50results about How to "Accurate decision support" patented technology

The invention discloses an evaluation method based on water ecological environment monitoring, and relates to the technical field of water ecological environment evaluation. Comprising the steps of data collection: obtaining a river basic information data set, a monitoring equipment information data set and a historical monitoring information data set, and building a cloud server to store the river basic information data set, the monitoring equipment information data set and the historical monitoring information data set. According to the method, each region is accurately monitored through region division of river landforms and a targeted monitoring method, the timeliness of monitoring data is ensured, the water quality condition can be evaluated in real time and the water quality of the corresponding region under unique weather can be evaluated by acquiring a region monitoring data set and a weather information data set in real time to cooperate with an evaluation model, and the water quality evaluation accuracy is improved. In addition, weather changes can be monitored and early warned, timely support is provided for dealing with emergencies, and by summarizing the method, related departments can formulate more reasonable treatment schemes, the water quality management efficiency and effect are improved, and the water quality problem is found and solved in time.

The invention relates to an Internet of Things cooperative sensing method based on encryption protection, and belongs to the technical field of Internet of Things. According to the method, security protection of sensitive data in communication transmission and cloud computing processes is ensured by using a fully homomorphic encryption algorithm, and a convolutional neural network model framework is designed to perform data prediction and abnormal source identification in combination with multi-source factor data. The model fuses a space environment topological structure and content features, and is beneficial for improving the scientificity of collaborative perception decision-making in the scene of the Internet of Things. According to the invention, through combination of the fully homomorphic encryption technology and the graph convolutional neural network, data security and sharing problems in an Internet of Things data integration processing process are solved, security sharing application of cross-regional perception information is realized, and the depth decision level of Internet of Things monitoring management is improved.

The invention provides a park personnel behavior early warning method and system based on big data and artificial intelligence, and relates to the technical field of intelligent monitoring. The source domain data is used as target domain data, a deep learning network model is established in combination with the historical behavior data set of the park personnel, and the deep learning network model is trained; using the trained deep learning network model to identify and classify the behaviors of the personnel in the park collected in real time; an early-warning model is constructed through a big data technology, the early-warning model is used for analyzing behaviors, recognized in real time, of personnel in the park, abnormal behavior judgment and early warning are carried out, the early-warning behaviors judged manually and the early-warning behaviors judged by a system are labeled and then synchronized to a source domain, the early-warning threshold value and strategy can be dynamically adjusted, and the early-warning effect is improved. The intelligent level of safety management of the park is improved, scientific and accurate decision support is provided for park managers, potential risks are effectively reduced, and safe and stable operation of the park is guaranteed.

The invention relates to the technical field of administrative office management, and particularly discloses an administrative office business whole-process visual management method, which comprises the following steps: constructing a real-time information communication system based on a specified platform; setting a task management module; carrying out fusion analysis on the collected real-time task data by adopting a Dempster-Shafer evidence theory; displaying at least one kind of information of task execution state, progress and key indexes through a visual display interface, and realizing whole-process visualization of the task; an authority management module is arranged to control the data access authority of the user and ensure the data security; and a task sharing and collaboration function is provided, and users are allowed to share task-related data and exchange opinions in real time and collaborate to complete the task. According to the method provided by the invention, the office efficiency and the management level can be effectively improved, and the internal information circulation and cooperation of an enterprise are promoted.

The invention discloses a method for calculating and visualizing the bearing capacity of a power transmission line under extreme meteorological conditions based on GIM and WebGIS. The method comprises the whole process from data analysis to real-time stress monitoring. A three-dimensional model of a power assembly is constructed by analyzing a GIM file of a power transmission line, and the three-dimensional model is exported into a standard format for verification. Meteorological data are collected and processed, meteorological parameter influence coefficients are configured, ultimate bearing capacity is calculated, and stress analysis and safety evaluation are carried out. The space coordinates of the sag conductor are calculated based on the three-dimensional model of the power transmission line, and a real-time conductor model is generated in combination with meteorological data and physical parameters of the catenary. And dynamically updating the state of the power transmission line through a three-dimensional visualization technology in combination with the tower model, the stress data, the lead model and the lead deformation degree, so as to find potential risks in time and take countermeasures. According to the scheme, accurate decision support can be provided for safety monitoring and maintenance of the power transmission line.

The invention discloses an underground powerhouse axis direction selection method adopting a knowledge graph and a block theory and a readable storage medium, and the method comprises the steps: S1, constructing an underground powerhouse axis knowledge graph: selecting factors through the axis direction of an underground powerhouse, determining entity object feature indexes, collecting and processing an entity attribute database, and constructing a knowledge graph; and mapping the entity attribute data and the entity relationship to nodes and edges of the knowledge graph, and establishing the knowledge graph. S2, sorting underground powerhouse area survey data, setting sporophores and attribute data of each entity object, and obtaining underground powerhouse axis entity objects and attributes through a knowledge graph; and S3, in combination with a block theory, selecting a proper axis direction of the underground powerhouse. The problems that in the prior art, a traditional arrangement scheme mainly depends on artificial experience and professional knowledge, and a systematic and scientific method is lacked to support the decision making process are solved, and the decision making efficiency is improved.

The application provides a PAN precursor contribution quantification method based on real atmospheric observation constraints, relates to the technical field of atmospheric pollution tracing, and comprises the following steps: obtaining real atmospheric observation data of a target region, including PAN, nitrogen oxides, ozone, volatile organic compounds, carbonyl compounds, photolysis frequency and meteorological parameters; constructing an observation constraint vector, establishing an observation constraint box model containing PAN conversion, VOCs oxidation, free radical circulation mechanism and the like and driving operation, recording the relationship between reaction flux and species to form a dynamic reaction network; determining a generation flux based on PAN mass conservation, reversely tracing peroxyacetyl radicals, intermediate products to observation precursors from the PAN generation reaction, and distributing the contribution according to the flux proportion; merging the contribution of the same precursor and its oxidation products, and quantifying the contribution amount and contribution rate of each precursor to PAN generation. The application overcomes the defects of high uncertainty and artificial assumption, and accurately quantifies the actual contribution of real atmospheric PAN precursors.

This invention discloses a method for predicting influent water quality of wastewater treatment plants based on impact-triggered refitting, specifically relating to the field of urban wastewater treatment technology. The prediction method includes the following steps: S1: Data acquisition and time alignment; S2: Sensor dead value removal and causal forward imputation; S3: Causal anomaly identification and peak / impact classification; S4: Impact-preserving preprocessing sequence construction; S5: Daily Fourier term construction; S6: SARIMAX model establishment; S7: H-step forward rolling prediction; S8: Impact-triggered short-window refitting; S9: Result output and impact early warning; Integrated prediction and early warning, with high engineering practicality: It realizes the integration of short-term rolling prediction of water quality indicators and impact risk early warning, outputting multi-dimensional prediction evaluation indicators and graded early warning information. The early warning information includes key engineering parameters such as impact amplitude and duration, which can directly provide accurate decision support for process control and operation scheduling of wastewater treatment plants.

The invention provides a power grid equipment standard knowledge graph construction method and system, and the method carries out the construction of a power grid equipment graph based on a natural language processing technology, a digital standard and standard knowledge, finally achieves the core functions of knowledge graph question answering, reading understanding question answering, intelligent searching and the like, achieves the man-machine interaction type conversation, and improves the work efficiency. And providing question and answer type accurate search covering various objects such as standards, equipment, parts, institutions, people, indexes and the like for a standard business application scene.

The application discloses a user-side power failure analysis method and system, which comprises the following steps: acquiring and sorting power grid state data and user terminal power consumption data sequences of a target area in chronological order; intelligently judging whether there is a power grid abnormal event in the power grid state data sequence based on a threshold strategy dynamically corrected based on environmental temperature; if there is, then according to the event time node, the associated sub-sequence is intercepted from each user power consumption data sequence, and the power consumption rate of change and the power failure duration are extracted as key features; then, the features are input into a pre-trained power failure classification model to identify the power failure type; finally, the density clustering algorithm is used to automatically generate a visual power failure influence area in combination with the spatial distribution information of the user terminal, and the visual power failure influence area is pushed to the user terminal. The power grid and user-side multi-source data are effectively fused, and the rapid and accurate identification of the power failure and the visual positioning of the influence range are realized.

The application discloses a post-earthquake railway structure state evaluation method and system based on multi-source data fusion, which comprises the following steps: constructing a finite element model according to the structure of a regional railway network, generating a simulation data set, training a physical information neural network model, and forming a proxy model library; collecting multi-source observation data, inverting the complete posterior probability distribution of the damage parameters according to the Bayesian theory, the structure damage parameters of the physical information neural network proxy model and the multi-source observation data; extracting the statistical characteristics of the damage parameters from the posterior probability distribution, probabilistically grading the damage degree of the structure, generating driving constraint suggestions according to the damage probability grading and combining the specifications, and reducing the Bayesian inversion time from several days to several hours through the physical information neural network proxy model, thereby improving the evaluation efficiency; the output of the Bayesian method is a probability distribution, which clearly shows the uncertainty range of the evaluation result and quantifies the uncertainty.

The invention relates to the technical field of farmland improvement, in particular to a farmland improvement zoning method and system, and the method comprises the following steps: 1, zoning factor selection and weight calculation; 2, processing partition basic data; 3, partition factor calculation and statistics; 4, performing partition data standardization calculation; and 5, constructing an accurate zoning model for farmland improvement. According to the method, farmland improvement suitability zoning can be accurately carried out, and a scientific and reasonable basis is provided for farmland improvement project planning and design.

This invention discloses a multi-dimensional indicator evaluation and automatic grading system for brand promotion tasks, relating to the field of brand promotion technology. It includes a data processing module for acquiring task feature data from a promotion task database, including dynamic features such as target audience segmentation, channel selection, and budget allocation. The module removes duplicate records and missing values ​​through data cleaning techniques and uses standardization techniques to convert the feature data into a structured feature dataset with a mean of 0 and a variance of 1, resulting in a structured feature dataset. This multi-dimensional indicator evaluation and automatic grading system for brand promotion tasks enables intelligent grading, optimized scheduling, and dynamic adjustment of promotion tasks, improving task execution efficiency and resource utilization, and providing more accurate decision support for promotional activities.

The invention relates to the technical field of image recognition, and provides a rice field heavy metal pollution risk assessment method and system based on image recognition, and the method comprises the steps: obtaining the multispectral image data of a rice field region; from the multispectral image data, for each pixel point, calculating relative spectral characteristics between selected spectral bands related to heavy metal stress; comparing the relative spectral features with a pre-established heavy metal stress feature mode set to obtain a feature comparison result; the heavy metal stress characteristic mode set is established based on relative spectral characteristic modes corresponding to heavy metal stress observed in different equipment degradation states; and according to a feature comparison result, based on a similarity discrimination threshold and spatial continuity, identifying a heavy metal pollution area and carrying out risk grading so as to obtain corresponding rice field heavy metal pollution risk assessment information. The method has the effect of improving the accuracy of rice field heavy metal pollution risk assessment.

The application discloses a labor risk assessment system based on deep learning judgment, belongs to the technical field of artificial intelligence and labor risk assessment, constructs an end-to-end technical architecture of "multi-modal feature fusion-multi-task deep learning-double path fusion analysis", maps multi-source labor data to the same vector space through multi-modal feature fusion, realizes dynamic evolution of multi-dimensional risk assessment standards by combining multi-task machine learning and reinforcement update, constructs a pre-deployment and in-service double-path judgment mechanism, fuses the evaluation results of three dimensions of the deployment unit risk, the deployer personal risk and the post risk, outputs recruitment decision suggestions and company overall labor operation risk rating, not only realizes a fundamental leap of labor risk assessment from static rule statistics to dynamic intelligent decision, but also realizes a closed loop coverage of labor risk from "pre-entry" to "in-process monitoring", and provides accurate and differentiated decision support for enterprises at different stages.

This invention discloses a ship behavior decision-making method based on heterogeneous information fusion and ensemble reasoning. First, it integrates multiple data sources to preprocess different types of data. Then, it extracts features from different data using deep learning technology and converts them into vector form. Next, it fuses different types of features through a cross-attention mechanism to generate a unified comprehensive vector for behavior prediction. Finally, it fine-tunes a pre-trained decision model using the fused information, enabling the model to generate natural language navigation strategies based on the prediction results. The fine-tuned decision model is then tested offline, deployed in the ship system, and continuously optimized through a feedback mechanism. Finally, it introduces multiple decision models and calculates the Shapley value for each model to generate a weighted voting decision result. This invention improves navigation safety and efficiency.

The invention relates to the technical field of energy storage equipment monitoring, and discloses a fault prediction and early warning system for an energy storage box-type substation. The multi-modal data acquisition and preprocessing module, the macroscopic operation mode vector extraction module, the real-time causal calculation engine module, the real-time dynamic causal entropy map construction module and the working condition causal baseline dynamic mapping module generate a theoretical health baseline map corresponding to the current working condition in real time according to the macroscopic operation mode vector; an atlas topology difference and anomaly detection module generates a difference atlas by comparing the real-time dynamic causal entropy atlas with the theoretical health baseline atlas; the topology fingerprint and fault diagnosis module analyzes the difference atlas to extract topology fingerprint vectors and matches a fault knowledge base to output a diagnosis conclusion. By constructing the health base line which is dynamically adjusted along with the working condition, normal operation fluctuation can be effectively filtered out, the accuracy of fault detection is improved, and diagnosis from abnormal detection to specific fault attribution is realized.

The invention discloses a method for grading geomagnetic storm disasters caused by CME, and relates to the technical field of space weather disaster monitoring, and the method specifically comprises the steps of data collaborative collection, data standardization preprocessing, parameter fusion inversion, trigger source positioning and grade pre-judgment and correction. According to the method, multi-source satellite data are synchronously acquired through a solar dynamics observatory, a sun-earth relation observatory and a Parker solar detector, and through a standardized preprocessing process, a CME comprehensive parameter inversion formula is fused with the multi-source satellite data; comprehensive inversion of multi-dimensional key parameters such as CME explosion time, source region position, three-dimensional propagation direction, initial speed, acceleration, mass and magnetic flux is realized, the innovation point directly aims at the defects that a traditional method is single in data source and incomplete in inversion parameter, and through a multi-source data fusion and mutual verification mechanism, the multi-dimensional key parameters of the CME are obtained. The precision and reliability of CME parameter inversion are improved, and data support is provided for subsequent geomagnetic storm trigger source positioning and disaster grading.

The present invention provides a full-process water scheduling simulation mutual feedback method, which can dynamically reflect the current water resources status and user needs by acquiring the water user demand data of the target area and the actual data of water project scheduling in real time. The method constructs a multi-time scale runoff forecasting mechanism, and uses advanced prediction technology and models to predict the runoff and water resources status at different time scales in the future to reduce risks. The full-process water scheduling simulation mutual feedback method not only considers the water scheduling of a single time scale, but also comprehensively considers the water scheduling needs of multiple time scales such as annual, set scheduling period, monthly, ten days, and real-time through a multi-time scale runoff forecasting mechanism, which can better meet the water demand of different time scales. Finally, based on the interactive strategy data of water resources management and control conditions, the method conducts a joint scheduling simulation of water resources of water projects in the target area, and can comprehensively consider multiple factors to generate a mutual feedback scheduling plan.

The present invention relates to the field of remote sensing estimation technology, specifically to a spatially variable multi-scale soil organic matter remote sensing estimation method, comprising the following steps: by collecting soil samples at differentiated locations, testing the soil organic matter content and extracting environmental factors, performing spatial difference analysis, analyzing the spatial variation relationship between environmental factors and soil organic matter, generating spatial variation patterns, optimizing the spatial weighted relationship between remote sensing indexes and environmental factors, and obtaining spatial weighted results of environmental factors. In the present invention, by analyzing the spatial variation relationship between environmental factors and soil organic matter, optimizing the weighted results, improving the estimation accuracy, bandwidth optimization and soil organic matter weight adjustment list correct local outliers, enhancing robustness, spatial heterogeneity adjustment and error correction improve the reliability of results, dynamic optimization and real-time updating overcome the limitations of static models, ensure the timeliness and accuracy of estimation results, and provide more accurate decision support.

The invention discloses a mountain water system distribution visualization analysis method, and relates to the technical field of geographic information systems.The mountain water system distribution visualization analysis method comprises the steps that multi-source geological and hydrological data of a target area is obtained; based on the multi-source geological and hydrological data, generating at least one thematic visualization layer, the thematic visualization layer being used for expressing spatial distribution characteristics of geological or hydrological attributes of the target area; and fusing the at least one thematic visualization layer to generate a mountain water system comprehensive visualization view. According to the method, multi-source geological hydrological data of a target area is acquired, a plurality of thematic visual layers including a water system distribution visual layer, a geological risk marking layer, a climate distribution layer and the like are generated based on the data, and then the layers are superposed and fused with a three-dimensional terrain base model; the mountain water system comprehensive visual view is formed, and the problem that in a traditional method, all thematic layers are independently displayed, and effective fusion is lacked is solved.

The application belongs to the field of wisdom city space-time information platform, and is a space-time service unified management and intelligent monitoring method based on APISIX gateway. Through Admin API, upstream mapping tables of city and district levels are established to realize decoupling of back-end address and external access address, support hot update and non-restart traffic switching during service adding, deleting, modifying and inquiring, construct a finite state machine for service approval state, automatically trigger creation, update or deletion of gateway routing configuration through an event-driven mechanism, develop a quota plug-in embedded in the access stage of APISIX, use Nginx shared memory to configure a composite key with service ID: application ID: plug-in context, call the incr method to atomically increment the record request number, calculate the remaining quota, automatically reset when TTL expires, and return HTTP 429 when exceeding the limit, configure the http-logger plug-in to send structured logs to a log server, calculate service dimension and application dimension indicators in real time through access records and expose APIs, and configure three types of composite early warning rules for service availability, service performance and access compliance.

The present invention relates to the technical field of machine tool casting evaluation, and specifically to a method for evaluating the performance of CNC machine tool castings, the method comprising: performing preprocessing operations on machine tool casting production data, analyzing the distribution fluctuation of each data indicator, judging the amplitude of its change in the overall data, and obtaining the importance analysis results of the indicator. In the present invention, by performing in-depth preprocessing and comprehensive analysis on the machine tool casting production data, the method can more accurately capture and analyze the data changes of different material types and production batches, ensuring that the real impact of each factor in the evaluation process can be effectively reflected. Secondly, by re-adjusting the indicator weights and constructing an evaluation model based on similarity analysis, the ability to cope with data missing and quality fluctuations in the evaluation process is enhanced. Even in the case of unstable raw material supply or changes in the production process, the actual impact of these changes on casting performance can be effectively mapped.

The invention relates to a power distribution network fault identification method based on a whale optimization algorithm LSSVM, and belongs to the technical field of power system fault diagnosis, the method uses an improved TS-GAN model to solve the problem of insufficient fault samples, and provides sufficient data support for subsequent diagnosis; the fault starting moment is efficiently determined by using a break variable monitoring algorithm, and complex mathematical transformation and model establishment do not need to be carried out; according to the DBO-VMD algorithm, the optimization efficiency and precision of key parameters are improved, complex fault signals can be effectively decomposed, IMF with abundant features can be separated out, envelope demodulation analysis is carried out by selecting a maximum kurtosis IMF component, and features such as envelope information are extracted; according to the WOA-LSSVM algorithm, kernel parameters and penalty factors of the LSSVM are optimized, local extreme values are avoided, various short-circuit faults of the power distribution network are recognized, more accurate and more comprehensive decision support is provided for operation and maintenance of the power distribution network, and finally the operation efficiency and reliability of the power distribution network are improved.

This invention provides a method, apparatus, equipment, and medium for production prediction based on time-varying reservoir parameters. The method includes the following steps: S1, establishing a variable decline exponential production decline model for tight gas reservoir wells; S2, collecting historical gas production data of tight gas reservoir wells, and confirming the second undetermined characteristic parameter β and establishing a first linear model based on linear fitting of lnq and t / (lnt)β, wherein the slope of the first linear model is -α and the intercept is lnq. i Value; and S3, confirming the theoretical initial output q based on the first linear model. i The invention uses a first undetermined characteristic parameter α to predict gas well production using the variable decline exponent production decline model. This invention better reflects the production decline law of tight gas wells, is simple to operate, and has higher prediction accuracy than traditional decline models with a constant decline exponent. It can be widely used for production decline prediction in tight gas reservoirs.

The invention relates to the technical field of vehicle exit analysis, and discloses a vehicle exit analysis method and system based on machine learning and big data, and the method comprises the steps: constructing a multi-source data collection system, collecting multi-source data related to a vehicle exit, and carrying out the preprocessing, and obtaining a standard analysis data set; constructing a multi-dimensional association knowledge graph, performing association mining to obtain a plurality of conduction paths of each core index, and determining a plurality of weighted feature sets according to all the conduction paths; training a vehicle exit analysis model according to all the weighted feature sets and an ensemble learning algorithm, analyzing data collected in real time by using the trained vehicle exit analysis model, and outputting a prediction result of a vehicle exit trend; and according to the prediction result and a pre-constructed decision rule base, generating a vehicle exit decision, and through effective fusion and relation mining of multi-source heterogeneous data, improving key index prediction accuracy, thereby realizing accurate prediction and decision support of a vehicle exit trend.

The application discloses a multi-dimensional customer label-based attribution analysis method and device, equipment and a computer program product. The method comprises the following steps: acquiring user data; performing multi-dimensional customer label classification processing and summarizing on the user data according to a time dimension to obtain processed user data; acquiring attribution analysis parameter information required by a business; calculating attribution indexes according to the processed user data and the attribution analysis parameter information to obtain a calculation result of the attribution indexes; and performing attribution analysis according to the calculation result of the attribution indexes to obtain an attribution analysis result. The application realizes dynamic correlation analysis on multi-dimensional customer attribute and behavior data. The attribution index calculation and analysis are combined with the processed user data and the attribution analysis parameter, so that key factors influencing business index changes can be located, and scientific and accurate decision support is provided for financial institutions in market promotion, customer service optimization and the like.

This invention discloses an end-to-end unit combination method for power systems driven by a spatiotemporal attention graph neural network based on physical data fusion. The method includes: acquiring power system operating data; constructing a spatiotemporal self-attention graph convolutional neural network (SINNN), and building a unit combination model based on the SINNN; inputting the power system operating data into the unit combination model for two-stage model training; the first stage guides model parameter initialization based on a fusion strategy of physical mechanisms, local relaxation of integer variables, and supervised pre-training; the second stage uses goal guidance, physical mechanism constraints, and local relaxation of integer variables to achieve secondary adjustment of model parameters; introducing an adaptive penalty term update algorithm to obtain the trained unit combination model; and realizing power system unit combination decisions based on the trained unit combination model. This invention can effectively handle the temporal and spatial constraints in the unit combination problem, achieving rapid end-to-end unit combination decisions.

The present application belongs to the field of gas storage, and particularly relates to a cavity forming dynamic tracking analysis method, aiming at solving the problem of lacking systematic analysis method when processing complex cavity forming data. The present application comprises: obtaining cavity forming data, calculating salt cavity effective volume based on the cavity forming data; obtaining the underground soluble salt volume and static volume formula based on the salt cavity effective volume; calculating the current cavity forming progress and cavity forming engineering progress based on the underground soluble salt volume; calculating the wellhead water injection pressure and oil cushion pressure based on the blocking solvent interface depth and along-the-way water head loss; calculating the wellhead nitrogen pressure based on the connecting point liquid column pressure balance principle; calculating the gas-water interface depth based on the volume formula; and calculating the pressure at the gas-water interface at the well bottom based on the gas-water interface depth. The present application can accurately reflect the actual state of cavity forming, optimize the salt cavity development process, and improve the resource utilization efficiency.

This application provides a multi-task fusion-based method for safety monitoring of high-altitude edge operations, comprising: acquiring image or video data of the construction site, and extracting boundary information, including at least the edge area, based on the image or video data; identifying construction workers and their safety equipment wearing status in the image or video data; extracting key point information of the construction workers' bodies, and identifying dangerous actions based on the key point information; calculating the relative positional relationship between the construction workers and the edge area based on the boundary information and the key point information; determining the risk level of the construction workers through a preset decision model based on the relative positional relationship, safety equipment wearing status, and dangerous action identification results, and outputting early warning information according to the risk level. The monitoring method provided in this application achieves accurate risk assessment of high-altitude edge operations through multi-task fusion, realizes real-time early warning, and reduces the probability of false alarms and missed alarms.