recognition sensitivity is enhanced through gray abrupt change point division, salient region extraction capacity is enhanced through weighted fusion of texture energy and gray gradient, and a cross-modal consistency feature group is constructed through combination of two-dimensional vector construction and similarity screening. The recognition expression integrity is improved, static threshold classification is replaced by vector distribution clustering, accurate mapping and classification decision making of material attributes in a complex scene are achieved, and the stability and the recognition rate of a coal gangue detection result are guaranteed.

The invention relates to the technical field of electricity metering anomaly monitoring, and provides a distributed resource access-oriented lightweight electricity metering anomaly monitoring method, which comprises the following steps of: acquiring electrical data and environment associated data of distributed access points at an edge side, and constructing a fluctuation fingerprint feature vector; when it is detected that the fluctuation fingerprint feature vector meets a preset fluctuation triggering condition, based on Pearson correlation analysis between the electrical data and the environment associated data, performing decoupling and elimination on false anomalies caused by environmental factors to obtain a fluctuation fingerprint feature vector of non-environmental suspicious anomalies; based on historical normal operation data, constructing a normal working condition mode library by adopting a clustering analysis method, and determining a feature center and a dynamic safety radius of each normal working condition mode; and calculating the feature distance between the non-environmental suspicious abnormal fluctuation fingerprint feature vector and each normal working condition feature center at the edge side, and judging whether the electricity consumption metering is abnormal or not according to the relationship between the feature distance and the dynamic safety radius.

The invention relates to the field of image recognition, in particular to an intelligent weld defect detection method based on machine vision, and the method comprises the steps: carrying out the collection and feature preparation of a weld region image, and obtaining a pixel point basic gray feature data set; performing trend prediction comparison on the local gray profile of the pixel point to obtain the deviation degree of the local gray profile; performing unit vector aggregation analysis on a pixel point neighborhood gradient direction to obtain a local gradient structure disorder degree; multiplicative modulation is carried out on the deviation degree of the local gray profile and the disorder degree of the local gradient structure to obtain a distance measurement function of structure perception; a weld defect recognition result is obtained by performing clustering analysis on a distance metric function of structure perception, so that the problem of missing detection caused by the fact that benign heterogeneous points and malignant defect points cannot be distinguished by the Euclidean distance in existing weld defect detection is solved.

The invention relates to the technical field of artificial intelligence and virtual reality, in particular to a large model scene drilling system based on AI-VR. The system comprises a student portrait construction module, a dynamic scene generation module, a multi-source data evaluation module and a holographic guide interaction module. According to the invention, the student portrait construction module collects multi-dimensional information and constructs a detailed portrait through clustering analysis, the dynamic scene generation module generates an initial scene model, and the multi-source data evaluation module constructs an operation step dependence graph, so that the operation condition in the learning process of the student is comprehensively and accurately evaluated; the holographic guidance interaction module uses a holographic projection technology to accurately guide students to operate correctly, and meanwhile, the AI large model dynamically adjusts scene difficulty and complexity according to real-time performance of the students, so that individual requirements of the students in different learning stages are met, error sources and influences are deeply analyzed, and a quantitative and scientific basis is provided for teaching evaluation and improved learning of the students.

The invention relates to the technical field of machine learning, and discloses a user recharging prediction method and device, equipment and a storage medium, and the method comprises the steps: associating behavior data of multiple platforms of a user through an equipment fingerprint algorithm, obtaining a user multi-dimensional feature set, determining a clustering number based on an elbow rule, and obtaining a user recharging prediction result; and performing clustering analysis on the user multi-dimensional feature set according to the clustering number, generating a user value grouping label, and inputting the user value grouping label into a random forest model to obtain recharging prediction results of different user groups. According to the method, multi-platform user behavior information is comprehensively integrated through an equipment fingerprint algorithm, data islands are broken, user value grouping labels are generated through elbow rule clustering, then the user value grouping labels are input into a random forest model to predict a recharging result, user basic features are considered, value grouping information is integrated, feature dimensions are enriched, and the recharging efficiency is improved. And users with different values can be described more accurately, so that the accuracy of recharging prediction of user groups with different values is improved.

The invention provides an uncertain scene-oriented micro-grid and shared energy storage collaborative robust optimization method. The method comprises the following steps of S1, constructing a micro-grid group and shared energy storage collaborative scheduling optimization operation framework; s2, constructing a wind and light uncertain scene set by adopting a scene generation technology; s3, constructing a load uncertainty scene set based on data-driven K-means clustering; s4, the activation probability of the load disturbance boundary is stably estimated based on the Wasserstein distance; s5, constructing a microgrid group and shared energy storage two-stage robust scheduling optimization model; step S6: carrying out dual transformation and Camp; solving the two-stage robust optimization model through a CG algorithm; step S7, designing an improved Shapley value method income allocation mechanism based on the network topology sensitive model; through load scene construction of data driving and clustering analysis, wind and light scene generation and clustering reduction technologies and in combination with collaborative optimization scheduling of the micro-grid group and shared energy storage, the renewable energy utilization efficiency can be improved, the intraday operation cost can be reduced, and collaborative development of energy storage and new energy can be assisted.

The invention relates to the technical field of data processing, and discloses a power sample data acquisition and classification method and system. The method comprises the following steps: synchronously acquiring active power, reactive power fluctuation and voltage harmonic data through a multi-point terminal, and constructing six types of characteristic index vector groups; a power load genetic optimization algorithm is used to optimize a classification threshold under power flow constraint; based on the optimal threshold value, clustering analysis is carried out through an EFC-KMeans algorithm in combination with impedance matrix characteristics; and inputting the clustering center into a multi-head power topology attention mechanism modeling node coupling relationship to realize power sample data classification and identification. The physical constraint conditions of the power system are effectively fused in the power sample data acquisition and classification process, so that the physical feasibility and engineering practicability of the classification result are improved.

The invention discloses a distributed collaborative decision-making system based on multi-modal data driving and an implementation method thereof, and relates to the technical field of group intelligence and distributed decision-making, and the system comprises a user end interaction module which provides a multi-modal interaction and decision-making scheme visual interface; the distributed node management module comprises a main node and an edge node, and the main node manages node registration, state monitoring and task distribution; the information fusion and preprocessing module is used for processing multi-source heterogeneous data; the decision analysis module is used for carrying out clustering analysis on the opinions and generating candidate schemes in combination with domain knowledge; the domain knowledge graph module is used for constructing a domain entity relationship network; the consensus mechanism and credit evaluation module determines multiple rounds of interaction rules, calculates a user credit value and influences an opinion weight; and the decision result output and feedback module is used for collecting user feedback for system optimization. According to the method, the stability, the response speed and the load balancing capacity are improved, the multi-source information processing and opinion aggregation quality is optimized, and efficient and reliable support is provided for distributed collaborative decision making.

The invention relates to the technical field of cross-border logistics, in particular to an artificial intelligence algorithm for cross-border overseas warehouse location storage and picking path optimization, which comprises the following steps: S1, obtaining order details, commodity characteristics and warehouse environment data, and monitoring warehouse states and cargo storage conditions in real time; s2, data preprocessing is carried out, features are extracted, clustering analysis is carried out, and association rules are mined; s3, performing rule matching, constructing a mixed integer programming model, performing constraint processing, and outputting a commodity storage strategy; and S4, converting the storage strategy into a warehousing operation instruction, and executing the warehousing operation instruction. The method has the beneficial effects that the accuracy of goods classified storage and the space utilization rate of the warehouse location can be improved, and the storage cost of the warehouse location is reduced.

The invention discloses an unmanned aerial vehicle cluster path planning and communication resource allocation joint optimization method for logistics distribution. The method comprises the following steps: constructing scene models of unmanned aerial vehicle cluster logistics distribution, wherein the scene models comprise an unmanned aerial vehicle cluster distribution model and an unmanned aerial vehicle cluster communication model; ground customers, namely target points, in the unmanned aerial vehicle cluster distribution model are subjected to clustering analysis, the target points are divided into Kclus clusters, so that the target points in the same cluster are relatively concentrated in the geographic position, meanwhile, it is ensured that the number distribution of the target points contained in each cluster is balanced through density constraint, and optimization of an initial logistics distribution task is achieved; performing unmanned aerial vehicle cluster path planning by using a simulated annealing algorithm to obtain an optimal flight path of the unmanned aerial vehicle cluster; and based on the position of the unmanned aerial vehicle in each time slot t in the future determined by the optimal flight path of the unmanned aerial vehicle cluster, performing distributed communication resource allocation on the unmanned aerial vehicle cluster in the dynamic flight process by using a competitive architecture depth Q network.

The invention provides a lamp layout method and a lamp, and relates to the technical field of intelligent lighting. Personnel activity data are generated by acquiring real-time signal data acquired by a sensor in a target space and performing clustering analysis and behavior recognition. And generating target illumination and color temperature data of each region through biological rhythm correlation modeling and time sequence prediction based on personnel activity data and historical rule data. And performing multi-target weight dynamic optimization and improved genetic algorithm solution by adopting the generated data and personnel movement characteristics to obtain a lamp control strategy. And performing priority division and differential driving adjustment in combination with the real-time distribution of the personnel and the aging state of the lamp, and generating illumination feedback data. And iteratively executing adjustment based on the feedback data, the target illuminance, the color temperature data and the adjacent lamp collaborative error optimization control parameters. Illumination distribution is optimized by dynamically adapting to personnel activity rules, real-time illumination requirements can be accurately matched to reduce energy consumption and improve utilization efficiency, and scene adaptability can be considered.

The invention discloses a clock domain crossing circuit timing sequence closed-loop optimization method and system, and relates to the technical field of integrated circuit design, and the method comprises the steps: reading a circuit netlist and timing sequence constraints, recognizing a converged path, and carrying out the clustering analysis to form a plurality of path groups; establishing a time sequence analysis model, and dynamically calculating the maximum delay constraint of the data signal in the path group; matching and executing at least one time sequence optimization strategy for each path group; and carrying out closed-loop time sequence verification, retaining a legacy path set which does not meet the constraint, and repeatedly executing the time sequence optimization strategy until a convergence condition is reached or the maximum preset number of iterations is reached. According to the method disclosed by the invention, the cross-domain path needing to be optimized in the DMUX structure can be accurately positioned without manual intervention, so that the path identification efficiency is improved, constraint omission or grouping deviation caused by manual operation is avoided, design defects are reduced from the source, and the design reliability of a chip is improved.

The invention provides a typhoon disaster risk traceability and prediction method based on disaster grade clustering and an interpretable model. Comprising the following steps: constructing an index system containing multi-dimensional typhoon disaster influence variables, carrying out clustering analysis on disaster consequences by utilizing a Gaussian mixture model based on historical typhoon disaster event data, and dividing severity levels of typhoon disasters; a Borderline-SMOTE algorithm is adopted to process the problem of class imbalance, and an XGBoost model is utilized to construct a nonlinear mapping relation between disaster influence variables and disaster grades; an SHAP method is introduced, the contribution degree of each input variable to disaster grade prediction is clarified, key disaster-inducing factors and disaster-inducing paths thereof are disclosed, and the interpretability of a model result is realized. The method also supports typhoon information input before a disaster, realizes disaster grade prediction and risk tracing, proposes targeted disaster prevention and reduction suggestions based on an SHAP analysis result, provides real-time and accurate typhoon disaster early warning and risk intervention basis for coastal cities, and has relatively strong practical guidance significance and popularization and application values.

The invention discloses a state monitoring method and system for an outdoor emergency power supply. Firstly, original data such as battery internal resistance, charging efficiency, temperature fluctuation and load abrupt change are collected to form an initial data set; and then noise suppression and fusion processing are carried out on the data set to obtain a smoothed battery parameter sequence. And constructing a dynamic trend vector by analyzing the differential change of the sequence, judging a potential anomaly level according to the slope of the dynamic trend vector, and outputting an anomaly probability score. And identifying an inter-parameter interaction cluster based on clustering analysis, and performing causal reasoning on a dominant cluster to determine a fault dominant factor. And finally, in combination with the real-time state, the environmental parameters and historical defect information, constructing a modeling matrix, and executing multi-dimensional clustering to identify specific fault types such as bearing wear, insulation aging and the like. If the fault is caused by internal resistance abnormity, an interference source is further positioned, and an accurate fault position is output. According to the invention, the battery fault monitoring accuracy and positioning capability in a complex environment can be effectively improved.

The invention belongs to the technical field of target detection, and discloses a passive millimeter wave target detection method and system based on regional clustering, and the method comprises the steps: dividing a brightness temperature image into a plurality of superpixel regions through a superpixel segmentation algorithm according to the similarity between target regions and the similarity between background regions, calculating a saliency image based on the regional statistical characteristics; according to the spatial distribution difference of boundary superpixels and internal superpixels, regional local direction centrality measurement is introduced to carry out clustering analysis, so that a candidate target region is highlighted; edge compensation is carried out on the preliminarily screened candidate target area; building a total variation optimization model by using regularization construction constraints; the local features of the compensated candidate target region are enhanced by solving the total variation optimization model; and finally, realizing accurate target detection and extraction through threshold segmentation operation. According to the invention, the accuracy of target detection and the integrity of target contour extraction can be improved.

The invention relates to the technical field of intelligent wheelchair scheduling, in particular to an intelligent wheelchair scheduling method and system. The method comprises the following steps: extracting an obstacle avoidance failure decision in a historical scheduling task, and generating a clustering logic of decision failure through clustering analysis; analyzing the motion trail deduction deviation of the sudden obstacle based on clustering logic, and further performing sudden risk pre-judgment lag analysis to obtain lag regression data; and lagging regression data is utilized to carry out front deviation correction memory learning of wheelchair scheduling braking, decision is optimized through reinforcement learning iteration, and finally optimized decision data is output. According to the method, the intelligent wheelchair scheduling technology is optimized, so that the intelligent wheelchair scheduling technology is more perfect.

The invention discloses a dialogue scene data visualization analysis method and system based on a knowledge graph, and relates to the technical field of data visualization analysis, and the method comprises the steps: obtaining dialogue scene data and context attributes, extracting related entity nodes and relation edges from a pre-constructed knowledge graph to construct a knowledge sub-graph, the dialogue data and the knowledge subgraph are fused to obtain dialogue semantic structure data, node importance analysis, semantic path analysis and intention clustering analysis are carried out based on the data to generate an analysis result set, and a dialogue semantic relation graph, a dialogue process path graph and a dialogue hotspot distribution graph are constructed respectively; a comprehensive visual analysis result is generated through unified coordinate mapping and weighted fusion, and meanwhile, a local semantic structure and a visual result are dynamically adjusted for newly added dialogue data in an incremental updating mode, so that real-time monitoring, mode recognition, semantic evolution accurate tracking and intelligent visual display of a dialogue scene are achieved.