148 results about "Decision-making models" patented technology

The invention discloses an Internet of things terminal secure access method and system based on edge computing. The method comprises the steps that an edge computing device carries out radio frequencyradiation signal collection on each legal sensing device, thereby obtaining collection results; the edge computing device preprocesses each legal device signal, removes outliers and carries out datanormalization on collected signals of each time; the edge computing device generates features through utilization of the normalized data, extracts feature vectors to generate feature data sets and transmits the feature vector sets to a cloud server; and the cloud server selects a classification algorithm to generate a data model, trains the data model according to the feature data sets and transmits an obtained decision-making model to the edge computing device. According to the method and the system, the data processing and access judgment are carried out at the edge computing side, and the method and the system are applicable to an Internet of things device interconnection scheme with limited resources and have the advantages of low computing complexity and high authentication accuracy.

The invention discloses a vehicle forced lane changing decision-making method based on a decision-making tree model. The vehicle forced lane changing decision-making method includes the following steps: firstly, reading related data during vehicle forced parallel lane changing in real time through a sensor; secondly, importing the obtained data into a vehicle forced lane changing decision-making module based on the decision-making tree model, wherein a method for building the module includes the steps of selecting training and testing data, splitting a tree, selecting attribute threshold values, pruning the tree, building the parallel lane changing decision-making tree model based on a weka platform and verifying the accuracy of the decision-making model; finally, forming a decision-making judgment result during vehicle forced lane changing through a decision-making module, and if the decision-making judgment result is that lane changing can not be carried out, giving an alarm in real time to remind a driver of the fact that lane changing can not be carried out. By means of the vehicle forced lane changing decision-making method, negative effects, caused by a complex early-warning algorithm and excessive decision-making judgment rules, on the judgment result are reduced, the accuracy and the reliability of decision-making judgment during vehicle forced lane changing are improved, and the false alarm rate is lowered.

The present invention discloses a vehicle control method and apparatus and a method and apparatus for acquiring a decision-making model. The vehicle control method, comprising: during travel of an unmanned vehicle, acquiring current external environment information and map information in real time; determining vehicle state information corresponding to the external environment information and map information acquired each time according to a decision-making model obtained by pre-training and reflecting correspondence relationship between the external environment information, map information and vehicle state information, and controlling a travel state of the unmanned vehicle according to the determined vehicle state information. Application of the solution of the present invention can improve security and reduce the workload.

The invention discloses an anti-fraud recognition method used for solving the problem that the anti-fraud capability is insufficient in the medical field. The method provided by the invention comprises the following steps of determining a target event; extracting target data related to the target event; and processing target data by adopting at least two methods of a decision-making model constructing method, a fraud data recognition method and a fraud behavior recognition method. The invention further provides a storage medium and a server with a safe computer.

The invention discloses an air conditioning load control strategy making method based on direct load control. According to the air conditioning load control strategy making method, a thermodynamic model of a single air conditioning unit is established and used for representing the relation among air conditioning power, temperature and time; an ideal in-turn control strategy for centralized control of air conditioning loads is analyzed according to the thermodynamic model of the single air conditioner unit and requirements of users for comfort level specified in a direct load control contract, and reduced upper limit values which can be provided by all the air conditioning loads under control are calculated. A decision-making model for the direct control of the air conditioning loads in actual electric power system operation is established. Through optimization of the control strategy of all the air conditioning loads under control, the deviation between actual force exerted by the air conditioning loads and ideal reduction quantity is minimized. Moreover, continuous starting and closing time of the air conditioning loads is used for replacing constraint conditions of a real-time room temperature representation air conditioning in-turn control strategy.

A computer implemented method of constructing a social network, the method including constructing the social network from a plurality of disparate, heterogenous data sources, wherein at least one of the plurality of disparate, heterogenous data sources includes a user generated data source; identifying a plurality of nodes and linkages; determining attributes of the nodes and linkages based on a plurality of disparate, heterogenous data sources, wherein the plurality of disparate, heterogenous data sources includes a combination of the user generated data source and at least one non-user generated source, wherein the attributes include at least one of a deterministic attribute, a probabilistic attribute, and a dynamic attribute; populating a mathemetical decision-making model based on the plurality of nodes and linkages, and the determined attributes of the plurality of nodes and linkages; determining attributes of the nodes and links at a second point in time; re-populating the mathematical decision-making model based on the plurality of nodes and linkages, and the determined attributes of the plurality of nodes and linkages at the second point in time.

The embodiment of the invention discloses a headline clickbait identification method and device, a server and a storage medium. The headline clickbait identification method comprises the steps of extracting text statistic characteristics and semantic characteristics of a headline, utilizing a pre-trained decision-making model, making the extracted text statistic characteristics and semantic characteristics serve as input of the decision-making model, outputting a decision-making score of the headline, comparing the decision-making score with a first preset threshold value, and determining whether or not the headline is a headline clickbait according to a comparison result. According to the headline clickbait identification method and device, the server and the storage medium, the text statistic characteristics and semantic characteristics of the headline are extracted in a multi-level, multi-granularity and multi-angle mode, the decision-making model is utilized to conduct decision-making scoring on the text statistic characteristics and semantic characteristics, and whether or not the headline is the headline clickbait is determined at last, so that the problems are solved that existing headline clickbait identification methods are large in error, poor in generalization capability and not high in identification accuracy, and the headline clickbait identification method and device have the advantages of being high in accuracy and recall rate.

The invention provides a human-face identifying method. The method is used for learning the similarity among human-face images on the basis of a one-class support vector machine and comprises the following steps of classifying human-face samples to obtain a training-sample set and a testing-sample set; classifying training samples in the training-sample set to obtain at least two classes, acquiring the training samples in each class to generate difference-sample pairs, and constructing a training-sample pair group; training the one-class support vector machine according to the training-sample pair group to obtain the decision-making model parameter of the one-class support vector machine and obtain a similarity discriminating model; carrying out similarity judgment by inputting testing difference samples generated by two testing samples which are randomly acquired in the testing-sample set into the similarity discriminating model. In the method, the data quantity input into the one-class support vector machine is reduced by classifying the training samples input into the one-class support vector machine according to the mode of generating training-sample differences in the homogeneous training samples, so that the calculating complexity is lowered.

The invention discloses a basin wind-light-water system multi-objective optimization scheduling method considering downstream ecology. The method comprises the steps of obtaining the basic informationof a cascade hydropower station; acquiring the basic information of the basin wind-solar power station; establishing a multi-objective power generation optimal scheduling mathematical model considering downstream ecology for a basin wind-light-water system objective and hard constraints according to the basin wind-light-hydropower station basic information; solving the established multi-objectivepower generation optimal scheduling mathematical model by adopting the improved AR-MOEA; and performing multi-attribute decision on the obtained non-dominated scheme by adopting SMAA-2. According tothe invention, the wind-solar-hydroelectric system is decoupled, so that the feasible solution is prevented from being damaged in the evolution process; a complete Pareto leading edge is obtained, a multi-attribute decision-making model of random multi-criterion acceptability analysis (SMAA)-2 capable of considering subjective willingness of a decision maker and uncertainty of attribute information is applied, more scheme sequencing information is provided for the decision maker, and the decision making can be conducted more scientifically and reasonably.

The invention provides an SOA-based comprehensive enterprise level information system operation and maintenance management method. The method comprises steps: modular system integration is carried out; functions of the system are packaged to services; an information index early warning threshold is made; system operation, service data integration, cleaning and relevance are carried out; acquired data are judged whether to exceed the early warning threshold; and early warning threshold is carried out. Heterogeneous information system integration is realized based on an SOA architecture, the effective integration problem of operation and maintenance work by the information system is solved, the operation and maintenance ability of the information system is enhanced fully, and lean resource configuration of the information system is realized via a comprehensive monitoring mode. With the help of the prior EBS service bus, the Web service, XML and other technical means, separation of business and service is realized, data cleaning and escape rules are made, the data format of the heterogeneous information system is unified, message interaction barriers are eliminated, and according to the pre-defined early warning information and the key index decision making model, system operation and business operation situations are analyzed, and decision making basis is provided for operation and maintenance management and business services.

The invention discloses a hilly crop irrigation system and method based on the Internet of things, and relates to the field of agricultural intelligent machinery. The hilly crop irrigation system comprises a crop soil moisture collection device, a meteorological information collection device, a wireless transmission module, an irrigation device and an irrigation decision-making model, wherein thecrop soil moisture collection device includes a soil moisture sensor and a data collector; the meteorological information collection device can collect meteorological information such as air, temperature, humidity and rainfall in real time; the wireless transmission module transmits the collected soil moisture information and meteorological information to an upper computer in real time; and the irrigation decision-making model in the upper computer calculates the current irrigation amount according to the information collected in real time and historical record information; and the irrigationdevice performs remote irrigation according to the calculated irrigation amount.

The embodiment of the invention discloses a Virtual Power Plant (VPP) scheduling optimization method based on demand side bidding and multi-energy complement. The VPP scheduling optimization method comprises the steps of predicting a load of a next day, estimating a response capacity and a cost, and participating in power market bidding according to predicted and estimated results; according to aload reservation or reduction plan obtained by bidding, releasing a load reduction moment and a to-be-reduced amount to the user; enabling the user to perform the demand side bidding based on an own loss load cost; and solving an optimized decision-making model based on a DSB and the multi-energy complement to obtain a load reduction amount of the user and an output increased amount of a CCHP, andsending a scheduling instruction to the user and the CCHP. According to the VPP interactive scheduling mechanism based on the demand side bidding and the multi-energy complement, a specific load reduction target is implemented by flexibly scheduling an FL and a multi-energy output, the comprehensive scheduling cost can be reduced obviously, and a multi-party win-win situation is implemented.

The invention relates to a crop precision irrigation decision-making method and system, and the method is characterized in that the method comprises the following steps: 1) enabling a field observation system to collect the real-time observation data of a to-be-measured crop at each monitoring point in an irrigation area in real time; 2) constructing an irrigation decision-making model based on the growth and yield prediction of the to-be-tested crops; 3) acquiring weather forecast information of the irrigation area and daily ordinal numbers of to-be-tested crops in the irrigation area in realtime; 4) determining a real-time irrigation decision-making result of the to-be-tested crop in the irrigation area according to the real-time observation data of the to-be-tested crop, the irrigationdecision-making model, the obtained weather forecast information and the obtained daily parameters in the growth period; 5) according to the remote sensing image of the irrigation area, obtaining spatial distribution data of the to-be-measured crops in the irrigation area and air relative humidity, surface temperature and vegetation coverage data of the irrigation area, and 6) determining a precision irrigation decision result of the to-be-measured crops in the irrigation area, and the method can be widely applied to the field of precision irrigation.

The invention provides an anti-fraud decision model construction method based on multi-dimensional data flow. The method comprises the following steps: S1, receiving a registration request of a user,and allocating function authority to the user; S2, configuring an anti-fraud decision model in a user-defined mode, and the anti-fraud decision model comprising a rule set, a scoring model and associations between the rule set and the rule set, between the rule set and the scoring model and between the scoring model and the scoring model; and S3, storing the configured anti-fraud decision model asa template into a decision model template market, and supporting editing and storage of a decision set in the anti-fraud decision model. According to the method, services such as anti-fraud identification, preposed risk control prevention, accurate risk identification and professional information verification are provided for a business system, a user can construct a decision model based on a self-owned rule set or a scoring model, safe operation of self-owned businesses is ensured, and meanwhile, the influence of false information on subsequent loan businesses and the loss caused by fraud requests are reduced.

The invention discloses a distribution network analysis and investment decision method based on association rule mining. The method comprises the following steps: collecting historical operation dataof a distribution network, carrying out data preprocessing, filling or eliminating bad data / missing data conditions, and carrying out data normalization processing according to index analysis requirements; carrying out dimension reduction through principal component analysis, and carrying out clustering analysis on all indexes through K-means clustering; for different principal components, mininga frequent item set and a strong / weak association rule through a data association rule, and determining a strong association index influencing each principal component; meanwhile, establishing a distribution network operation evaluation model, and searching for weak points of the distribution network according to the comprehensive scores and the scores of all levels; establishing an investment return rate model according to the index annual change rate and the annual investment amount, and mining indexes of investment sensitivity; and finally, establishing an investment quantitative decision-making model by integrating the operation status of the distribution network, the principal component strong correlation indexes and the investment return rate model, and performing quantitative investment decision-making analysis.

The invention discloses a comprehensive multi-dimension goods owner selection quantification method enabling a member to evaluate a goods owner objectively and comprehensively from multiple dimensions in a quantitative mode. According to the method, multiple measure indexes affecting selection including loading and unloading punctuality, the number of times of carriage, the number of times of complaints from platform members, goods payment and information issuing timeliness ratio, and one-time offer close deal rate are fully considered, the weight of each index is determined quantitatively based on the index weight division method of a multi-attribute decision-making model combining the least square method and the ELECTRE-II method, reasonable evaluation of the credibility of a goods owner on an e-commerce platform with logistics service as transaction object is well achieved through precise big data mining and analyzing and model algorithms, and platform members can judge the comprehensive condition of a goods owner and make choices meeting their own needs.

The invention is suitable for the field of security check, and provides a passenger attention degree ranking method and device. The method comprises the steps: collecting the current navigation information of a passenger; Building a classification decision-making model through employing the historical navigation information of the passenger and other passengers; pre-judging the attention degree of the passing of the passenger through the security check through employing the classification decision-making model and the current navigation information. The beneficial effects of the invention lie in that the method enables the current security check to be more reliable and brings convenience to a security check worker to make a safety decision; and the method enables the security check to be more efficient, and facilitates the reduction of security check time.

The invention discloses an airport pavement crack detection method based on infrared and visible light image data fusion. The method comprises the following steps: registering an infrared image and a visible light image; calculating the contrast ratio of the infrared image and the visible light image after registration to obtain respective initial crack pixel points; establishing a fusion decision-making model based on local gray scale and temperature probability distribution, and verifying an initial crack communication area formed by adjacent initial crack pixel points by using the model to obtain a candidate crack area; fusing the candidate crack regions in the visible light image and the infrared image to generate a fused candidate crack region; and screening the fusion candidate crack area to obtain a final real crack area detection result. The method has the advantages that complementarity of infrared and visible light sensor detection technologies is well utilized, the problem that crack detection is limited by means of a single sensor is solved, the sensitivity to illumination in the crack detection process is reduced, the robustness to environmental noise is enhanced, and the detection accuracy is improved.

The invention discloses a road and bridge disease analysis and maintenance decision-making method based on big data, which can discover potential, implicit and unknown rules in complex construction, operation, detection, overhaul and maintenance data and scientifically and objectively determine disease causes. Various influence factors such as PCI / BCI, daily maintenance level and traffic volume are introduced into the maintenance management decision model; structured and unstructured data generated in road and bridge design, construction, operation and maintenance processes are fused through abig data analysis method; a big data association analysis method is adopted to establish an association model between the road and bridge disease grades and multiple factors; therefore, a PCI and opportunity cost optimal decision-making model under fund constraint and personnel constraint conditions is established; the effectiveness of the model is verified through field inspection and professional detection data, key factors influencing the health conditions of roads and bridges are determined, a final prediction result is obtained, then a road and bridge maintenance decision scheme is intelligently recommended, and a foundation is laid for road and bridge maintenance decision.

The invention discloses a micro-grid active operation decision-making method based on sensitivity analysis. The method comprises the following steps: using a situation awareness technology to collect,understand and predict various types of information elements related to distribution network power quality change, and mastering a power quality change situation; and on the basis of predicting the future change trend of the power quality, establishing an active operation decision-making model of converter situation awareness and power flow calculation through an information interaction architecture between micro-grid converters. Based on the obtained active operation decision-making model, an advanced converter control strategy is proposed, the optimal operation mode decision of a distribution network is achieved, more effective means are provided for solving power grid power quality control, so that the safety management of the power grid is changed from passive to active, and safe andreliable operation of the distribution network is guaranteed.

The invention discloses an equipment fault diagnosis method and device based on cloud service, and the method comprises the steps: S1, obtaining a fault diagnosis symptom vector which comprises the operation data of equipment of an automatic verification system in real time based on a cloud storage technology; S2, obtaining a fault vector through fuzzy reasoning operation according to the obtainedfault diagnosis symptom vector; and S3, inputting the fault vector into the trained ELM secondary fault diagnosis model for secondary fault diagnosis to obtain a fault type diagnosis result. The datamanagement performance based on the cloud service is combined with the two-stage fault diagnosis decision-making model composed of fuzzy reasoning and ELM, and the technical problem that the equipment fault diagnosis accuracy of a traditional automatic verification center based on the cloud service is low in complex automatic metering detection system environments of multiple sources, multiple dimensions, heterogeneity and the like is solved.

The invention discloses a method for determining risk assessment parameters. The method comprises the steps that assessment information with the risk assessment parameters to be determined of a user is acquired; the assessment information of the user is subjected to variable sorting to obtain a first-type variable value and a second-type variable value; and the risk assessment parameters of the assessment information of the user are determined according to the first-type variable value, the second-type variable value and a decision-making model with an assessment information decision-making function, wherein the first-type variable value is obtained after fraud information is eliminated from the assessment information, and the second-type variable value is determined according to whether a fraud decision-making condition is met. Through the method for determining the risk assessment parameters in the embodiment, the accuracy of the risk assessment parameters can be improved.

The invention relates to a power grid usable power transmission capability risk benefit decision-making method based on power flow entropy. The method includes: (1), acquiring running parameters of each element of a power grid; (2), performing uncertain sampling on running state of the power grid; (3), calculating power flow entropy and usable power transmission capability of the power grid in a system state after sampling; (4), judging whether sampling termination condition is reached or not; (5), building a usable power transmission capability risk benefit model; (6), combining the power flow entropy to generate a usable power transmission capability decision-making mode, and determining an optimal release value according to the model. A decision-making model combining power flow entropy of the power grid and the usable power transmission capability risk benefit model is built for the first time and comprehensively takes power grid system running state and risk benefit into consideration, decision making is performed on usable power transmission capability release value from a safety technology level and a market economy level, the release value is enabled to be more fitted with running actual condition of the power grid, and economic benefit is improved effectively.

The invention discloses a decision-making method for an airport taxi passenger carrying problem. The method comprises the following steps: firstly, carrying out parameter calibration on an airport flight number, a passenger arrival number, a taxi number, waiting time and driver earnings; then establishing a revenue maximization model, comparing the waiting net revenue and the return net revenue ofthe taxi driver, selecting a decision with the maximum net revenue, if the number of batch times that the taxi can be released is greater than the number of batch times required for carrying all passengers, indicating that the taxi is more and fewer, the passengers cannot be pulled out, and absolutely selecting direct empty taxi return at the moment; otherwise, indicating that the taxi driver canreceive the passenger, and comparing the waiting net income and the returning net income to decide whether to return directly or not; finally, establishing a rational decision model. By comparing thewaiting net income with the returned net income E = E2-C, a decision-making method is provided for airport drivers, and the drivers are enabled to select an airport passenger-carrying decision-makingscheme with the maximum net income.

The invention discloses a clary sage oil stability evaluating method based on a two-dimensional correlation spectrum. According to the clary sage oil stability evaluating method, on the basis of the thermal disturbance two-dimensional correlation Raman spectrum, corresponding dynamic spectra of a sample in a thermal perturbation action state are recorded for correlation analysis, and thus two-dimensional wavelet transformation is introduced to conduct high-dimensional multi-scale decomposition and hierarchical reconstruction on the correlation spectra; submodels of each layer of reconstructedcorrelation spectrum are conducted through parallel factor analysis; and finally, all the submodels are fused into a unique unified decision-making model through a method of weighting so as to finallyrealize judgment of quality stability of clary sage oil. Compared with conventional Raman spectrum analysis, through the clary sage oil stability evaluating method, the resolution accuracy and sensitivity of a conventional Raman spectrum analysis model can be significantly improved, thus a rapid evaluation method for stability of tobacco essence raw materials is constructed, stability quality control over the tobacco essence raw materials can be achieved step by step, and the quality control over the tobacco essence raw materials is greatly promoted.

The invention belongs to information technology field, especially relating to a city spatial information sharing platform comprising public information communication network, spatial information exchange network, public spatial information resource and integrative spatial database, spatial information standard criterion module, spatial information management regulation, institution and user system module. The public spatial information resource is system core; multi-level network management structure and institution and user system module exchanges data with the public spatial information resource; the public information communication network comprises: spatial metadata management system, spatial information sharing platform service system, spatial decision-making model service sharing system, spatial information browsing and inquiry service system, spatial data conversion system, spatial data compression and network transmission system, spatial data acquiring system. The spatial information sharing platform is highly automated and widely used.

The invention provides an access satellite determining method and device. The method comprises the steps of on the basis of history energy state parameters of to-be-accessed satellites, determining an energy state parameter of each to-be-accessed satellite in a current time slot; determining a state transfer parameter of user equipment accessing each to-be-accessed satellite in the current time slot; determining state transfer distribution condition of a satellite system composed of the to-be-accessed satellites according to the energy state parameters of the to-be-accessed satellites and the state transfer parameters of the user equipment; and establishing a decision-making model according to the state transfer distribution condition, and determining a target access satellite for accessing the current user equipment in the to-be-accessed satellites according to the decision-making model. According to the target access satellite determined through the method, the network capacity of a satellite system is optimized, and the energy of the satellite system is also optimized. The energy consumption of the determined target access satellite is low; the service life of the satellite system is prolonged; and the technical problem that the satellite system determined through an existing satellite access strategy is relatively high in energy consumption and short in service life is mitigated.

The invention relates to a method of recognizing a 2D image and a 3D image. The method comprises the following steps: (1) multiple 2D images and multiple 3D images serve as a sample image set; (2) each image in the sample image set is divided into a left half image sample and a right half image sample with the same size, and color autocorrelogram features of the left half image sample and the right half image sample are extracted respectively; (3) the difference C1 between the color autocorrelogram features of the left half image sample and the right half image sample and a correlation coefficient C2 between the left half image sample and the right half image sample are calculated, and the C1 and the C2 serve as evaluation indexes; (4) the C1 and the C2 are integrated, a decision-making model is built, and the optimal classification boundary is obtained; and (5) through extracting the color autocorrelogram features and the correlation coefficient features of the left half image and the right half image of the to-be-recognized image, the to-be-recognized image is classified and marked based on the optimal classification boundary.

The invention provides a decision making method and apparatus based on survey data, a storage medium and a terminal device. The method comprises the following steps: obtaining survey data, wherein thesurvey data comprise a continuous value feature, a category feature and text information for describing a survey process; extracting a semantic representation feature from the text information; combining the continuous value feature with the category feature to obtain a width model input feature; performing generalization processing on the preprocessed continuous value feature and the category feature to obtain a depth model input feature; and inputting the semantic representation feature, the width model input feature and the depth model input feature in a decision making model to obtain a decision making result of the survey data. By adoption of the decision making method and apparatus provided by the invention, the decision can be made by combining the semantic features of the text inthe survey data, which is beneficial to improving the accuracy of the decision making.