58 results about "Optimization system" patented technology

The invention relates to the technical field of collaborative optimization, in particular to a virtual power plant power generation-utilization-price collaborative optimization system based on an AI large model, and the system comprises a load confidence matching module, a resource stability mapping module, a source-load capacity coupling module, an electricity price interval adjustment module and a comprehensive regulation and control linkage module. According to the method, the confidence interval prediction of the load demand is realized based on the hybrid neural network modeling of the load behavior data and the equipment temperature control characteristic sequence, and the scheduling matching confidence is measured according to the boundary overlapping condition of the prediction interval and the power generation response characteristic; a stability screening mechanism for adjusting resources is constructed in combination with the output fluctuation ratio and the equipment inertia characteristic, the controllability of load adjustment and the real-time performance of source side response are improved, the price adjustment rhythm is corrected through an electricity price response delay factor, dynamic closed-loop linkage between load adjustment and price guidance is achieved, and the load adjustment efficiency is improved. The execution priority is dynamically updated under the condition that multiple response conditions are matched, and the certainty of resource scheduling and the sensitivity of response are improved.

The invention discloses an e-commerce supply chain intelligent scheduling optimization system and method based on big data, and relates to the field of intelligent logistics scheduling, and the system comprises a demand prediction module, a balance optimization module, a path optimization module, a collaborative replenishment module and a feedback driving module. According to the method, the deep learning model and the time sequence decomposition method are combined, and multi-level modeling is performed on the historical order data and the real-time sales data, so that supply chain imbalance caused by prediction deviation is avoided. A dynamic replenishment plan is generated based on the prediction result and the inventory early warning information, real-time matching of the inventory and the demand is achieved, the stockout rate and inventory redundancy are effectively reduced, and the storage resource utilization rate is improved. By establishing the multi-constraint path optimization model and comprehensively considering order distribution, vehicle load and real-time traffic data, the distribution path can be dynamically adjusted, the vehicle utilization rate and the distribution time efficiency are improved, and the energy consumption and the cost caused by empty driving and detour are reduced.

The invention relates to the technical field of e-commerce logistics and supply chain management, and discloses a multi-channel e-commerce platform order processing optimization system and method, and the method comprises the steps: correcting physical inventory data through a Lagrange dual variable fed back in a previous period, calculating a virtual inventory, and receiving a discrete order flow; constructing a space-time hypergraph model of the to-be-processed order according to the commodity homogeneous attribute and the spatial neighborhood attribute; performing constraint optimization solution on the hypergraph model based on a Lagrangian relaxation algorithm, and generating an optimal order allocation matrix meeting productivity constraints and a Lagrangian dual variable of a current period; and analyzing the distribution matrix to generate an operation instruction, issuing the operation instruction to the physical warehouse, and feeding back the dual variables to the inventory calculation module. According to the method, collaborative operation benefits are mined through the space-time hypergraph, and a negative feedback closed loop with physical capacity pointing to front-end sales is constructed by using dual variables, so that performance cost optimization and flow adaptive control are realized.

The invention relates to the technical field of logistics scheduling, and discloses an intelligent cross-border logistics scheduling optimization system, and the system comprises the steps: S1, obtaining cross-border logistics full-chain parameters in real time through a multi-source heterogeneous data collection module, and generating a logistics basic data set; s2, performing real-time risk quantification processing on the logistics basic data set based on a dynamic risk modeling engine, and constructing a logistics risk factor matrix; by constructing a multi-source heterogeneous data acquisition module and integrating the real-time transportation situation, policy compliance and global risk data of a cross-border logistics full chain, the problems of data islands and information lag in a traditional system are solved, comprehensive perception and deep fusion of logistics basic data are realized, a solid data support is provided for subsequent intelligent scheduling, and the real-time transportation situation, policy compliance and global risk data of the cross-border logistics full chain are integrated. And the perception capability of the system to a complex cross-border environment is improved.

The invention discloses a cloud computing bare metal hardware market distribution and management optimization system and method. The system comprises a resource access module, a distribution channel management module, an intelligent matching module, a transaction settlement module, a data analysis and optimization module, a safety and operation and maintenance management module and the like. Standardized aggregation of heterogeneous resources is realized through a resource access system, and the problem of fragmented management is solved; the distribution channel management system dynamically adjusts distribution rules and improves the channel cooperation efficiency; the intelligent matching system is combined with user behavior analysis to realize accurate supply and demand connection; the transaction settlement system integrates payment channels and marketing tools and simplifies fund circulation; the data analysis system precipitates full-link data to support decision optimization; the safety and operation and maintenance system guarantees safe and stable operation. According to the method, through the steps of resource access standardization, channel rule dynamic and the like, efficient, intelligent and standardized management of the whole distribution process is realized, and the market distribution efficiency, accuracy and safety are improved.

The invention provides an electricity market transaction optimization system based on deep reinforcement learning, and the system comprises a hybrid prediction subsystem which is used for optimizing an electricity market transaction strategy through electricity price fluctuation prediction, frequency modulation demand prediction and carbon price trend prediction; the multi-agent decision-making subsystem is used for carrying out optimization generation and dynamic adjustment on an electricity market transaction strategy through a plurality of agents with specific tasks; and the risk control subsystem is used for monitoring, evaluating and controlling the transaction risk of the power market through market risk control, ontology risk control and policy risk response, and optimizing the transaction strategy of the energy storage system. According to the technical scheme, multi-target collaborative optimization and cross-time arbitrage of energy storage participating in an electric power spot market, an auxiliary service market and a carbon emission permit market are realized.

The invention discloses a quantitative transaction strategy dynamic optimization system and method based on deep learning, and belongs to the technical field of quantitative transactions, and the system comprises a data collection module which is used for collecting data of a target market invested by an investor from a data source; the data source comprises a security exchange and financial media; the acquisition frequency setting module is used for setting the frequency of data acquisition from the data source according to the transaction demand of the investor, and the acquisition frequency setting module comprises a distinguishing unit and a data setting unit; the distinguishing unit is used for distinguishing the transaction demands into high-frequency transaction demands and intermediate-frequency transaction demands according to the transaction demands. Through dynamic data adaptation, quantitative risk grading, multi-feature prediction and hierarchical fund management, accurate optimization and risk controllability of a quantitative transaction strategy are realized, and adaptability and income stability of the strategy in a complex market environment are improved.

The invention relates to the technical field of management systems, and particularly discloses a marketing scene dynamic simulation and strategy optimization system, which comprises a multi-source data fusion module, a dynamic scene simulation engine, a multi-agent strategy game module and a strategy iterative optimization and deployment module, and a closed loop from market environment perception to optimal marketing strategy generation and execution is realized. According to the invention, through a microcosmic consumer heterogeneity model, in combination with deep survival analysis and an attention mechanism, decision laws of individual consumers and differentiated responses to marketing stimulation can be accurately captured, the limitation of macroscopic analysis of a traditional system is broken through, full-dimension conversion prediction from individuals to groups is realized, and the prediction efficiency is improved. Refined data support is provided for strategy making, and the marketing conversion efficiency is effectively improved.

The present application relates to the field of strategy optimization, in particular to a credit data dynamic arrangement and strategy optimization system based on order perception. The credit report order is parsed to extract enterprise identification, analysis dimension and precision threshold; the internal historical database is searched, and the timeliness score is calculated based on the update frequency, industry volatility and risk level weighting; the timeliness score is compared with the precision threshold, and the gap analysis model is triggered to identify the external data dimension that needs to be supplemented in response to the condition not being met; the supplier selection engine is started based on the external data dimension, the multi-objective optimization algorithm is used to solve the supplier evaluation matrix to obtain the optimal supplier combination; the optimal supplier combination is called to obtain external data, which is fused with historical records after verification to generate a report. The present application dynamically allocates data sources on demand, avoids blind purchasing, and makes the data acquisition cost and data quality reach a quantitative balance under the condition of meeting the analysis accuracy.

The invention discloses a merchant agent hierarchical pricing and multi-agent e-commerce transaction optimization system and method, and relates to the field of telemarketing. The method is realized through combination of a user agent Agent-U, a market agent Agent-M and a merchant agent Agent-S. The merchant agent Agent-S comprises a user agent Agent-U, a market agent Agent-M and a merchant agent Agent-S. The user portrait analysis module is used for generating a value evaluation coefficient in real time; the third-level price strategy library is used for storing a new customer erosion pricing strategy, a VIP value addition strategy and a conventional competitor benchmarking strategy; and the dynamic adjustment engine responds to market intelligence data pushed by the market. According to the invention, the value evaluation coefficient calculation model is fused with the historical consumption, the service sensitivity and the potential value index to realize the accurate user portrait, and then differential response is implemented by adopting the three-level price strategy library, so that the problems existing in the prior art are solved.

The present application relates to the field of coating parameter self-optimization, and discloses a coating process parameter self-optimization system and method fusing model self-learning, wherein a coating process parameter self-optimization method fusing model self-learning comprises the following steps: collecting process parameters, production conditions, equipment power states and detection result data of multiple batches of coating production in real time; aligning and correlating the data according to the process sequence to form a unique mapping relationship; reversely determining corresponding process parameter nodes and working condition node sets to generate a consistency index; jointly comparing the consistency index and the corresponding data chain distribution to output corresponding working condition drift identifiers; introducing the consistency index and the working condition drift identifiers as constraint conditions into a parameter update model to output a constrained parameter update result; and writing the corresponding new round of detection results into the unique mapping relationship to generate an incremental updated mapping relationship and a reachable state space. The present application has the advantage of improving the stability of the optimization result.

The application discloses a distributed decoupling optimization method for a comprehensive energy system considering carbon trading, and comprises the following steps: establishing a centralized optimization framework of an electrically coupled system, initializing global data and information of a power system and a gas system; constructing a centralized model of a regional comprehensive energy system, wherein an objective function of the model comprises the power system, the gas system and carbon emission cost, and corresponding operation constraints are added to the objective function; converting an original non-convex problem into a mixed integer second-order cone programming based on SOCP relaxation, and performing reactive power optimization by using an ADMM consistent distributed algorithm; introducing consensus variables to represent the synergistic effect between the power and natural gas networks based on the ADMM method of consistent variables, so as to solve a distributed optimization problem of the regional comprehensive energy system; and finally, a case analysis of a regional electric and gas comprehensive energy integrated system is performed, and the distributed decoupling optimization of the system is realized by using the ADMM method of consistency. The application also comprises a distributed decoupling optimization system for a comprehensive energy system considering carbon trading.

The invention relates to the technical field of financial science and technology, in particular to an intelligent transaction optimization system based on source network load storage. According to the technical scheme, the intelligent transaction optimization system based on source network load storage comprises an electric power balance optimization module, a system security and stability module, a cost control optimization module, an intelligent scheduling control module, an intelligent operation and maintenance management module and a market transaction optimization module; according to the invention, through cooperative work of the matching engine and the electronic contract module, a direct transaction channel of a source network load storage whole link is established. Through a standardized electronic contract and an intelligent matching algorithm, real-time and efficient matching between green electricity producers and consumers is realized, information barriers and institutional cost in traditional transactions are eliminated, mobility of green electricity transactions is improved, transaction cost is reduced through a direct transaction mode, and participation enthusiasm of market subjects is enhanced.

The invention provides a second harmonic characterization and optimization system, which comprises an incident light path system, an emergent light path system and an annealing light path system, and is characterized in that the incident light path system is used for enabling a light beam emitted by an incident laser source to enter a tested sample to generate second harmonics; a signal reflected by the second harmonic waves passes through the emergent light path system and then enters a spectrograph to analyze a result; and the annealing light path system is used for annealing a tested sample. According to the second harmonic characterization and optimization system, the annealing light path system capable of achieving in-situ laser annealing is arranged, accurate characterization of interface signals is achieved, meanwhile, accurate annealing is conducted on the same position, the annealing effect can be fed back in real time, time and material losses of the steps of electrode introduction and the like are reduced, and the service life of the second harmonic characterization and optimization system is prolonged. And meanwhile, the laser annealing effect can be subjected to secondary harmonic measurement and real-time feedback through integrated arrangement of laser secondary harmonic and laser annealing, and the result of increasing the yield is achieved.

The invention discloses a reinforcement learning-based house resource dynamic market valuation prediction optimization system, which comprises a data processing module for collecting real estate transaction, geographic information, economic indicators and policy event data and generating a house resource state vector; the expert data module is used for constructing a weighted expert track set according to expert valuation records and transaction prices; the state recognition module is used for executing point change detection and determining market state identification; the confrontation signal module is used for generating a hetero-variance weighted confrontation reward signal based on the improved GAIL model; the risk constraint module introduces conditional value risk constraints based on quantile regression to generate risk weighted signals; the strategy optimization module is used for updating valuation strategy parameters by the risk weighting signals and distilling the valuation strategy parameters into a lightweight reasoning model; and the deployment updating module is used for executing incremental training and parameter updating based on the newly added data. According to the invention, robust optimization and risk adaptive adjustment of the valuation strategy are realized.

The application discloses a blockchain system layered cooperative scheduling optimization method based on transaction volume prediction and relates to the technical field of blockchains.The application increases the performance index, transaction volume index and resource usage index of the blockchain system to provide data support for subsequent optimization, monitors and visually observes the operation of the system in real time, and uses a dynamic adjustment method to cope with sudden frequent transactions and the hysteresis of dynamic adjustment.According to a power formula for measuring the overall performance of the system, compared with single parameter optimization, the overall performance of the system is improved to a certain extent.A multi-objective scheduling optimization method based on an ant colony algorithm is used to cope with the dynamic characteristics of container resource usage, to adjust the target node of the task with the change of the load expectation, to ensure the relative balance of the load, to meet the task demand of the blockchain system, to rationally allocate the existing resources, and to maximize the resource utilization rate as much as possible.

The application discloses a stock dynamic balance method based on sales law prediction and a purchase optimization system, relates to the technical field of stock balance and purchase optimization, and predicts the number of new customers in a current period by using customer transaction data of each historical period, analyzes the stock demand of each commodity in the current period by combining commodity sales data, commodity stock data and customer transaction data of each historical period, obtains the commodity display page of each historical customer and the commodity display page of each new customer in the current period according to the analysis of customer transaction data, commodity sales data and commodity stock data of each historical period, and finally judges whether the stock demand analysis and display page analysis in the current period are reasonable. The application predicts the stock by combining multi-dimensional dynamic data, reduces the stock risk, formulates the individualized commodity display page for each customer, is favorable to strengthening customer stickiness and maximizing the retail volume.

The invention relates to the technical field of employment service, in particular to a dynamic employment service strategy optimization system and method based on multi-modal data analysis, and the system comprises an information collection module which collects user information and market supply and demand information; the post matching analysis module is used for calculating a stability index based on historical data and a post change degree, constructing an occupational portrait and calculating an initial matching degree score; the feature stability evaluation module calculates a stability index corresponding to each feature; the stability weight calculation module is used for generating differentiated second feature weights; and the recommendation strategy optimization module is used for adjusting matching model parameters by utilizing the second feature weight and outputting a corrected post recommendation result. According to the method, quantitative evaluation of stability and market volatility is carried out on different types of feature information, and fine adjustment is carried out on the weight coefficient, so that the accuracy, the real-time performance and the stability of post recommendation are remarkably improved, and the efficiency and the quality of man-post matching are improved.

The application discloses a green certificate and CCER coupled power dispatch decision optimization method and device. The method comprises the following steps: acquiring historical data of price influencing factors, dispatch information data of power plant suppliers, and coupling relationship of green certificates and CCER; predicting the prediction data of various prices by using the historical data and prediction data of the price influencing factors; constructing the state space, action space and reward function of the multi-agent reinforcement learning of the power plant suppliers in the electricity-carbon-certificate market by using the prediction data of various prices, the dispatch information data of the power plant suppliers, and the coupling relationship of green certificates and CCER, and iteratively optimizing the optimal power dispatch decision of the power plant suppliers by using the deep Q network algorithm. The application realizes the intelligent collaborative decision of power dispatch in the deep fusion scenario of green certificates, CCER market and electricity market by constructing the power dispatch decision optimization system based on the combination of the LSTM prediction model, the BP neural network and the multi-agent reinforcement learning.

The application provides a marketing strategy dynamic simulation optimization system data processing method and device, and relates to the field of data processing. The method comprises the following steps: establishing an industry market demand prediction model with a specified period based on industry characteristic data; establishing a market competition situation and market influence model based on historical market data, and determining the competition type of each market participant in the market competition structure in the target industry through the market competition situation and market influence model; establishing a production capacity and energy storage model based on the production process characteristic data, the upper limit of production capacity data and the inventory turnover level data of the target industry; constructing a market dynamic twin engine based on the production capacity and energy storage model, the market competition situation and market influence model and the industry market demand prediction model; and dynamically simulating the marketing strategies corresponding to different competition types through the market dynamic twin engine to obtain optimal marketing strategy data with a specified period.

The invention discloses a staff and quota optimization system and method based on power grid enterprise operation performance analysis, and belongs to the technical field of power enterprise management. Comprising a data acquisition module used for acquiring instantaneous state data of each factor; the index calculation module is used for calculating a real-time business fluctuation index; the mode judgment module is used for dynamically judging whether a current operation mode should be in a standard operation mode or an elastic regulation and control mode according to a comparison result; the interval calculation module is used for calculating and outputting an elastic fixed personnel interval; and the parameter correction module is used for carrying out posteriori correction on weight parameters of various impact factors for calculating the real-time business fluctuation index. By constructing the multi-source business fluctuation factor set, calculating the real-time business fluctuation index and outputting the elastic fixed-staff interval, the effect of accurate matching of human resource configuration and dynamic business requirements is achieved, and the problem of insufficient business fluctuation adaptability caused by a static prediction model in the prior art is solved.

The application discloses a non-performing asset disposal optimization system and method based on intelligent data analysis, and relates to the technical field of financial management; the application integrates multi-source heterogeneous data, constructs a dynamically updated knowledge graph, extracts credit, market and disposal risk characteristics; multi-dimensional risk sub-models are constructed, historical data and optimization algorithms are used to dynamically adjust model parameters, and the prediction accuracy and generalization ability in complex scenarios are improved; based on a weighted scoring mechanism, multiple risk values are fused, and a preset threshold is combined to realize automatic determination of non-performing assets; through a genetic algorithm, a multi-objective optimization is performed on a disposal scheme, an optimal strategy is generated and executed, and a 'evaluation-disposal-feedback' closed loop is formed; the application solves the problems of data island, static model rigidity, high artificial dependence and lack of quantitative optimization of strategies in traditional systems, improves the non-performing asset identification accuracy and recovery rate, compresses the disposal period, and provides a full-process intelligent management scheme.

Systems, methods and computer readable media for automated marketing decisions based on company valuation results derived from ensemble machine learning models include collecting potential customer data for a set of potential customers from a lead source and transmitting the potential customer data to an optimization system. An ensemble machine learning model that establishes a transaction value for each of the set of potential customers based on an enterprise valuation of the seller. A marketing action is then taken. The marketing action may include one or more of budgeting for a transaction with the lead source, targeting communications to members of the set of potential customers, accepting or rejecting members of the set of potential customers, or offloading members of the set of potential customers.

The invention relates to the technical field of energy consumption monitoring and optimization of solid waste treatment equipment, and discloses an energy consumption monitoring and resource utilization optimization system of road solid waste treatment equipment, which comprises a data fusion module for acquiring fused multi-source data and generating a probabilistic component vector of a material; the market insight module is used for quantifying liquidity based on market data and generating a most valuable target product combination; the reverse planning module is used for reversely searching a process by taking the target product as an end point, generating a processing chain and evaluating a success probability; the strategy decision module is used for calculating the expected strategy profit of each processing chain and determining a globally optimal execution strategy; and the scheduling execution center analyzes the optimal strategy into an equipment operation instruction set and issues the equipment operation instruction set to the industrial control system. According to the method, by calculating the expected achievable income including the success probability and the market mobility discount and the total execution cost, the optimal execution strategy with the maximum expected strategy profit is finally solved, and it is ensured that the optimal economic return is taken as the target in production each time.

This invention belongs to the technical field of resource scheduling and management, and relates to an intelligent scheduling and queuing optimization system for charging piles based on big data analysis. The system includes: a state parameter aggregation module for analyzing sensor and electrical signals to establish a dynamic state parameter set; a predictive index calculation module for performing time-series extrapolation to generate time index pairs containing expected arrival and predicted release times; a time-series constraint filtering module for establishing exclusive serviceable time windows and performing verification to filter target pair sets; a global scheduling optimization module for establishing the globally optimal allocation using a combinatorial optimization algorithm with the total predicted waiting time as the target; a resource locking control module for issuing pre-occupancy signals to achieve logical locking of physical resources in the controller; and a closed-loop execution monitoring module for converting into a navigation path and monitoring deviation magnitude to achieve dynamic adjustment. This invention solves the problem of improving matching efficiency and shortening waiting time by utilizing dynamic operating parameters and a global perspective to coordinate resources.

The invention provides a second harmonic characterization and optimization system, which comprises a vacuum cavity, an incident light path system, an emergent light path system and an annealing light path system, and is characterized in that a tested sample is arranged in the vacuum cavity; the incident light path system is used for enabling a light beam emitted by the incident laser source to enter a tested sample to generate second harmonic waves, a signal reflected by the second harmonic waves passes through the emergent light path system and then enters the spectrograph to analyze a result, and the annealing light path system is used for annealing the tested sample based on a feedback signal of the spectrograph. The vacuum cavity is used for adjusting the vacuum degree or the inflation atmosphere. According to the invention, the vacuum cavity capable of adjusting the atmosphere is used for second harmonic characterization of defects, the influence of the external environment is avoided, the detection precision is improved, the annealing light path system is arranged, atmosphere adjustment of laser annealing is carried out, real-time annealing is carried out on an interface with non-ideal measurement, and the steps of measurement and experiment are reduced.

The invention discloses a quality evaluation and optimization system for a point cloud segmentation edge, and relates to the technical field of three-dimensional computer vision and point cloud processing, in the system, a data input module obtains a three-dimensional point cloud segmentation result containing a three-dimensional coordinate and a semantic tag, a feature extraction module captures point cloud global features based on a point cloud Transform network, and the feature extraction module extracts the point cloud global features to obtain a point cloud segmentation result; meanwhile, instance boundary points are recognized through radius neighborhood search, boundary features are obtained through self-attention network processing, a weighted fusion module dynamically fuses the two types of features through learnable weights to generate fusion features, and a score calculation module predicts the segmentation quality index and evaluation contribution weight of each point through a parallel MLP network; a quantized boundary segmentation quality score is obtained through weighted average, a quality optimization module fuses a boundary optimization loss item and a standard segmentation loss into a composite loss function, end-to-end training and parameter updating are carried out on a segmentation model, and optimization and improvement of boundary processing capacity and segmentation precision are achieved.

The invention relates to the technical field of artificial intelligence, in particular to a community commodity AI marking optimization system, which collects commodity basic data and scene data through a data acquisition module, and selects and calls a plurality of AI models for parallel or serial processing through a model scheduling module; a result fusion module integrates model output and generates a preliminary marking result, and a feedback generation module performs automatic verification on the result according to a preset rule and generates verification feedback data; and finally, a result optimization module dynamically adjusts the weight of the model according to feedback, and an optimized target marking result is obtained. According to the invention, through cooperative work of multiple modules, automation and continuous optimization of community commodity marking are realized, and the marking quality and the business efficiency are significantly improved.