62 results about "Dynamic programming model" patented technology

The invention provides an inventory optimization method and system based on a deep learning model, and relates to the technical field of deep learning, and the method comprises the steps: obtaining the multi-dimensional data of a commodity, constructing a dynamic convolution kernel through employing a graph neural network, constructing a soft clustering distribution matrix in combination with a multi-layer perceptron, and obtaining a long-term dependence feature fusing a space dimension and a time dimension. And fusing the short-term and long-term features, inputting the fused short-term and long-term features into a bidirectional long-short-term memory network to generate a sales prediction sequence, and calculating a prediction confidence interval to obtain a final sales prediction result. And calculating a safe inventory level based on a sales prediction result, generating a replenishment decision by using a dynamic planning model based on deep reinforcement learning in combination with an inventory cost function, and finally sending the decision to a supply chain execution system. The sales volume is accurately predicted through the deep learning model, the inventory management is optimized, the storage cost, the stockout cost and the overstock cost are reduced, and the supply chain efficiency is effectively improved.

The invention relates to the technical field of wind turbine generator data analysis, and discloses an offshore wind turbine generator operation data analysis and prediction system. The system comprises a marine environment data integration module for collecting data to generate a multi-source time-space synchronization data set; the multi-modal feature fusion module is used for extracting cross-modal correlation features to generate a high-dimensional fusion feature tensor; the dynamic fault prediction module is used for constructing a two-way gating circulation network model to predict the degradation probability and the residual life of key components of the equipment; and the self-adaptive optimization control module is used for constructing a multi-target dynamic programming model to optimize a fan operation strategy. In addition, the system is further provided with a feedback correction module for correcting prediction model parameters, and a virtual sensor module based on a physical information neural network is used for monitoring tower stress and diagnosing sensor faults. According to the system, comprehensive monitoring, accurate fault prediction and optimal control of the offshore wind turbine generator are realized, the operation efficiency, reliability and safety of the wind turbine generator are effectively improved, and the operation and maintenance cost is reduced.

The invention provides a new energy output prediction method and system based on Monte Carlo Dropout, and the method comprises the steps: carrying out the probabilistic prediction of new energy output through a Monte Carlo Dropout technology, generating a dynamic prediction result containing a confidence interval, and quantifying the uncertainty of meteorological sudden change and equipment state; secondly, constructing a multi-stage random dynamic programming model, discretizing a prediction interval into multi-scene input, designing a non-linear objective function based on the discharge depth, and synchronously optimizing the electricity purchase cost and the energy storage aging cost; and finally, realizing rolling optimization of the system in combination with a model prediction control framework, and dynamically adjusting an energy storage aging cost weight by updating prediction data and a scheduling instruction on line and embedding an energy storage health state real-time feedback mechanism. The photovoltaic and wind power consumption rate can be remarkably improved, the full life cycle cost of an energy storage system is reduced, and meanwhile, the robustness of a scheduling strategy in extreme weather is ensured.

The invention provides a fuel cell vehicle energy-heat cooperative control method considering thermal characteristics of a power system, and solves the problem that energy and heat management at low temperature is difficult to collaboratively optimize. According to the method, an energy-heat collaborative global dynamic planning model is established through a long-time-domain average vehicle speed, and the optimal reference trajectory of the SOC and the fuel cell temperature is solved off line by integrating the preheating energy consumption of a power cell and the temperature coupling effect of the fuel cell. And in a short time domain, an LSSVM and BPNN fusion algorithm is adopted to predict the vehicle speed, real-time rolling optimization is performed on the SOC and the fuel cell temperature in combination with a nonlinear MPC strategy, and a global optimal track is tracked. According to the method, on the premise of meeting the temperature requirements of the cabin and the battery, the lowest hydrogen consumption of the whole vehicle and the optimal power system efficiency are achieved, and the energy utilization rate and the cruising ability under the severe cold working condition are improved.

The invention discloses a power conversion cabinet scheduling method and system based on a dynamic programming model and a storage medium, and the method comprises the steps: collecting a user power conversion track, power conversion cabinet state data and user power conversion behavior data, and carrying out the preprocessing; according to the preprocessed data, calculating a correlation effect among all the power conversion cabinets, combining the correlation effect with the geographic positions of the power conversion cabinets, and performing clustering analysis by adopting a spatial clustering algorithm to obtain a clustering result; constructing a dynamic planning model based on the preprocessed data and the clustering result, and solving the dynamic planning model to obtain a power conversion cabinet area layout scheme with the maximum income; planning an optimal cabinet moving strategy for moving the power conversion cabinet from the original position to the latest position according to the scheme of the power conversion cabinet area layout, and executing the operation of moving the power conversion cabinet; and when the set time limit is reached, continuing to execute intelligent dispatching of the battery changing cabinet. The battery replacement time of the user is shortened, the overall service level is improved, and more efficient and convenient battery replacement experience is provided for the user.

The invention relates to the technical field of cloud computing, and discloses a data processing method and system based on cloud computing, and the method comprises the steps: dividing a cloud computing system into a data storage unit, a computing resource scheduling unit and a task distribution unit, determining the parameters of each unit, carrying out the modeling, constructing a distributed mathematical simulation model, and solving to obtain an initial simulation result. By establishing a dynamic programming model and a genetic algorithm model, computing resource scheduling and task allocation are optimized respectively, and a data redundancy strategy and a fragmentation rule are determined at the same time. The minimum system total energy consumption, the minimum task average time delay or the maximum resource utilization rate serves as a global optimization objective function, and the convergence condition is judged to optimize system configuration. According to the method, the data storage reliability, resource scheduling reasonability and task allocation efficiency of the cloud computing system are effectively improved, global optimization of the system is realized, and the method has a good application prospect.

A time-series production simulation method taking capacity dynamic programming into consideration, and an apparatus and a medium, relating to the technical field of power systems. The method comprises: establishing a single-year time-series production simulation model; on the basis of the single-year time-series production simulation model and a CNN-GRU network, constructing an equivalent load support rate interval decision network; on the basis of the single-year time-series production simulation model, constructing a multi-stage dynamic programming model oriented to the problem of power capacity expansion; using a NO search algorithm to compress a state space in the multi-stage dynamic programming model, so as to obtain a compressed state space for the problem of dynamic programming; and in the compressed state space, using an APO optimization algorithm and a DCS algorithm to construct a time-series production simulation method solution framework taking capacity dynamic programming into consideration, and using the time-series production simulation method solution framework to determine a fast time-series production simulation result taking capacity dynamic programming into consideration.

The invention belongs to the technical field of photovoltaic power stations, and particularly relates to an energy scheduling and peak-valley arbitrage collaborative optimization method and system for a photovoltaic power station, and the method employs a two-stage optimization architecture: in a day-ahead planning stage, building a distributed robust optimization model based on prediction data, and generating a reference scheduling plan; in the real-time scheduling stage, different control instructions are generated by calculating the photovoltaic output deviation ratio and the income deviation value and combining the state of the storage battery. And when the system is in a power shortage state, switching to a power supply reliability guaranteeing mode, otherwise, executing a peak-valley arbitrage strategy through the random dynamic programming model. According to the method, the deviation between the expected income and the actual income is compared in real time, the photovoltaic output fluctuation and the battery state are combined to switch the operation mode, and the dynamic balance path breaks through the limitation that a traditional scheduling scheme is too conservative or too dangerous, so that the system can cope with uncertainty and keep the optimal economical efficiency at the same time.

The invention discloses a stable and suitable coordination method for watershed mountain water, forest field, lake grass and sand, and relates to the technical field of ecological environment protection and governance, and the method comprises the following steps: 1, collecting watershed ecological background data, and constructing an ecological hydrological database; 2, constructing a landscape pattern-ecological system coupling model according to the ecological hydrological database, and carrying out ecological function partitioning; 3, constructing a comprehensive coupling relation framework in the drainage basin according to the ecological function partition, and identifying a key ecological hydrological problem; 4, constructing a nonlinear-multi-target dynamic planning model according to the key ecological hydrological problem; 5, solving the nonlinear-multi-target dynamic programming model to obtain a parameter optimal solution; and 6, constructing a coordination strategy according to the optimal solution of the parameters. The method comprises the following steps: establishing a drainage basin ecosystem collaborative regulation model by taking collaborative optimization of a drainage basin ecological hydrological function as a core target, determining optimal parameters by optimizing the model, and formulating a coordination strategy.

The invention provides a server parameter optimization method and device, and the method comprises the steps: obtaining a state parameter set and an execution action set of a server cluster, and the state parameter set and the execution action set are provided with time labels; based on the state parameter set and the execution action set, a multi-agent reinforcement learning algorithm is utilized to determine local evaluation prediction parameters; based on the state parameter set and the execution action set, global evaluation prediction parameters are determined by using an adaptive dynamic programming model; and optimizing the execution action set based on the local evaluation prediction parameters and the global evaluation prediction parameters. According to the method disclosed by the invention, the local evaluation prediction parameters and the global evaluation prediction parameters corresponding to the server cluster are determined by using the QMIX model and the ADP model, so that automatic optimization of the execution action set of the server cluster is realized, and the stability and the service efficiency of the server cluster are improved.

The invention belongs to the technical field of information processing, and discloses a file approval method and a related device, and the method comprises the steps: receiving a to-be-approved file submitted by an applicant, and extracting the preset file attribute information of the to-be-approved file; encrypting the to-be-approved file to obtain an encrypted to-be-approved file; generating an optimal approval path based on the approval path dynamic planning model in combination with preset file attribute information of the to-be-approved file; the approval path dynamic planning model is a pre-trained reinforcement learning model; transferring the encrypted to-be-approved file according to the optimal approval path, and distributing the to-be-approved file to the approval personnel of each approval level in the optimal approval path for approval until the approval personnel of all approval levels in the optimal approval path complete approval; according to the method, the reinforcement learning model is used as the dynamic approval path planning model, and the optimal approval path is accurately generated, so that the approval process can plan a reasonable circulation sequence according to the characteristics of the approval file, and the file approval efficiency is improved.

The invention discloses a civil aviation element configuration optimization method based on mixed integer dynamic programming. The method comprises the following steps: S1, constructing a Chinese civil aviation core element and carbon emission spatial-temporal characteristic database; s2, establishing a mixed integer dynamic programming model with the purpose of minimizing the total cost of the system in the programming period; and S3, establishing decision variables, constraint conditions and a fusion solution algorithm framework required by the mixed integer dynamic programming model. And S4, based on the fusion solution algorithm framework, solving the mixed integer dynamic programming model by using a mathematical programming solver integrated with a robust optimization module so as to obtain a civil aviation core element dynamic configuration scheme which is optimal in total system cost in multiple periods in the future and meets the uncertainty scene. According to the method provided by the invention, a multi-source data fusion algorithm is optimized, a carbon emission measuring and calculating method is deepened, and solver parameters are adjusted, so that the collaborative requirements of improving the operation efficiency and reducing the carbon emission from the perspective of carbon cost are met.

The invention discloses a dam break flood refuge path dynamic planning model and method based on a cellular automaton, a Moore neighborhood topological structure is adopted for refuge path planning, and the refuge path planning model is a transition probability calculation formula for refugees to move to adjacent cells. Based on cellular automaton theoretical modeling, the dam break flood emergency evacuation process can be discretized, the real-time evolution rule of the dam break flood is considered, the behavior characteristics of refugees are fully considered, the assessment of the refuge transfer route is not limited to the route length, a multi-dimensional safety assessment system is also constructed, and the safety of the refuge transfer route is improved. The core indexes cover path geometric features and space-time safety parameters. The space safety criterion requires the path topological structure to strictly avoid the flood risk area and the submerged area, and the geometric safety of the evacuation trajectory is ensured; the time safety criterion focuses on flood dynamics response time efficiency, advanced prediction of the submerging trend is achieved through the model, and the reliability of the evacuation time sequence is guaranteed.

The invention discloses a dynamic optimal matching method for an online car-hailing aggregation platform. The dynamic optimal matching method comprises the following steps: S1, defining variables required by approximate dynamic planning; s2, constructing an approximate dynamic programming matching model for maximizing the total revenue of the aggregation platform; and S3, based on the real-time analyzed variables required by the approximate dynamic programming, value approximation is performed on the expected profit in the approximate dynamic programming model by adopting an approximate dynamic programming algorithm, so that a platform vehicle driver and passenger matching strategy can be determined, and dynamic optimal matching can be realized. The dynamic approximate programming algorithm is introduced into the online car-hailing driver and passenger pricing matching strategy, more accurate pricing matching strategy adjustment is realized through real-time analysis of passenger demands, driver supply and market dynamics, the platform can continuously optimize the pricing matching strategy, the profit is maximized, the travel experience of the user is maintained, and the user experience is improved. The method not only improves the efficiency and stability of the whole system, but also can promote the reasonable utilization of resources, creates a win-win situation for drivers and passengers, and plays a positive role in the sustainable development of the platform.

The invention relates to the technical field of railway signal processing, and discloses a track circuit compensation capacitor fault prediction method and system. The method comprises the following steps: acquiring real-time impedance spectroscopy data by using a distributed capacitive sensor network; performing multi-scale wavelet decomposition on the data, and extracting frequency domain energy distribution and transient abnormal fluctuation characteristics; constructing a dynamic Bayesian network model, and updating hidden state node posterior probability distribution through a variational inference algorithm; generating a fault risk index sequence based on a posterior probability, and designing an adaptive threshold adjustment strategy by using a reinforcement learning framework; constructing a mixed integer dynamic programming model to output fault early warning grade data; and constructing a multi-stage decision tree which comprises a feature screening layer, a pattern matching layer and a verification feedback layer. The method and the system can accurately predict the track circuit compensation capacitor fault in real time, improve the fault prediction accuracy and the system adaptability, reduce the false alarm rate, and provide reliable basis for railway operation and maintenance.

The present application relates to the technical field of resource scheduling, and particularly relates to an emergency rescue resource scheduling optimization method based on dynamic programming, which comprises the following steps: obtaining a population density coefficient of each to-be-rescued point and a road point to each reachable to-be-rescued point thereof; obtaining an initial resource demand degree of each to-be-rescued point; constructing a dynamic programming model to obtain a weighted scheduling time to a target to-be-rescued point; obtaining a road distance from the target to-be-rescued point to each reachable to-be-rescued point thereof and a resource arrival time of each reachable to-be-rescued point thereof; obtaining a second resource demand degree of each reachable to-be-rescued point of the target to-be-rescued point; obtaining a weighted scheduling time to each reachable to-be-rescued point of the target to-be-rescued point; and the dynamic programming model is planned again to obtain an emergency rescue resource scheduling route. The present application aims to dynamically program the emergency rescue resource scheduling, analyze the influence of the change of the resource demand degree of the to-be-rescued point with time, and make the resource scheduling route consider the time factor.

The invention discloses a man-machine cooperation disassembly task dynamic planning method under uncertain operation time. The method comprises the following steps: 1) constructing a man-machine cooperation disassembly information model under the uncertain operation time; 1.1) constructing an uncertain operation time description model of the product parts; 1.2) constructing a disassembling tool, direction and station position switching time model by considering the operation characteristics of the robot and the disassembling personnel; 1.3) constructing a product part disassembly constraint relation model; 2) taking the man-machine cooperation disassembly information model under the uncertain operation time constructed in the step 1) as an environment of a reinforcement learning algorithm, and establishing a man-machine cooperation disassembly task dynamic planning model; and 3) using the trained man-machine cooperation disassembly task dynamic planning model to generate a man-machine cooperation disassembly task planning scheme under the uncertain operation time. The uncertainty of the structural adhesive softening time is quantified by constructing the uncertain operation time man-machine cooperation disassembly information model, and the characterization problem of the disassembly operation time is solved.

The application relates to the technical field of wind turbine data analysis, and discloses a system for analyzing and predicting offshore wind turbine operation data. The system comprises a marine environment data integration module, which collects data to generate a multi-source spatiotemporal synchronous data set; a multi-modal feature fusion module, which extracts cross-modal correlation features to generate a high-dimensional fusion feature tensor; a dynamic fault prediction module, which constructs a bidirectional gated recurrent network model to predict the degradation probability and residual life of key components of equipment; and a self-adaptive optimization control module, which constructs a multi-objective dynamic programming model to optimize the operation strategy of the wind turbine. In addition, the system is also provided with a feedback correction module to correct the parameters of the prediction model, and a virtual sensor module based on a physical information neural network to monitor the tower stress and diagnose sensor faults. The system realizes comprehensive monitoring, accurate fault prediction and optimized control of offshore wind turbines, effectively improves the operation efficiency, reliability and safety of the wind turbines, and reduces the operation and maintenance cost.

The present invention discloses a children's integrated growth and development assessment and management system, specifically relating to the technical field of growth and development assessment; by collecting children's physiological parameters and performing dynamic time series analysis based on machine learning, the growth and development stages of children are divided; the dynamic time warping algorithm is used to process the time series data of children's limb proportions to evaluate the synchrony of bone growth and soft tissue development; by integrating the growth and development stages and synchrony, it is identified whether a child has a risk of developmental deviation; for children with a risk of developmental deviation, combined with genetic information, a genetic algorithm and a dynamic programming model are used to evaluate the individual growth potential of children; the synchrony of children's bone growth and soft tissue development and the individual growth potential and developmental adaptability of children are analyzed in association to evaluate the probability of potential developmental abnormalities and determine whether to initiate personalized intervention measures, realizing comprehensive monitoring and risk warning of children's growth and development status, and having scientificity and practicality.

This invention discloses a reservoir power generation optimization scheduling method that takes into account the spawning protection of the four major Chinese carps, including: 1) establishing a mathematical model of an ecological scheduling mode that takes into account the spawning protection of the four major Chinese carps; 2) establishing a reservoir power generation optimization scheduling model that takes into account the spawning protection of the four major Chinese carps; 3) proposing a dual-state dynamic programming model (DPTS) that couples the optimal state of the scheduling process with the additional state of the scheduling mode; 4) using the proposed dual-state dynamic programming model (DPTS) to solve the reservoir power generation optimization scheduling model established in step 2) to obtain the optimal reservoir power generation scheduling process. This invention addresses the problem of coordinating the power generation scheduling process and the ecological scheduling mode, which cannot be solved by traditional mathematical programming methods or intelligent optimization methods. It proposes a dual-state dynamic programming model (DPTS) optimization modeling method, which can effectively solve the aforementioned mathematical model and obtain the optimal reservoir power generation scheduling process that coordinates the conflict between the ecological scheduling mode that takes into account the spawning protection of the four major Chinese carps and the power generation scheduling process.

The invention relates to the technical field of resource scheduling, in particular to an emergency rescue resource scheduling optimization method based on dynamic planning, which comprises the following steps of: acquiring a population density coefficient of each to-be-rescued point and a route point to each reachable to-be-rescued point of the to-be-rescued point; obtaining an initial resource demand degree of each to-be-rescued point; constructing a dynamic planning model to obtain weighted scheduling time planned to the target to-be-rescued point; obtaining the distance time from the target to-be-rescued point to each reachable to-be-rescued point and the resource arrival time of each reachable to-be-rescued point; obtaining a second resource demand degree of each reachable to-be-rescued point of the target to-be-rescued point; obtaining the weighted scheduling time of each reachable to-be-rescued point planned to the target to-be-rescued point; and the dynamic planning model plans again to obtain an emergency rescue resource scheduling route. The invention aims to analyze the influence of the resource demand degree of the to-be-rescued point along with the time change while dynamically planning the emergency rescue resource scheduling, so that the time factor is considered in the resource scheduling route.

The invention discloses a riding route dynamic planning method and system based on an intelligent riding helmet, and relates to the field of route dynamic planning, and the method comprises the steps: firstly fusing multi-dimensional physiological and behavior data streams collected by the intelligent riding helmet with GPS and riding intention information in real time, so as to construct a feature vector capable of comprehensively representing the current comprehensive state of a rider; and then an unsupervised learning model based on an auto-encoder is introduced, deep reconstruction is carried out on the state feature vector, and the degree that the current riding state deviates from the personalized normal mode of the rider is accurately learned and quantified, so that a dynamic anomaly score is obtained. And based on the abnormal score, adaptively adjusting a multi-target weight vector in a route dynamic planning model, and further triggering and generating a candidate new route which better conforms to the current physiological state. Therefore, the internal physiological state change of the rider can be tightly coupled with the external route decision, so that more accurate, active and personalized dynamic planning of the riding route is realized.

The invention relates to the technical field of electronic part production, and discloses an electronic part production sampling decision-making system based on dynamic programming, which comprises a data acquisition module for collecting raw material information, production equipment parameters, production environment data and product quality detection data through a sensor, a data interface and the like, and sending the data to a data processing module; the real-time performance, accuracy and integrity of the data are ensured, and the data are transmitted to the data processing module. According to the electronic part production sampling decision-making system based on dynamic programming, the dynamic programming model module takes minimization of quality cost as a target, multiple cost factors are comprehensively considered, a constructed sampling decision-making model is more comprehensive, the production state of the next stage is flexibly determined according to whether sampling is carried out or not through a state transition equation, and the production efficiency is improved. The optimal decision sequence can be deduced from the perspective of the overall production cycle by adopting an inverted order solving method, so that the sampling strategy is adjusted in time according to the dynamic change of the production process, and the scientificity and adaptability of the sampling decision are improved.

The present invention provides an inventory optimization method and system based on a deep learning model, which relates to the technical field of deep learning. The method includes obtaining multi-dimensional data of commodities, constructing a dynamic convolution kernel using a graph neural network, and combining a multi-layer perceptron to construct a soft clustering assignment matrix to obtain long-term dependence features that integrate spatial and temporal dimensions. After fusing short-term and long-term features, the fused features are input into a bidirectional long short-term memory network to generate a sales volume prediction sequence, and the prediction confidence interval is calculated to obtain the final sales volume prediction result. Based on the sales volume prediction result, the safety inventory level is calculated, and combined with an inventory cost function, a dynamic programming model based on deep reinforcement learning is used to generate a replenishment decision, and finally the decision is sent to the supply chain execution system. The present invention accurately predicts sales volume through a deep learning model and optimizes inventory management, reduces warehousing costs, out-of-stock costs, and overstock costs, and effectively improves the efficiency of the supply chain.

The present disclosure provides a server parameter optimization method and device, wherein the method comprises: obtaining a state parameter set and an execution action set of a server cluster, the state parameter set and the execution action set having a time label; based on the state parameter set and the execution action set, determining a local evaluation prediction parameter by using a multi-agent reinforcement learning algorithm; based on the state parameter set and the execution action set, determining a global evaluation prediction parameter by using an adaptive dynamic programming model; and based on the local evaluation prediction parameter and the global evaluation prediction parameter, optimizing the execution action set. The method of the present disclosure determines the local evaluation prediction parameter and the global evaluation prediction parameter corresponding to the server cluster by using the QMIX model and the ADP model, thereby realizing the automatic optimization of the execution action set of the server cluster, so as to improve the stability and service efficiency of the server cluster.

The application discloses an AI telephone customer service automatic scheduling method for large-scale services and belongs to the technical field of intelligent customer service scheduling. A preset time window is taken as a monitoring granularity, and three types of features, including call semantic complexity, customer emotion time sequence and AI node computing power load, are collected in parallel. Then, semantic features and customer portrait are fused to calculate an expected business value score, and the hardware load is quantified to calculate the marginal service cost of AI resources, so that a dynamic programming model with the maximum business value per unit of computing power as the target is constructed. In combination with the value and cost ratio, a service path is determined from a multi-level AI model resource pool and an artificial channel. When the service subject needs to be switched, the dialogue state is synchronized according to a distributed cache, the unperceived migration is completed under the premise that the voice channel is not disconnected, the model weight is iteratively updated by using online reinforcement learning, and the scheduling strategy is adaptively optimized. The application is widely applied to large-scale AI telephone customer service scenes and takes into account service experience and computing power utilization efficiency.

The application particularly relates to a robot milling posture optimization method based on a pruning strategy and a dynamic programming algorithm, which comprises the following steps: firstly, based on differential kinematics, the maximum allowed variation of adjacent tool position point redundant Euler angles is conservatively estimated to obtain a pruned search window; the redundant angles in the window are discretized to construct a dynamic programming model. In the solving process, the search window is pruned to reduce the single-step search space, and a memoization caching mechanism is adopted to eliminate repeated calculations. Taking the minimum cumulative deformation error as the target, a penalty cost function and a forward recursive state transition equation are established in combination with joint limiting, singularity, collision avoidance and trajectory smoothness constraints, and a global optimal redundant angle sequence is obtained through backtracking. The application greatly improves the posture optimization calculation efficiency while ensuring the machining precision.

The embodiment of the present application belongs to the field of artificial intelligence and relates to a question-answer matching method for a question-answer system, including constructing a dynamic programming model of the question-answer matching system. When receiving a user's question sentence, concept keywords of the user's question sentence are extracted based on the dynamic programming model; the concept keywords are matched with concepts stored in a knowledge base to determine an optimal concept sequence corresponding to the concept keywords; a standard concept sequence pre-stored in the knowledge base is obtained, and the optimal concept sequence is matched with the standard concept sequence to obtain a standard answer corresponding to the user's question sentence. In addition, the present application also relates to blockchain technology, and the standard answer can be stored in a blockchain. The present application realizes the rapid acquisition of optimal keywords, enables the correct answer corresponding to the current user's question sentence to be quickly matched through the optimal keywords, and improves the matching efficiency and accuracy of the question-answer system.

The invention relates to the technical field of power systems, in particular to a convex hull construction method, system and equipment for a single-unit combination problem and a medium, and the method comprises the following steps: firstly, constructing a unit combination mixed integer programming model based on a single-unit combination state; then, based on the unit commitment mixed integer programming model and the minimum start-stop time constraint, constructing a state transition space; thirdly, based on the state transition space, constructing a dynamic planning model; and finally, transforming the dynamic programming model to obtain a linear programming model. According to the convex hull construction method for the unit combination problem of the single unit provided by the embodiment of the invention, an original mixed integer programming problem is converted into a linear programming problem through equivalent transformation in a mathematical form, so that the solving difficulty of the unit combination problem of the single unit is reduced; and meanwhile, the calculation efficiency of the unit combination problem of the single unit is remarkably improved.

The application discloses a smoke screen jamming bomb launching optimization method and system based on a 0-1 dynamic programming model, relates to the technical field of jamming bomb launching, and comprises the following steps: constructing different launching scenes of a UAV carrying a smoke screen jamming bomb to interfere with an incoming missile; in view of the different launching scenes, discretizing time, constructing a motion trajectory model of the UAV, the missile, free fall of the smoke screen jamming bomb and a smoke cloud cluster, constructing an equation of a line connecting the missile and a target point at each time point, determining the distance from the center point of the smoke cloud cluster to the line, establishing a shielding model according to the relationship between the distance and the radius of the cloud cluster; defining whether the shielding condition is met at the discretized time as a decision variable, taking the maximum of the accumulated discrete shielding effective time as the target, combining the constraint conditions of the flight angle and the flight speed of the UAV, the launching time and the detonation time of the smoke screen jamming bomb and the shielding model, constructing a 0-1 dynamic programming model at the discretized time, and obtaining the optimal launching strategy through solving.