57 results about "Response model" patented technology

The invention relates to the field of computer industry, and discloses an integrated computer software and hardware combined sales optimization system and method, and the method comprises the steps: extracting software and hardware sales records, customer transaction behaviors and version updating tracks, and constructing a fusion data set of heterogeneous sales data; performing association weight analysis on the fused data set, and extracting strategy sensitive points in software and hardware linkage transaction in combination with a customer behavior intention model and product life cycle characteristics; constructing a product combination feasible region in a specific sales window by adopting a combination optimization graph search algorithm based on the tag nested structure; mapping the candidate combined product list to a historical sales behavior map, and extracting dynamic feedback modes of a combined strategy under different sales paths by introducing a price elastic response model and market disturbance fluctuation characteristics; and carrying out iterative adjustment and node intervention on the strategy path based on the high-sensitivity area. The method has the advantage of improving the scientificity of sales strategy formulation.

The invention discloses a regional integrated energy system optimization method and system, and the method comprises the steps: S1, constructing a multi-energy demand response model, and carrying out the linkage scheduling among multi-energy loads based on the multi-energy demand response model; s2, designing and optimizing a stepped carbon transaction mechanism; and S3, performing multi-objective optimization and cooperative operation. According to the invention, through a three-layer optimization architecture of multi-energy demand response, stepped carbon transaction and multi-target cooperation, economic, low-carbon and efficient cooperation optimization of the regional integrated energy system is realized, and the blank of the traditional technology in the aspects of multi-energy flow linkage scheduling, dynamic carbon price excitation and new energy refined consumption is filled.

The invention discloses an energy storage system control method and system based on time-of-use electricity price and multi-modal optimization, and the method comprises the steps: simulating supply and demand fluctuation in a complex scene through a pre-constructed energy storage system control strategy model based on deep reinforcement learning, dynamically optimizing a charging and discharging plan of energy storage equipment, and generating an energy storage resource distribution efficiency optimization scheme; generating a real-time electricity price adjustment scheme by adopting a game theory price adjustment algorithm based on the energy storage resource distribution efficiency optimization scheme, the real-time demand of power grid supply and demand balance, the user electricity consumption behavior change and the power grid operation state dynamic state; generating a user behavior response data set through a pre-constructed user behavior response model based on the real-time electricity price adjustment scheme in combination with user economic benefit protection requirements; and calculating a fluctuation ratio of a power grid load change trend by combining the user behavior response data set with real-time monitoring data through a power grid supply and demand balance dynamic evaluation algorithm, and determining a final energy storage scheduling scheme. The purposes of real-time monitoring and collaborative optimization of energy storage system control are achieved.

The invention discloses a lightweight member marketing method and device for real-time conversation, a terminal and a storage medium, and the method comprises the steps: responding to a received user voice stream, continuously generating an incomplete intermediate text stream through streaming voice recognition, and inputting the intermediate text stream into a lightweight marketing response model; the lightweight marketing response model predicts the potential intention of the user in real time based on the intermediate text stream, and pre-assembles one or more candidate response frameworks from the fragmented marketing corpus; when it is detected that the utterance of the user ends, the real intention of the user is determined based on a complete final text stream generated by streaming speech recognition; and arbitrating the candidate reply framework according to the weighted decision factor set to obtain an arbitration result, determining final reply content according to the arbitration result, converting the final reply content into an instant response call, and outputting the instant response call. According to the method, the time delay of the real-time call marketing process can be reduced, and the concurrent processing capability is improved.

The invention relates to the technical field of catering oil fume emission time sequence accurate cooperative control, in particular to a catering oil fume emission dynamic regulation and control system which comprises a monitoring module for collecting oil fume concentration, environmental parameters and execution mechanism state signals; the dynamic modeling module generates an emission trend predicted value; the response quantification module is combined with the delay parameters to construct a physical dynamic response model; the time sequence compensation module is used for calculating fan lag offset, purification unit advance offset and air valve interlocking offset based on real-time working conditions; the cooperative control module outputs a synchronization instruction carrying an offset parameter, so that the fan speed is increased, and the activation time of the purification unit is aligned with the opening and closing action time of the air valve; the closed-loop correction module extracts an actual response curve of the execution mechanism; and the model updating module compares the theoretical output value and updates the delay parameter when the deviation exceeds the threshold value. Through physical response modeling and a dynamic time sequence compensation mechanism, the problem of time sequence mismatch of cooperative control of the fan, the purification unit and the air valve is solved, the purification efficiency is improved, and invalid energy consumption is reduced.

The invention discloses an intelligent fatigue prediction method and system based on recreation facilities, and belongs to the technical field of intelligent operation and maintaining.The method comprises the steps that stress-strain data, environmental parameters and acoustic emission signals of a target recreation facility in multiple operation modes are collected, and an original multi-source data set is constructed; identifying microcrack initiation time nodes and fatigue early-stage features thereof based on change point detection and spectral analysis; a fatigue response sensitivity matrix is generated by constructing a microscopic response model fused with environmental factors; predicting a microcrack propagation path by using a time recursion model, identifying a fatigue risk point, and automatically generating a maintenance suggestion; if a frequency domain abnormal signal is found, carrying out residual life reevaluation and dynamically optimizing model parameters; according to the method, early fatigue recognition, trend prediction and adaptive optimization can be realized, and the safety and maintenance efficiency of recreation facilities are improved.

The invention discloses a training method of a reply key point determination model, a verbal skill reply method and a related product, and the method comprises the steps: obtaining instruction information used for model training, and the instruction information is used for instructing a to-be-trained model to output historical reply key points corresponding to historical dialogue data based on the historical dialogue data, the historical reply key points are to-be-replied keyword information analyzed from historical dialogue data; constructing a training data set, wherein the training data set comprises historical dialogue data and historical reply key points; the to-be-trained model is trained based on the instruction information and the training data set, a reply key point determination model is obtained after training is finished, and the reply key point determination model is used for outputting reply key points corresponding to the to-be-processed dialogue data based on the to-be-processed dialogue data. Therefore, the customer service reply efficiency and response speed can be remarkably improved, and the customer satisfaction degree is further improved.

The invention discloses a vehicle load identification method based on a multi-modal large model, and the method comprises the following steps: selecting a reference bridge in a region for testing, and obtaining a reference bridge case library; analyzing the new bridge through a multi-modal large model, and matching a plurality of reference bridges most similar to the core characteristics of the new bridge from a reference bridge case library; the multi-modal large model migrates a load response model and model parameters of the reference bridge case to a new bridge through a case reasoning mechanism; and according to the structural difference between the new bridge and the matched reference bridge and the actual working condition of the new bridge, the multi-modal large model carries out architecture reconstruction on the migrated load response model. The method has the beneficial effects that the new bridge can directly reuse the model parameters and the load response rule of the reference bridge through the constructed reference bridge case library in combination with the retrieval enhancement generation and bridge-crossing knowledge migration mechanism of the multi-modal large model, so that the time cost and the economic cost of bridge-crossing deployment can be greatly reduced.

The invention relates to a sequential test design method based on multi-response modeling considering response correlation. The method comprises the steps of constructing a response model capable of simultaneously predicting multiple responses based on a multi-response Bayesian support vector machine model, performing iterative sampling by combining a local development criterion based on expanded nearest neighbor gradient projection and a global exploration criterion based on a variance matrix diagonal product, and continuously updating the response model, and until the sequential test design stop criterion is met. By adopting the method, the mapping relationship between a plurality of factors and a plurality of responses in a complex application system can be constructed at the same time, the correlation between the responses is represented, available information is increased through information transmission between the responses, the modeling precision of the response model is improved, and the modeling efficiency is improved. And thus, the effectiveness of sequential test design of a complex application system with multiple responses is improved.

The invention discloses a wind power flexible direct current system frequency response model construction method without communication frequency support, and belongs to the field of power system safety and stability control. According to the method, a traditional frequency response model is expanded by considering power changes of wind power and flexible direct current when a system is disturbed, so that contribution of a communication-free active frequency support strategy to dynamic frequency of the system is quantitatively evaluated. On the basis of the constructed frequency response model, control parameters without communication active frequency support are optimally designed by considering constraints of power change and DC voltage fluctuation of the wind driven generator. According to the method, the optimization model of the frequency control parameters is solved based on the equivalent system frequency response model, the application range of the frequency response model is expanded, and important reference is provided for frequency control and stable operation of a power system.

The invention relates to the technical field of power system optimization control, and discloses a micro-grid energy management method, system and device and a storage medium, and the method comprises the steps: constructing a first optimization model containing renewable energy, distributed power generation and demand response based on an actual operation scene of a micro-grid; establishing a demand response model based on a first load response mechanism, and applying the demand response model to the first optimization model; introducing a first optimization algorithm, and fusing a greedy search mechanism of a second optimization algorithm on the basis of the first optimization algorithm to obtain a first fusion optimization algorithm; and in combination with the actual operation data, solving a first optimization model of the application demand response model by using a first fusion optimization algorithm to obtain an optimal scheduling scheme of each distributed energy source. According to the method, the price elasticity demand response strategy and the advanced meta-heuristic optimization technology are combined, the future micro-grid management practice is effectively guided, and the development of a more elastic and environment-friendly energy system is facilitated.

The invention provides a combined heat and power operation method based on supply and demand bilateral collaborative optimization, which relates to the technical field of energy management, and comprises the following steps: decoupling the thermoelectric connection of a combined heat and power system through an energy storage device and a multi-energy conversion device; based on the decoupled cogeneration system, constructing a demand response model; wherein the demand response model comprises an electrical load response and a thermal load response; according to the demand response model, establishing a mathematical model with the purpose of minimizing the sum of the system operation cost and the response compensation cost; wherein equipment operation constraints on the supply and demand sides are introduced into the mathematical model; a mathematical model is converted into mixed integer linear programming, a mathematical modeling tool is used for carrying out model compiling, a commercial solver is called to solve the mathematical model, a combined heat and power operation rule of supply-demand double-side collaborative optimization is obtained, flexible scheduling and efficient energy utilization of a thermoelectric system are achieved, the operation cost is reduced, and the operation efficiency is improved. And the adaptive capacity of the system to renewable energy sources is enhanced.

The application discloses a kind of based on master-slave game integrated energy system optimization scheduling method, equipment and product, it is related to electric power system control technical field, the method includes obtaining the load prediction data of current scheduling period, renewable energy output prediction data and environmental parameter;Load the integrated energy system equipment model, integrated demand response model and ladder carbon transaction model constructed in advance, based on the model and the data obtained, the distribution robust master-slave game optimization scheduling model of current period is constructed, and the game equilibrium solution under the most unfavorable uncertainty scenario of energy operator is solved, and the optimization scheduling result is obtained.The application realizes the fair sharing of carbon responsibility between game subjects and emission reduction incentive, and still can obtain robust scheduling scheme under extremely unfavorable scenario, guarantee the economy and safety of system.

The application discloses a kind of multi-element load linkage regulation method, system, equipment and medium, comprising: constructing the two-stage operation transaction model of multi-element load aggregation main body user, forms lower user response model;Establish two-stage robust regulation model dominated by distribution network operator;Introduce power grid topology adjustable constraint;Coupling user response model and enhanced operator regulation model, build double-layer interactive optimization framework, form two-stage robust double-layer optimization problem containing integer variable;Optimization problem is solved using nested column constraint generation algorithm, output optimal electricity price guide strategy, direct load control amount and topology adjustment scheme, as the total scheme of multi-element load linkage regulation for weak point uncertainty.

The application belongs to the technical field of power systems, and provides a user demand elasticity quantification method and system considering multi-element user side resource cooperation, comprising: obtaining response models of different user side resources; considering a power grid framework, constructing a multi-element user side resource cooperation and mutual aid optimization model of the obtained response models; solving the constructed cooperation and mutual aid optimization model to obtain cooperation capability quantification results; based on the obtained cooperation capability quantification results, correcting electricity load demand of user participation in demand side response; according to the obtained electricity load demand correction amount, constructing a multi-dimensional elasticity coefficient matrix, quantifying user demand according to the constructed matrix, and completing user demand elasticity quantification considering multi-element user side resource cooperation.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to automated control for a physical system with generic forecasting models. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a training component that trains one or more multivariate time series forecasting models, and a prediction component that forecasts long-horizon action trajectories for a set of state variables over a defined range of time. Furthermore, an analysis component can linearize the state-based action response model, wherein the linearized the state-based action response model can be formulated into an MILP optimization problem and solved to obtain a multi-step set-point recommendation.

A sequence combination-based load long-time power sequence generation method, system and device, and a medium, the method comprising: collecting load-related data, and dividing a load long-time power sequence into two segments; constructing a load power prediction model by adopting a deep directed residual map convolutional neural network, and generating a load power sequence based on load prediction, namely a first section of load power sequence; generating a load power sequence by adopting fuzzy C-means clustering and a Markov method, and correcting the load power sequence according to the constructed load power model considering load demand development and the power demand response model to obtain a second section of load power sequence; and splicing the first section of power sequence and the second section of power sequence according to a time sequence to form a load long-time power sequence. The method not only combines the advantage of high short-term load prediction precision, but also fully considers the important influence of rapid increase of electrical load and large-scale application of demand side response on the load power sequence in China at present.

The invention discloses a virtual power plant optimal load response method, system and device based on Copilot and a medium. The method comprises the steps that a target virtual power plant Copilot response model is acquired; decomposing the demand response task by using a decomposition module to obtain a fine-grained task of each participating node, and inputting the fine-grained tasks into a fine-grained task processing module for processing; a solver module is used for solving each fine-grained result, and a recommended first response strategy is obtained; evaluating the first response strategy according to the performance influence data and the empirical parameters to obtain an evaluation result, and adjusting the first response strategy according to the evaluation result to obtain a second response strategy; and executing the second response strategy by using the energy controller module, obtaining execution result data, and feeding back the execution result data and performing optimization training. The response strategy is corrected and adjusted by using the monitored environment change and system performance change, so that the stability and flexibility of the model are improved, and the technical problem is solved.

This invention discloses a warehouse management system and method based on RFID electronic tag positioning, comprising the following steps: deploying multiple RFID readers to construct a temporal resonant excitation field; writing a set of response control parameters and binding RFID electronic tags to the items to be managed; determining whether a response state has been entered and constructing a tag response time set; performing preliminary tag positioning to generate initial three-dimensional spatial coordinates; collecting electromagnetic environment information to perform further judgment and jointly determining whether a response state has been entered; constructing a virtual tag response model to generate completed three-dimensional spatial coordinates; constructing tag response behavior characteristics and generating disturbance scheduling parameters; and writing the spatial behavior attribute set of RFID electronic tags into the warehouse management system. This invention uses temporal resonance and virtual tag modeling to achieve accurate RFID warehouse positioning, anomaly completion, and high-density, efficient inventory management.

The invention discloses a garlic whole-process monitoring decision-making platform based on AI and big data, relates to the technical field of artificial intelligence, and solves the problems of data aperture heterogeneity and sample deviation in garlic price prediction in the prior art and the problem that a result deviates from the actual market due to the lack of inventory-behavior feedback modeling in the prediction process. According to the scheme, a multi-level linkage architecture comprising a data protocol layer, a causal deduction layer, an interactive analysis layer, a feedback simulation layer and a parameter calibration layer is constructed, and a consistent data stream is formed by performing time sequence protocol and causal correction on multi-source price data; performing interactive analysis on the price chain and the inventory sequence, introducing a multi-subject response model to simulate market feedback, and finally forming a closed-loop prediction sequence through a dynamic calibration mechanism; according to the method, the prediction stability of garlic whole-process monitoring decision and the reliability of risk research and judgment are remarkably improved.

This specification provides a method, apparatus, and storage medium for distribution transformer (DTR) scheduling based on differentiated edge demand. The method includes: acquiring load demand information of electricity users and a differentiated price-based response model of the electricity users; inputting the load demand information and the differentiated price-based response model into a pre-trained price-demand prediction model to obtain price-demand relationship data; and determining a DTR scheduling strategy based on the price-demand relationship data, preset constraints, and preset DTR costs. The technical solution provided in this application addresses the problem that existing technologies, which set a linear relationship between electricity consumption changes and electricity price changes, still struggle to achieve the desired DTR scheduling results.

The application discloses a vehicle load identification method based on a multi-modal large model, which comprises the following steps: selecting a reference bridge in a region for testing to obtain a reference bridge case library; analyzing a new bridge through a multi-modal large model to match a plurality of reference bridges with the closest core characteristics of the new bridge from the reference bridge case library; the multi-modal large model migrates the load response model and model parameters of the reference bridge case to the new bridge through a case reasoning mechanism; and the multi-modal large model reconstructs the migrated load response model according to the structural differences between the new bridge and the matched reference bridge and the actual working conditions of the new bridge. The application has the beneficial effect that, through the constructed reference bridge case library, the generation of the multi-modal large model retrieval enhancement and the cross-bridge knowledge migration mechanism, the new bridge can directly reuse the model parameters and load response law of the reference bridge, thereby greatly reducing the time cost and economic cost of cross-bridge deployment.

The present invention provides a method for constructing an automatic response model and an automatic response method. The method for constructing the automatic response model includes: extracting features from target response information to generate first identification information corresponding to the target response information, where the target response information is customer response information in the case of failed machine marketing; based on the first identification information, determining at least one target marketing script information from candidate artificial marketing script information corresponding to candidate customer response information, where the candidate customer response information is all customer response information in the case of successful artificial marketing. The method for constructing the automatic response model of the present invention can improve the conversion rate of machine marketing.

The invention provides an enterprise risk early warning and coping model deployment method and device, a medium and equipment. The method comprises the following steps: acquiring enterprise risk knowledge, and constructing a risk early warning knowledge base; obtaining enterprise risk cases, and constructing a risk case library; obtaining enterprise risk data, carrying out cleaning processing and labeling processing on the enterprise risk data to obtain a sample set, and carrying out model training according to the risk early warning knowledge base, the risk case base and the sample set to obtain an enterprise risk early warning and coping model; carrying out optimization processing on the enterprise risk early warning and coping model; carrying out multi-dimensional testing on the enterprise risk early warning and coping model after optimization processing; and after the test is passed, deploying the enterprise risk early warning and coping model. Due to deep learning of massive risk cases and coping strategies by means of a large model, scientific and feasible coping schemes are customized for various risks, and enterprises can be assisted to quickly take proper measures in the face of complex and variable risks.

The application discloses a method and system for active response load prediction based on a hybrid neural network, which adopts the features of real load data and generates time series data as input, adopts a CNN-LSTM neural network model for a load classifier, uses an AD response model to simulate the active response effect of the load, and adopts an RNN neural network model for load prediction, so that the application has the advantages of novel scheme and accurate result, and can perform load feature analysis and preprocessing on a basic data set containing different types of loads; a time series data set is created according to the preprocessed data set as a benchmark data set for load classification research, the application can predict the attribution label of the load and classify the load. The model extracts different types of load features through CNN, introduces a batch normalization layer for standardizing the output of the CNN layer, stabilizes the training process and accelerates convergence, and captures the dependency between time steps through LSTM, so that the output result of the classification model has high accuracy and reliability.

The application belongs to the field of intelligent conversation, and provides a conversation intelligent access system and method, which comprises the following steps: hosting different types of multiple conversation accounts to the cloud to realize centralized management and unified scheduling of the accounts; receiving conversation messages from the multiple conversation accounts in real time, and performing effectiveness screening and preprocessing on the accessed messages; classifying and distributing the accessed effective conversations based on a shunting model; identifying customer intention based on a response model, and automatically responding to conversations meeting preset rules; manually responding to conversations not shunted to the AI response module; performing feature extraction and labeling processing on accessed customer information to establish a customer portrait; and dynamically updating the shunting model and the response model based on the customer portrait.

The invention discloses an independent energy storage day-ahead market transaction decision optimization method and system, and relates to the technical field of power grid regulation and control, and the method comprises the steps: constructing an electricity price change response model, constructing an excitation compensation response model, and constructing a hybrid response model; constructing a multi-objective decision optimization function according to the maximum independent energy storage profit, the minimum demand response cost and the highest user satisfaction degree, and constructing a transaction decision optimization model through the multi-objective decision optimization function, an electricity price change response model, an excitation compensation response model and a mixed response model; and inputting current day-ahead market transaction information and current load data to the transaction decision optimization model, solving the transaction decision optimization model according to the multi-objective decision optimization function, and obtaining an independent energy storage day-ahead market transaction decision. The method has the beneficial effects that the cost and profit of the user side and the independent energy storage side are balanced, and the suitability and rationality of decision making are improved.

The application discloses a multi-aggregator demand response incentive method for overlapping users, which comprises the following steps: establishing a demand response model of users, a dissatisfaction model of users participating in demand response, and an optimal incentive model of aggregators implementing demand response; establishing a multi-aggregator cooperation game model considering overlapping users, and formulating a negotiation set in the cooperation game; regarding the overlapping users as users participating in the demand response plan of each aggregator, obtaining an incentive strategy S1 of each aggregator according to the response model of the users; regarding the overlapping users as users not participating in the demand response plan of each aggregator, obtaining an incentive strategy S2 of each aggregator according to the response model of the users; judging the optimal result of the negotiation set according to S1 and S2, and finally obtaining the best incentive of each aggregator under the condition of the overlapping users.

This invention relates to the field of electric vehicle charging technology, and discloses a method and system for optimizing charging fees for charging piles based on dynamic rates. The method includes: collecting multi-dimensional feature data and user charging data, performing preprocessing and feature extraction; constructing and training a charging demand prediction model to predict charging demand in real time; constructing a price response model and combining it with a charging load prediction curve for dynamic rate optimization; performing user cluster analysis and designing personalized incentive strategies; setting rate information release rules and dynamically scheduling charging resources; collecting operational data and user response data in real time, and optimizing the charging demand prediction model and price response model based on the charging load prediction curve; and performing data encryption and privacy protection. This invention, through a personalized incentive mechanism, formulates differentiated incentive strategies for three types of users: price-sensitive, time-sensitive, and convenience-first.

The application discloses a power grid state evaluation and prediction method, device, terminal and medium, the method comprises the following steps: real-time collection and preprocessing of power distribution network terminal equipment operation data in smart grid, spectrum analysis is carried out, and the characteristics of the signal are analyzed through wavelet transform; a nonlinear system response model based on deep learning is constructed, and the parameters of the response model are optimized; in combination with machine learning, the power grid dynamics are evaluated and predicted according to the results of FFT and wavelet transform and the output of the above response model. The application provides a comprehensive and efficient solution for real-time collection and preprocessing of power grid data in smart grid and evaluation and prediction of smart grid dynamics. Through innovative technical means and algorithms, the application shows significant advantages in the stable and efficient operation of smart grid, especially in analyzing, evaluating and predicting the state characteristics of the power grid.