39results about How to "Scientific prediction" patented technology

The invention belongs the virtual simulation technical field, in particular to a macroscopic, mid-scope and microscopic multilevel urban parking demand prediction model integrated system, which comprises a system data module, an urban overall parking demand macroscopic prediction module, a comprehensive development sharing parking demand mid-scope prediction module and a parking garage entrance service level microscopic analysis module, wherein the system data module is used for importing and storing parking demand prediction data; the urban overall parking demand macroscopic prediction module is used for predicting the overall parking demand; the comprehensive development sharing parking demand mid-scope prediction module is used for predicting the largest parking demand of each block and is connected with the urban overall parking demand macroscopic prediction module; the parking garage entrance service level microscopic analysis module is used for predicting a parking garage entrance service situation; and the three prediction modules are respectively connected with the system data module. The macroscopic prediction module not only considers the parking demand of traveling vehicles, but also considers the parking demand of the vehicles which are not on trip, the mid-scope prediction module considers the shared parking demand of multi-nature buildings under the reachability situation of buses, bi-directional correction of the prediction results of the macroscopic, mid-scope and the microscopic modules can be realized, the system quantitatively predict the parking demand of different cities of different levels so as to provide important support for different parking researches.

The invention provides a gestation diabetes risk monitoring system based on dynamic physics and physical and chemical factors and belongs to the field of medical instruments in the department of obstetrics and gynecology. The gestation diabetes risk monitoring system is characterized by comprising a computer, a toggle switch array, a resistor array and a gestation diabetes pathogenesis risk LED alarming module; a pregnant women information input module of dynamic physics check and physical and chemical factors, a logic switch array module of pregnant women gestation diabetes pathogenesis risk factors and logic regression value computation module of pregnant women gestation diabetes pathogenesis risk are arranged in the computer; a voltage comparison module and an LED array are arranged in the gestation diabetes pathogenesis risk LED alarming module. According to the invention, the logic switch value is utilized to control the make-and-break state of the toggle switch; a risk factor value in the logic regression manner is utilized to control the resistance value of the resistor array, so as to indicate the relative risk degree; the resistance value of the resistor array is utilized to control a voltage comparator, so as to output electrical level and light the LED alarm. According to the invention, the risk degree of the dynamic gestation diabetes can be comprehensively evaluated from multivariate physical and chemical factors and the real-time alarm can be conducted.

The invention discloses a quick search ruler for forest fire danger classes. The search ruler is provided with a quick search table comprising fire danger indexes of a plurality of factors, and corresponding comprehensive fire danger indexes and fire danger classes. The plurality of fire danger factors comprise four basic fire danger factors, namely temperature, relative humidity, precipitation and wind speed, two correction fire danger factors, namely vegetation green condition and snow coverage, and the like. The forest fire danger classes can be conveniently searched through the quick search table on the search ruler; and the search ruler can simply, accurately and scientifically predict forest fire danger.

The invention discloses a quick search ruler for grassland fire danger classes. The search ruler is provided with a quick search table comprising fire danger indexes of a plurality of factors, and corresponding comprehensive fire danger indexes and fire danger classes; the plurality of fire danger factors comprise four basic fire danger factors, namely temperature, relative humidity, precipitation and wind speed; the four basic fire danger factors are taken as grassland fire risk indexes; the weighted average of fire danger indexes of the four fire danger factors is taken as a comprehensive fire danger index; and a corresponding fire danger class is obtained according to the comprehensive fire danger index. The grassland fire danger classes can be conveniently searched through the quick search table on the search ruler; and the search ruler can simply, accurately and scientifically predict grassland fire danger.

The invention discloses a development zone planning land scale predicting method based on benefits of space. The development zone planning land scale predicting method based on benefits of space includes the steps: 1) predicting the planning industrial land scale based on benefits of space; 2) based on benefits of space, development potential and the like, determining distribution of the planningland scale in different industrial plates; 3)based on benefits of space of each industry, predicting the planning industrial land scale of each industry and the total planning industrial land scale; and 4) based on ratio prediction of the planning industrial land and other lands, predicting the development zone planning construction land scale, and at the same time, based on prediction of benefitsof space of the construction land, predicting the development zone planning construction land scale and performing mutual checking. The development zone planning land scale predicting method based onbenefits of space predicts and determines the development zone planning industrial land, the industry-classified land and the total planning construction land scale, can provide technical support fordevelopment zone planning making, town and country construction and land management, and can provide experience and reference for related town and country planning, and land use planning and management.

The invention provides a road traffic flow condition prediction method in a data sparse time period. When traffic flow data are insufficient, a transformation rule of a to-be-predicted road traffic flow in a time sequence is explored by using a time dynamic sequence supplementing method; a road traffic condition of a data sparse time period is restored by environment information feature extractionbased on a conditional random domain, so that a time evolution sequence of the road traffic flow in a period of time is obtained; matching with a historical time sequence of the road traffic flow isperformed to find out a time sequence fragment with a similar evolution trend and a traffic flow condition of a prediction time point is deduced. The test and on-site detection show that the prediction result of the traffic flow data sparse time period is basically accurate and reliable, so that defects of road traffic flow condition prediction in the data sparse time period in the prior art are effectively overcome, the traffic flow condition prediction weakness is eliminated, and the overall quality of the road traffic flow condition prediction method is improved.

The invention discloses a mobile network base station traffic prediction method, and belongs to the technical field of wireless communication data analysis. The method comprises the following steps: acquiring a current network cell load index, current network cell work parameter information and planning base station information; calculating a current network base station coverage area, a planningbase station coverage area, an adjacent current network base station set of the current network base station, and an adjacent current network base station set of the planning base station; obtaining akernel density model; calculating the initial prediction traffic of the base station; obtaining a base station traffic prediction model; and obtaining the predicted traffic of the planning base station. On the basis of simulation of current network actual data, an applicable kernel density model is obtained and initial traffic prediction is carried out, and then secondary prediction is carried out in combination with a machine learning algorithm, so that scientific and accurate prediction of planning base station traffic can be achieved, a reference basis is provided for network construction,and the optimal effect of the network construction cost is achieved.

The invention relates to the field of education big data mining, graph neural network and learner behavior modeling, and provides a knowledge tracking method based on test question heterogeneous graph representation and learner embedding, the method adopts a heterogeneous graph neural network technology in the deep learning field to represent multi-dimensional features of test questions, and meanwhile, complex learner characteristics are modeled in combination with a project reaction theory, and ability characteristics of learners are captured by adopting a clustering mode and the like; finally, the test question and learner mixed features are fused to a traditional knowledge tracking model, and knowledge tracking and learner performance prediction for different learner groups are achieved. According to the invention, the learning condition of the learner can be scientifically and comprehensively predicted, and the purpose of assisting the teacher in precise teaching is achieved.

The invention discloses a copy selection method based on copy response time prediction. Compared with an existing copy response time prediction algorithm, the method provided by the invention emphatically considers that the influence degree of sampling values of copy response time of different moments on prediction of copy response time is different. Closer is a sample to a prediction point, larger is a weight value, and otherwise, the weight value is smaller. Such a model solves the problem of different influence degree of influence factors on copy response time in different periods, thereby improving prediction precision.

The present invention provides a prediction method of a gas emission rate. The method comprises the steps of: 1. arranging a gas sensor, performing real-time monitoring of gas concentrations, and transmitting data to a database to calculate and store a gas emission rate; 2. extracting safety gas emission rates in the database, constructing a gas emission rate prediction model, performing gas emission rate prediction of input parameters according to the gas emission rate prediction model, and outputting a predicted value; 3. comparing the predicted value with a real-time monitoring value, forming error analysis, and updating the gas emission rate prediction model; and 4. repeatedly performing the steps 1-3, and performing real-time monitoring of the gas emission rate. Through adoption of high non-linear mapping of a neural network model and an Matlab language computing environment, data in the data is extracted in real time to correct the gas emission rate data model, and therefore, predicted errors are small, the prediction is more scientific and accurate, and scientization and quantification guidance is provided for avoiding outburst of gas.

The invention discloses a comprehensive humidity detection system, especially to a comprehensive humidity detection system for grain detection. A remote monitoring analysis management platform is adopted to monitor the water content of grain in a grain bin, and a sampling procedure is not needed, so the workload of grain monitoring is minimized and the labor cost is reduced. Large apparatuses with complex structures are not needed, so the detection cost is reduced. The system is capable of automatically identifying the position of a detection terminal in the grain bin, a manual system input step and other steps are minimized, the intelligent level of the system is improved, and grain monitoring is more convenient and accurate.

The invention belongs to the field of hydraulic engineering, and particularly relates to a dredging channel back-silting amount predicting method based on a timing sequence analysis-Markov chain method. The method includes the following steps that an original sequence of spatial dispersion is selected; a predicted value sequence is generated; the relative residual sequence of the original sequence and the predicted value sequence is calculated; the relative residual sequence is divided into intervals; Markov chain prediction is performed among the intervals; the water depth prediction interval is averaged to obtain a predicted water depth value, and an original water depth value is substracted from the water depth value to obtain a back-silting value. A timing sequence analysis method and the Markov chain are combined to obtain the timing sequence analysis-Markov chain prediction method, the change trends and random fluctuation of the sequences can be reflected at the same time, and the predicting method conforms to the actual change conditions of the dredging channel back-silting sequence better. By using the predicting method, the relative error rate is only 1.04%, the timing sequence analysis-Markov chain method can improve the precision by 97% compared with a single timing sequence method, and the prediction of the timing sequence analysis-Markov chain method conforms to actual measurement data better compared with the grey theory.

The invention provides a distributed situation awareness calling method and a distributed situation awareness calling device. The method comprises the steps of packaging interfaces for acquiring different information sources; facilitating customer calls, data streams in a unified format are obtained through preprocessing; extracting high-frequency project group elements from the data stream; generating high frequency association rules, situation evaluation is carried out for evaluation quantification; carrying out fusion with different evaluation systems; obfuscating the data elements, obtaining situation values of a single device and a local network; combining the architecture composition of the whole network; obtaining the situation value of the whole device; importing the situation values of different levels into a neural network model for prediction; and finally, visually displaying a prediction result, fully evaluating the whole distributed system and each single device, establishing association between each device and each layer, and performing rule detection and risk value calculation on different rules, thereby scientifically predicting future devices and providing valuablereference suggestions for users.

The invention discloses a risk judgment method for a polymer flooding oil-extraction technology and relates to the technical field of polymer flooding oil-extraction. The risk judgment method comprises the steps that the numerical values and the application boundaries of risk indexes of an oil reservoir are obtained, wherein the risk indexes comprise the temperature of the oil reservoir, the watermineralization degree of the oil reservoir, the permeability, the crude viscosity, the concentration of divalent cations, the permeability variation coefficient, the buried depth of the oil reservoirand the relative density of crude; whether the numerical values of the risk indexes are in the application boundaries or not is judged, when the numerical values of all the risk indexes are in the application boundaries, the risk scores, corresponding to the numerical values of the risk indexes, of the risk indexes are obtained according to a first preset rule; according to the risk scores of therisk indexes, the risk evaluation score of the oil reservoir is obtained according to a second preset rule; and the risk degree of the polymer flooding oil-extraction technology of the oil reservoiris judged according to the risk evaluation score. According to the risk judgment method for the polymer flooding oil-extraction technology, the more scientific and comprehensive risk evaluation scoreis obtained by considering the influences of the multiple risk indexes.

The invention provides a situation awareness virtualization method and a situation awareness virtualization device. The method comprises the steps of packaging interfaces for acquiring different information sources; facilitating customer calls, obtaining data streams in a unified format through preprocessing; extracting high-frequency project group elements from the data stream; generating high frequency association rules, carrying out situation evaluation for evaluation quantification; carrying out fusion with different evaluation systems; and obfuscating the data elements, obtaining situation values of a single device and a local network; combining the architecture composition of the whole network; and obtaining the situation value of the whole device. According to the method, situationvalues of different levels are imported into a neural network model for prediction. Finally, a prediction result is visually displayed. The whole network and each single device are fully evaluated. The association is established between each device and each layer, so that future devices can be scientifically predicted. Valuable reference suggestions are provided for users.

The invention discloses an aquaculture state monitoring method based on a hidden Markov model, and the method comprises the following steps: S1, building an aquaculture model based on the hidden Markov model according to the relationship between a hidden parameter extracted based on an aquaculture rule and an aquaculture dominant state, and enabling the hidden parameter to be used for representingaquaculture abnormal state information; S2, obtaining breeding dominant states at different moments, wherein the breeding dominant states comprise breeding water environment information and fish school activity information; S3, obtaining an observation sequence according to the breeding dominant state; S4, according to the observation sequence and the aquaculture model, various abnormal probabilities are obtained through calculation, if the abnormal probabilities are larger than corresponding abnormal threshold values, it is considered that corresponding anomalies appear, and if not, it is considered that no anomalies appear. The method has the technical characteristics of comprehensive monitoring, real-time monitoring and accurate abnormal monitoring.

The invention provides a production data statistics and analysis system of air traffic control automation system, which is deployed in a hardware environment and comprises: an interface subsystem forreceiving control duty operation record information output by an OMSS system and information output by a control tower electronic process list system and an air traffic control automation system; a database subsystem which comprises a basic database and a statistical database; a data recording subsystem which is used for acquiring the information sent by the interface subsystem, analyzing the information and storing the information into the basic database; a statistical calculation engine which is used for carrying out background statistical calculation on the data in the basic database and storing the data into a statistical database; and a Web subsystem which exchanges information with the statistical database of the database subsystem so as to provide service for the browser terminal ina Web mode. The statistical and analysis system automatically forms flight flow statistical data of waypoints, airways, sectors and the like, and analysis data of system hardware operation states, radar data quality and the like.

The invention relates to a technology for preparing coal water slurry from wastewater, and aims to provide a prediction and optimization system and method for intelligently determining a wastewater coal water slurry preparation scheme. The prediction and optimization system comprises a coal water slurry forming concentration prediction module and a wastewater proportion optimization module, wherein the coal water slurry forming concentration prediction module comprises a wastewater property database unit, a coal and additive type selection unit and a slurrying data export unit, and is used forpredicting the coal water slurry slurrying concentration according to the selected types and proportions of wastewater, coal types and additives; and the wastewater proportion optimization module comprises a wastewater proportioning optimization unit and a proportioning scheme data export unit, for optimally determining the optimal blending ratio of various types of wastewater by taking the highest pulping concentration as a target. According to the prediction and optimization system, an optimal way for mixing and utilizing various wastewater is realized, and the efficient, clean and low-costutilization of various wastewater in industries such as coal conversion and the like can be promoted. The prediction and optimization system can select the optimal wastewater proportioning scheme toprepare the wastewater coal water slurry, thereby enhancing the benefits, can save tedious steps of measuring the concentration of the coal water slurry by a test method, thus reducing the operation cost, and shortening the operation time.

The invention belongs the virtual simulation technical field, in particular to a macroscopic, mid-scope and microscopic multilevel urban parking demand prediction model integrated system, which comprises a system data module, an urban overall parking demand macroscopic prediction module, a comprehensive development sharing parking demand mid-scope prediction module and a parking garage entrance service level microscopic analysis module, wherein the system data module is used for importing and storing parking demand prediction data; the urban overall parking demand macroscopic prediction module is used for predicting the overall parking demand; the comprehensive development sharing parking demand mid-scope prediction module is used for predicting the largest parking demand of each block and is connected with the urban overall parking demand macroscopic prediction module; the parking garage entrance service level microscopic analysis module is used for predicting a parking garage entrance service situation; and the three prediction modules are respectively connected with the system data module. The macroscopic prediction module not only considers the parking demand of traveling vehicles, but also considers the parking demand of the vehicles which are not on trip, the mid-scope prediction module considers the shared parking demand of multi-nature buildings under the reachability situation of buses, bi-directional correction of the prediction results of the macroscopic, mid-scope and the microscopic modules can be realized, the system quantitatively predict the parking demand of different cities of different levels so as to provide important support for different parking researches.

The invention provides a space-time traffic flow prediction method driven by enhanced hierarchical learning. With full utilization of mutual correlation of related road sections in time and space, a nonlinear, high-dimensional and random road traffic flow evolution mode is dynamically simulated through a reinforced hierarchical learning network; road traffic flow feature extraction based on a restricted Boltzmann machine model is designed and realized; and dimensionality reduction is further carried out on road traffic flow data of an input layer and the road traffic flow characteristics afterdimensionality reduction are classified by using an SVM method to obtain a final traffic flow prediction result. The tests and on-site detection show that the accuracy of the prediction result is over 85.6% when the reliability of the sample is 75%; and the accuracy of the prediction result is over 96.3%, when the reliability of the sample is 90%. Therefore, the accuracy and reliability of traffic flow prediction are greatly improved. The traffic flow prediction method having advantages of solid theoretical basis, good traffic flow prediction timeliness and good real-time performance of the prediction result has the wide application space.

The invention discloses a mobile network base station traffic prediction method, which belongs to the technical field of wireless communication data analysis. It includes: obtaining the load index of the existing network cell, the industrial parameter information of the existing network cell, and the planned base station information; calculating the coverage of the existing network base station, the planned base station coverage area, the set of adjacent existing network base stations of the existing network base station, and the adjacent existing network of the planned base station A collection of base stations; obtaining a kernel density model; calculating the initial predicted flow of the base station; obtaining a forecast model of the base station flow; obtaining the predicted flow of the planned base station, etc. Based on the simulation of the actual data of the existing network, the present invention obtains the applicable kernel density model and performs the initial traffic prediction, and then combines the machine learning algorithm to perform the secondary prediction, which can realize the scientific and accurate prediction of the planned base station traffic, and provide a reference for network construction , so that the cost of network construction can achieve the best effect.

The invention discloses a risk judgment method for a polymer flooding oil-extraction technology and relates to the technical field of polymer flooding oil-extraction. The risk judgment method comprises the steps that the numerical values and the application boundaries of risk indexes of an oil reservoir are obtained, wherein the risk indexes comprise the temperature of the oil reservoir, the watermineralization degree of the oil reservoir, the permeability, the crude viscosity, the concentration of divalent cations, the permeability variation coefficient, the buried depth of the oil reservoirand the relative density of crude; whether the numerical values of the risk indexes are in the application boundaries or not is judged, when the numerical values of all the risk indexes are in the application boundaries, the risk scores, corresponding to the numerical values of the risk indexes, of the risk indexes are obtained according to a first preset rule; according to the risk scores of therisk indexes, the risk evaluation score of the oil reservoir is obtained according to a second preset rule; and the risk degree of the polymer flooding oil-extraction technology of the oil reservoiris judged according to the risk evaluation score. According to the risk judgment method for the polymer flooding oil-extraction technology, the more scientific and comprehensive risk evaluation scoreis obtained by considering the influences of the multiple risk indexes.

The invention provides a method for intelligently scheduling buses, which is characterized in that: an electronic terminal of station is set at a bus station which is connected with a bus-mounted system through a wireless module wirelessly, and connected with a bus scheduling center through a GPRS (general packet radio service) module and a transmission network wirelessly so as to acquire the passenger flow volume at the bus station in real time. A predictor of scheduling decision software is connected with a passenger flow volume collector so as to predict passenger flows. A fuzzy decision device is connected with the predictor and the passenger flow volume collector so as to identify a bus running mode; and output of the fussy decision device is connected with a peak BP (back propagation) network, a middle-peak BP network and a low-peak BP network respectively so as to realize the optimal departure interval decisions under different running modes. The method has the advantages that: (1) the passenger flow information is real-time and reliable; (2) the prediction is scientific based on real-time passenger flow; and (3)the scheduling decisions are made under the different modes, and the results are more reliable. The method provided by the invention realizes exact monitoring, scientific prediction and reasonable decision, can be applied to the scheduling of bus system and has huge economic and social benefits.

The invention discloses a method and system for predicting an oil and gas enrichment area based on potential energy values and physical property values. The method comprises the steps: according to drilling data, the potential energy values and the physical property values of all measuring points in a region are calculated; the potential energy values and the physical property values of all the measuring points and the corresponding oil bearing saturation of all the measuring points are calculated, and the facies-potential reservoir controlling function relationship is obtained; and accordingto the facies-potential reservoir controlling function relationship, the oil and gas enrichment area in the region is predicted. According to the drilling data and laboratory measurement data, geological features in the exploration region are comprehensively analyzed, a typical oil and gas reservoir is analyzed, the relationship between a power system and of oil and gas distribution is determined,the oil and gas enrichment area in the region is predicted, and oil and gas exploitation is facilitated.

The present invention provides a method and device for calling distributed situational awareness, which encapsulates the interfaces for collecting different information sources, which is convenient for customers to call, obtains a data stream in a unified format through preprocessing, and extracts high-frequency item group elements from the data stream, Generate high-frequency association rules and send them to situation assessment for evaluation and quantification. Through the integration with different assessment systems and fuzzy processing of data elements, the situation value of a single device and local network is obtained, and the situation of the entire device is obtained by combining the structure of the entire network. value, import situation values ​​at different levels into the neural network model for prediction, and finally visualize the prediction results, fully evaluate the entire distributed system and each individual device, establish associations with each device and each layer, and perform different rules for different rules. Rule detection, calculation of risk value, so as to scientifically predict future devices and provide users with valuable reference suggestions.

The invention discloses a flood inundation analysis and early warning system for power transmission facilities. The system is composed of a flood inundation analysis module, a data presentation module, a flood inundation statistic output module, a power transmission facility inundation knowledge base module and a early warning module, can quickly, accurately and scientifically simulate, measure and calculate the flood inundation range around the power transmission facilities and the water depth distribution of the inundated area, and can respectively present the analysis result in two-dimensional and three-dimensional views so as to report the inundation state of the power transmission facilities and early warn the inundation risk of the power transmission facilities, thereby providing important information support and decision basis for flood prevention and disaster mitigation for the power transmission facilities.

The present invention provides a weighted and quantized situational awareness method and system, which collects data from different information sources, obtains a data stream in a unified format through preprocessing, extracts high-frequency item group elements from the data stream, generates high-frequency association rules, and sends Through the integration of different evaluation systems and fuzzy processing of data elements, the situation value of a single device and local network is obtained, combined with the structure of the entire network, the situation value of the entire system is obtained, and the situation of different levels Import the value into the neural network model for prediction, and finally visualize the prediction results, fully evaluate the entire system and each individual device, associate each device and each layer, and weight the elements of the high-frequency project group, so that future future The system makes scientific predictions and provides users with valuable reference suggestions.