43results about How to "Good decision support" patented technology

The invention provides a health management system and method for a complex system having at least one information source with data sources, an Aircraft Condition Analysis and Management system (ACAMS) for monitoring the data sources, an information controller for collecting and processing the data sources and a diagnostic/prognostic reasoner for fusing the collected data sources to establish current and future states and conditions of the complex system.

The invention provides a method for bus origin-destination (OD) investigation by using mobile phone base station data and operating vehicle global position system (GPS) data, comprising the following steps: 1) collecting mobile phone positioning data and bus GPS data; 2) transferring the mobile phone positioning data into travel information of users; 3) extracting characteristic values from the travel information of the users; 4) analyzing the extracted characteristic values to obtain basic travel characteristics; 5) matching bus travel information with the bus GPS data to obtain bus travel characteristics; and 6) carrying out statistical process on the obtained travel characteristics, and then outputting a population travel characteristic report form. The method is based on the mobile phone positioning data and the bus GPS data and then is used for performing a series of processes on the mobile phone positioning data and the bus GPS data, thereby automatically obtaining a high-quality, high-fineness and large time-span population travel characteristic reform form from a great amount of data, intelligently acquiring the population travel characteristics, reducing manpower and material resource consumption and improving the accuracy and effectiveness of the investigation.

The invention provides a construction method and device of a dynamic medical knowledge base. The method comprises the following steps: obtaining the personal information and the sign data of a patient; obtaining an intervention guidance opinion given by a doctor according to the personal information and the sign data of the patient; generating the personal information and the sign data of the patient and the corresponding intervention guidance opinion of the doctor into rule knowledge according to a terminological dictionary and a pattern base of the medical field; and according to the obtained rule knowledge, updating the medical knowledge base. The scheme of the invention carries out association analysis on structured information-quantization sign data and unstructured information- the intervention guidance opinion of the doctor, establishes the medical knowledge base which can be dynamically updated, and improves the mining dimensionality of user data, and generated knowledge can provide decision support for an expert system to carry out personalized data analysis.

The invention discloses a source-load-storage coordinated scheduling method for improving new energy consumption. The method comprises the steps of S1, aggregating a thermal power plant, a new energypower plant, user loads and energy storage equipment into a source-load-storage scheduling system, and obtaining a new energy output curve, a heat utilization load curve and a power utilization load curve of the system; S2, establishing a source-load-storage coordinated scheduling model with the objective of maximizing new energy consumption quantity and minimizing the system operation cost; and S3, solving the source-load-storage coordinated scheduling model through utilization of improved multi-objective particle swarm optimization, and carrying out computing to obtain the source-load-storage coordinated scheduling method. The method has the advantages of simple realization method and flexible application. Schedulable resources such as power equipment, the user loads and the energy storage equipment in the system can be utilized rationally. The new energy consumption is facilitated, and moreover, operation cost of the system is reduced.

The invention provides a unit commitment (UC) optimization method based on two-phase firefly encoding. The method comprises the steps of first determining a UC model; then carrying out mutation and self-adaptive improvement for a standard firefly search mechanism; next, carrying out discretization of fireflies to solve a UC start and stop problem; further, solving a load optimal distribution sub-problem by real number encoding of the fireflies; solving the two problems alternatively; and finally obtaining a complete solution of the UC. The invention can improve the solving speed and global optimization capability of the UC, and provide better decision support for electric power system dispatchers.

The invention discloses a complex line full parallel AT traction power supply system and method based on comprehensive energy. The system comprises a complex line full parallel AT traction power supply system and a comprehensive energy system; a photovoltaic array, a wind generating set and a fuel cell are connected in parallel to a direct current bus, electric-hydrogen storage is added to supplement power vacancy and peak load shaving, comprehensive energy is accessed into a traction power supply system through a reasonable mode, the power and the state of each microsource are detected in real time, the energy optimization management by taking the lowest total generation cost as a target is achieved based on a particle swarm optimization. The complex line full parallel AT traction powersupply system and method based on comprehensive energy can ensure the safety and stability of the system and the high reliability of power supply; the traction energy consumption structure is optimized, and the new energy consumption level is improved; and the method meets the development direction of national energy conservation and emission reduction, and reduces the power supply requirement ofthe electrified railway on the power system to a certain extent.

The invention discloses an information processing method based on a geographic topic model. The information processing method includes following steps: S1, extracting text data and geographic position information to which the text data belong to form to-be-processed text data, and storing the to-be-processed text data into a database; S2, preprocessing the to-be-processed text data in the database to generate processed data; S3, building the geographic topic model according to the processed data, and solving the geographic topic model to acquire a correlation between topics and geographic positions. In the method, semantic information in a text and the geographic position information are correlated for mining analysis of the topics to correlate the topics in the text with the geographic positions, so that the geographic positions of topic research can be found accurately to acquire main subject study directions of each region, and a better decision-making support can be provided for users.

The invention discloses a meteorological calamity prediction method based on a multivariate linear regression algorithm. The method comprises: first of all, according to historical data, determining major meteorological calamities of an area to be predicted in a specific period, and then respectively establishing a mapping relation equation between the various major meteorological calamities and meteorological factors; and finally, introducing meteorological factor parameter values in the mapping relation equation between the various major meteorological calamities and meteorological factors to obtain a value of probability that the corresponding meteorological calamities take place. According to the invention, the multivariate linear regression algorithm is applied to a meteorological calamity prediction technology, the mapping relation equation between the major meteorological calamities and meteorological factors is established, what is needed is only to collect the meteorological factor parameter values, and requirements for sample data are not high. The method provided by the invention can be applied to various environments, different mapping relation equation coefficients can be obtained according to different meteorological factor values of each place, and the adaptability is high; and the calculation process provided by the method of the invention is relatively simple and does not require repeated debugging, thus the application value is wide.

The invention discloses a source-load-storage scheduling method based on an improved multi-objective particle swarm optimization algorithm. The method comprises the steps of: S1, integrating a thermalpower plant, a clean energy power plant, a user load and an energy storage device into a source-load-storage scheduling system, and determining the scheduling optimization objective function and theconstraint condition of the source-load-storage scheduling system to achieve the minimum system operating cost and the highest clean energy consumption; S2, using the scheduling optimization objectivefunction as the fitness function of the improved multi-objective particle swarm optimization algorithm, and using the constraint condition as a particle variable constraint section of the algorithm;and S3, by using the improved multi-objective particle swarm optimization algorithm, obtaining a minimum value of the fitness function and a particle variable that takes the minimum value of the fitness function according to the fitness function and the particle variable constraint section. The method is easy to implement and flexible to use, can improve the solution efficiency of a power scheduling scheme, and can obtain a reasonable power scheduling scheme with good economic benefit.

The invention discloses a heat power plant heating network monitoring system, which comprises a field device layer, a centralized monitoring later, an information management layer and a network for connecting the layers. The heat power plant heating network monitoring system has the beneficial effects that integration of management and control for the heating network is realized. energy managementand control for the heating system are combined, centralized and dynamic balance control on the heating network is realized, hydraulic balance and thermodynamic balance for a primary network can be effectively solved, and optimal control and decision support for energy conservation and consumption reduction can be realized.

The invention discloses a method and a device for diagnosing faults of rail locomotive network control systems. The method includes building fault state identification models on the basis of Bayesiannetworks and Markov transition matrixes; acquiring MVB (multifunctional vehicle bus) data packet on MVB in real time, acquiring occurrence frequencies corresponding to fault feature points in currentmonitoring standard calibration time delta t and acquiring fault feature occurrence probability and mapping probability of the fault feature points on the basis of the occurrence frequencies; computing prior probability of fault nodes, which correspond to fault features, in four fault states by the aid of prior probability transition models and ultimately computing posterior probability of the fault nodes, which correspond to the fault features, in the four fault states on the basis of prior probability and mapping probability parameters by the aid of probability conversation formulas. The fact that the fault states corresponding to the highest posterior probability are current states of the fault nodes is the highest in reliability.

The invention discloses a short-term scheduling rule extraction method based on a variable structure deep learning framework. The method comprises the following steps: step 1, constructing a deep learning network; 2, selecting an input factor decision variable sample pair; 3, normalizing the sample data in the step 2; step 4, selecting and optimizing key hyper-parameters; step 5, and carrying outnetwork reconstruction; and step 6, network training, wherein the reconstructed network obtained in the step 5 is utilized to input the sample obtained in the step 3 for network learning, a final deeplearning network is obtained, and the network is the extracted short-term scheduling rule. Based on actual historical operation data of a power station, a deep learning network model based on a long-short-term memory network is constructed, internal rules contained in an actual operation process are mined, a power station short-term scheduling rule is established, and initial and end water levelsof a power station scheduling period, a period water incoming process and a power station power receiving network load process are used as input factors. The end water level of the power station period serves as a decision variable, and the model output result is more suitable for the actual scheduling process.

The invention discloses a distributed BIM collaborative platform, which comprises a platform host, and an architectural design team node, a structural design team node, an electromechanical pipeline design team node, a construction team node, a construction team node and a survey team node connected with the platform host, wherein each team node is connected with a plurality of work nodes. The platform host is used for integrating, processing and storing all models, data and information of the project. Upon completion of integration, the latest data, information and model are updated to all team nodes, and an interface is provided for external users. The team node includes a model integration module, a collision detection module and a bandwidth monitoring module, and each work node includes a design module. The platform realizes the high sharing of project model and information, simplifies the collaborative process, ensures the integrity and security of data, improves the efficiency and reduces the cost.

The invention discloses a stochastic optimization control method and system for the inside of a virtual power plant participating in gas power market. The method comprises the steps that S1 an electric-heating-gas model of the virtual power plant is constructed, and a target benefit function of the electric-heating-gas model is determined; S2 a discretization solution model of a super-quantile isconstructed according to the target benefit function; and S3 the discretization solution model is used as a fitness function to construct an intelligent algorithm model, and a pre-built control schemeis used as the initial input of the intelligent algorithm model to calculate and determine an optimal control scheme under a preset operation scenario. The method has the advantages of strong representativeness, good accuracy and the like.

The invention discloses a river and lake ecological health intelligent diagnosis method, which comprises the following steps: constructing a diagnosis index set, and determining the specific type and number of ecological health diagnosis indexes; calculating ecological health diagnosis indexes; carrying out ecological health diagnosis index scoring; determining a weight by using an analytic hierarchy process in combination with a Telffie method; and carrying out ecological health diagnosis by adopting a grading index scoring method, step-by-step weighting and comprehensive scoring. According to the invention, the river and lake ecological health diagnosis model is constructed through an analytic hierarchy process and an index system method, and meanwhile, the river and lake ecological health intelligent diagnosis model is combined with a geographic information system, so that the visualization of data storage, updating, analysis, evaluation results and pathogenic factors is achieved, and the most convenient decision support is provided for river management.

The invention relates to a comprehensive decision making method for a heat supply project. The method comprises the following steps of establishing a multi-dimensional index system including economic indexes, environmental indexes, risk indexes and flexibility indexes; calculating the economic indexes, environmental indexes, risk indexes and comfort indexes of the heat supply project; applying an expert grading method to determine the index weight of each dimension; and calculating the comprehensive index of each candidate heat supply scheme, sorting the candidate schemes according to the comprehensive index of each candidate heat supply scheme, and selecting the heat supply scheme with the smallest heat supply index as the decision-making scheme. The method is reasonable in design, and proposes a multi-dimensional index system and a comprehensive index calculation and decision-making method. The heat supply scheme is evaluated by the multi-dimensional index system including the economic indexes, environmental indexes, risk indexes and comfort indexes so as to provide optimal decision making support, thereby guiding the rational planning of heat supply projects.

The invention discloses a stock prediction method based on positive and negative correlation trend matching. The main idea of ​​the method is to search for a strong correlation trend that is positively or negatively correlated with the historical data of all stocks to predict the trend of the stock in the near future, and based on the trend after the matching date of the relevant trend, positive or negative Restore the later trend of the stock to be predicted as its prediction result. The method predicts the possible trend of each stock in the next week or two. The forecast results include not only the daily closing price, rise and fall, but also the daily opening price, highest price, and lowest price. The final result of the method also provides a comparison chart of the positive and negative most relevant stocks and the original stocks to be predicted. The basically similar or opposite stock trends provide good decision support for short-term stock operations.

The invention provides a tumor treatment auxiliary decision-making method based on reinforcement learning, and the method comprises the steps: constructing and training a patient state transition model and a treatment decision-making model, wherein the patient state transition model carries out the modeling of the state change of a tumor patient through a recurrent neural network, using a diagnosis and treatment scheme and examination indexes obtained in actual diagnosis and treatment as data sources, and simulating the state change of the tumor patient under a certain diagnosis and treatment scheme. The treatment decision model carrying out modeling on the process of treating a tumor patient through reinforcement learning, the patient state transfer model is used as a data source, a deep Q network (DQN) is constructed to serve as a strategy network, an excitation function is constructed on the basis of RECIST solid tumor curative effect evaluation standards and TNM tumor imageological staging standards, and iterative training is carried out. According to the method, the workload of tumor specialists can be reduced to a certain extent, the treatment means predicted by the model can serve as decision reference to reduce decision errors of doctors, and the doctors are assisted to specify feasible treatment schemes.

The invention discloses a library big data analysis and decision support platform based on cloud computing. The library big data analysis and decision support platform is characterized by comprising acloud computing data processing system, a reader information acquisition system, a book evaluation system, a reader behavior portrait system and a library decision support system. The reader information acquisition system uploads acquired reader data to the cloud computing data processing system for data analysis. The book review system uploads collected book review data to the cloud computing big data platform, and uploads the reader behavior fitting data preprocessed by the reader behavior portrait system to a cloud computing big data platform. The library decision support system receives reader data information distributed by the cloud computing big data platform. The cloud computing data processing system is used for collecting book review data in a larger range, so that the book review data can be perfected. The decision support can be provided for library collection construction of a library.

The invention discloses a multi-scene multi-commodity chain convenience store site selection optimization method in a competitive environment, and the method comprises the following steps: determiningthe constraint of a chain convenience store site selection problem for the consideration of the travel cost of enterprise commodity distribution and vehicle dispatching; describing a store site selection process of the consumer by using a random utility theory, and determining influence factors and specific parameters influencing decision making of the consumer; establishing a multi-commodity chain convenience store site selection model under the constraint of the store number, and maximizing the store area popularity of a convenience store enterprise; considering the influence of the consumer characteristic difference on the convenience store site selection strategy, and establishing a multi-commodity chain convenience store site selection model based on user portrait subdivision in twotypical scenes; designing a linearization conversion method of a target function, and converting the nonlinear site selection model into a mixed integer programming model; searching basic parameters of a to-be-selected site, a competitive storefront position, consumer demands and other site selection problems; and performing calculating to obtain the optimal site selection point and the corresponding store area popularity in various scenes.

The invention discloses an annual verification management method for employment of the disabled, which comprises the steps of (1) inputting annual verification information of employment of the disabled; (2) checking the annual verification information of employment of the disabled; (3) processing the annual verification information of employment of the disabled; and (4) paying employment securityfunds for the disabled by enterprises or the social workers. The annular verification management method simplifies the workflow of annual verification for the employment security funds for the disabled, improves the accuracy of the annual verification work for the employment security funds for the disabled, facilitates annual verification data overall planning, further improves the efficiency andquality of annual verification and funds collection of the employment security funds for the disabled, and effectively reduces the management cost and the service operation cost of annual verificationfor the employment of the disabled.

The invention discloses a construction risk prevention and control method and a construction risk prevention and control system for a shield tunneling machine. The method comprises data acquisition and transmission, big date storage, processing and analyzing, risk recognition and early warning. The data mainly comprises machine data, fault data, guide data, ground settling data, duct piece gesturedata and engineering data. The big data storage and analysis and processing comprise a server and big data technology related software. The risk recognition and early warning comprise steps of engineering construction risk prevention and control, machine fault risk early warning, heading parameter early warning, quality risk prevention and control, construction period risk prevention and controland the like. The construction risk prevention and control method and the construction risk prevention and control system for the shield tunneling machine based on big data analysis can establish an informationized risk prevention and control system and avoid or reduce loss to a project due to risks such as equipment faults, staff operation errors and the like effectively, so that safe and efficient construction of the shield tunneling machine is guaranteed.