149 results about "Evolution strategy" patented technology

The invention discloses a planning and scheduling system for optimizing road and bridge construction progress by using artificial intelligence, and relates to the technical field of road and bridge construction. The system comprises a data interaction system module, and the data interaction system module is bidirectionally and electrically connected with a model collaboration mechanism module. Through multi-source data fusion and model collaboration, the construction progress prediction precision is improved by 30%, resource waste is reduced by 20%, in the aspect of risk prevention and control, the geological disaster early warning advance rate reaches 85% through a space-time risk model, the social risk occurrence rate is reduced by 89% through public opinion monitoring, resource scheduling can be adjusted in real time through reinforcement learning and an evolutionary strategy, and the construction progress prediction efficiency is improved. The emergency risk response time is shortened by 50%, the block chain storage ensures that data cannot be tampered, the intelligent contract improves the multi-party collaboration transparency, and the construction management level is comprehensively improved. The problem that a road and bridge construction progress planning and scheduling system in the prior art does not dynamically adjust resource allocation in combination with risk factors and does not cover collaborative analysis of multi-source data is solved.

The invention relates to a joint estimation method for SOC and SOH of a power battery, in particular to a joint estimation method for SOC and SOH of a lithium ion power battery based on FOASEKF-EKF, comprising fractional order equivalent circuit models of two parallel fractional order CPE branches, and providing a hybrid genetic algorithm HGA fusing a differential evolution strategy and an adaptive variation mechanism. Accurate estimation of SOC and terminal voltage under a fast time scale is realized by introducing a sliding-mode observer and an FOASEKF, periodic online correction is performed on model parameters and battery capacity based on an EKF under a slow time scale, and high-precision and high-robustness battery SOC and SOH joint estimation is realized. The method is suitable for complex industrial environments such as electric automobiles and rail transit, does not need to set a large number of hyper-parameters, does not excessively depend on the quality and quantity of data, has good interpretability, adaptability and engineering practicability, can still achieve high-precision cooperative estimation of SOC and SOH especially under the working conditions of frequent start and stop and unsteady operation, and has good application prospects. And misjudgment and drift estimation risks are obviously reduced.

The invention relates to a clustering and entropy-guided reentrant hybrid flow shop scheduling method. The method comprises the following steps: step 1, establishing a problem model; step 2, setting algorithm operation parameters; 3, adopting an initialization strategy to generate an exploration population and a development population; 4, judging whether a first-stage termination condition is met or not, if not, executing a first-stage evolutionary strategy and an updating strategy on the exploration population and the development population, and otherwise, executing the step 5; 5, constructing an elite population; 6, judging whether a second-stage termination condition is met or not, and if not, executing a second-stage evolutionary strategy on the elite population; otherwise, outputting a Pareto solution set; and 7, updating the elite population. According to the method, dynamic balance of global exploration and local development is realized, and the solution distribution can be improved while the solution set convergence is ensured, so that the completion time and the total energy consumption are reduced, the production cost is reduced, and the workshop scheduling efficiency is improved.

The invention discloses a commercial building energy monitoring and intelligent control method and device and a storage medium, and belongs to the technical field of building intelligent control, and the method comprises the steps: collecting data, building a nonlinear mapping relation, and generating an energy consumption demand prediction tensor; injecting an adversarial disturbance sample, and evaluating the robustness of the prediction model; in combination with the energy consumption baseline, performing cross confirmation and correction on the prediction data exceeding the threshold value; performing attribution analysis on the corrected energy consumption sequence to generate an energy consumption attribution map; adjusting the solution of a multi-objective optimization function according to the atlas, and generating an optimal cooperative control strategy; and the comprehensive efficiency is used as a reinforcement learning reward, strategy parameters are iteratively updated, and a control knowledge base is formed. According to the method, a closed-loop control framework integrating robust demand prediction, dynamic attribution analysis, collaborative optimization decision and a self-evolution strategy is adopted, intelligent regulation and control of building energy consumption can be realized, and the long-term adaptive optimization capability is improved.

The invention discloses a low-altitude economic unmanned aerial vehicle data processing method and system based on a large model, and relates to the technical field of low-altitude economic data processing, and the method comprises the steps: extracting low-altitude multi-target decision features of a low-altitude semantic decision map, carrying out the fuzzy reasoning of the low-altitude multi-target decision features, and generating an anti-interference control instruction set; based on the anti-interference control instruction set, fault logs and task execution data during operation of the unmanned aerial vehicle are collected, and an evolution strategy library is generated through association rule mining; and performing causal analysis according to the evolution strategy library, generating a cluster coordination rule upgrade package, performing dynamic verification on the cluster coordination rule upgrade package, and outputting a self-healing strategy. According to the method, the reliability and the safety of task execution of the unmanned aerial vehicle are improved by constructing the semantic association large model and generating the anti-interference control instruction set.

The invention belongs to the technical field of electric digital data processing, and particularly relates to a method for optimizing errors of a logistics sorting encoder based on an improved grey wolf algorithm. According to the method, Logistic chaotic mapping and Gaussian perturbation are superposed to generate a diversity initial parameter population so as to break through the limitation of traditional random initialization, a fitness function is designed to quantify an angle compensation residual error, and parallel computing is utilized to accelerate evaluation. In the iteration process, global exploration and local development are dynamically balanced through adaptive convergence factors, a bimodal perturbation mechanism is constructed in combination with a differential evolution strategy and Levy flight variation, population effectiveness is maintained through reflection boundary processing, guiding of # imgabs0 # wolf is enhanced through dynamic weight distribution, the position of a leader wolf is updated by adopting an elitist retention strategy, and the population effectiveness is improved. And finally, outputting the optimal compensation parameter when the maximum number of iterations or the residual threshold is met, thereby improving the positioning precision and the operation efficiency of the logistics sorting system.

The invention discloses an intelligent building fault prediction method based on an adaptive algorithm, and the method comprises the steps: obtaining operation state data collected by a plurality of sensor nodes, carrying out the normalization preprocessing, inputting an improved adaptive prediction model, and obtaining the implicit state representation; an initial fuzzy rule set is generated through fuzzy rule induction, a real-time evolution strategy is introduced, fuzzy rules and neural connection weights are dynamically adjusted according to error feedback, and a self-adaptive prediction model updated through evolution is formed; and then performing multi-step prediction on the key operation parameter time sequence by using the updated model, comparing a prediction result with a dynamic fault threshold value to generate a candidate fault indication, and determining the position and category of a fault to be pre-warned in the building system through time sequence stability verification and space consistency analysis. The method can significantly improve the accuracy and real-time performance of intelligent building fault prediction, and has a good application prospect.

The invention discloses a linear guide rail optimization design method and device, a medium and a program product, and the method comprises the steps: (1) constructing a simulation model and a MaOP design model which can optimize the rigidity, modal and weight at the same time based on the linear guide rail structure and static load analysis; (2) generating an elite population based on a Latin hypercube and diversity criterion, obtaining target values of the elite population, establishing a database, and constructing a Gaussian process function model; (3) designing mixed mutation operation based on OCC to generate a filial generation guide rail set; (4) designing a DEP-driven DPM evolutionary strategy to generate a candidate guide rail set, and selecting an optimal candidate guide rail; and (5) obtaining each target value of the optimal candidate guide rail, updating the database and the Gaussian process function model, returning to the step (3) until all optimization targets meet requirements, and outputting an optimal parameter value. According to the method, the MaOP process aiming at the rigidity, the modal and the weight of the linear guide rail can be effectively balanced, and higher precision and better comprehensive performance are achieved.

The invention discloses a cross-border e-commerce intelligent product selection system based on artificial intelligence, and the system comprises a data collection and preprocessing module which is used for collecting original data of a cross-border e-commerce platform and carrying out the processing operation; the parameter sampling module is used for sampling and generating a structure parameter coding vector set; the candidate model construction module is used for constructing a deformable attention neural network model; the model output module is used for outputting a commodity sales prediction value and a selected commodity recommendation probability; the multi-task loss evaluation module is used for calculating a multi-task fitness score; the fitness driving optimization module is used for selecting elite individuals and updating evolutionary strategy parameters; the evolution control module is used for executing an iterative optimization process; the optimal model extraction module is used for constructing a final deformable attention neural network model; and the recommended selected product output module is used for outputting a commodity recommendation result set. According to the invention, collaborative output and performance optimization of commodity sales prediction and intelligent commodity selection judgment results in a cross-border e-commerce scene are realized.

The invention relates to a microwave wireless energy transmission reflector antenna fast multi-objective optimization method comprising the following steps: establishing an MWPT system simulation model, adopting a Bernstein polynomial basis function to carry out dimension reduction processing on a decision space of an antenna, and reducing the number of decision variables; expressing the constructed MWPT system transmitting antenna optimization model as a multi-objective optimization model through a multi-objective optimization function; constructing an agent model based on Gaussian process regression GPR; a proxy model and an evolutionary strategy are integrated through a Gaussian process regression proxy model and a covariance matrix adaptive evolutionary algorithm, a non-dominated solution set is obtained through iterative optimization, and then the multi-objective design of reflector antenna aperture illumination is optimized. According to the method, three performance indexes of BCE, PRL and APC are comprehensively considered, the Bernstein polynomial basis function is adopted to carry out dimension reduction processing on the antenna design decision space, the number of antenna design decision variables is effectively reduced, the proxy model is introduced into the antenna optimization design method, and the optimization design efficiency is improved.

The invention discloses an SIP voice outbound routing method and system based on artificial intelligence, and relates to the technical field of mobile data communication services. The SIP voice outbound routing method and system based on artificial intelligence comprises the steps that S1, gateway operation state data and call feedback data in the SIP voice outbound process are collected and preprocessed, and a standardized outbound state data set is constructed; s2, carrying out gateway comprehensive evaluation on the conversation capability and the stability of the gateway, and dynamically adjusting the priority order of the gateway in a routing path; s3, performing path performance analysis on the real-time performance of the routing path, and correcting the scheduling participation frequency of the corresponding channel in real time; and S4, performing scheduling evaluation on the scheduling state, and updating a scheduling control strategy in real time. The problems that the SIP outbound service lacks an end-to-end intelligent routing closed-loop optimization mechanism, an evolution strategy based on data feedback is not constructed, and the overall routing efficiency and the intelligent evolution capability are seriously limited are solved.

The invention belongs to the technical field of communication networks, and discloses a block chain topology-consensus co-evolution method and system based on reinforcement learning, and the method comprises the steps: collecting the state information of each node in a block chain network, carrying out the standardization processing and multi-dimensional feature extraction of the state information of each node, and obtaining a block chain topology-consensus co-evolution model; mapping into node state feature vectors available for reinforcement learning, and forming node state codes; a reinforcement learning strategy space is constructed according to the node state codes, a topology evolution strategy is dynamically generated by using a strategy iteration method, and topology adaptive evolution of the block chain network is realized; a structural dynamic constraint mechanism is introduced in the reinforcement learning process, and endogenous driving of topological evolution is carried out; calculating the dynamic difference between the potential energy change between the block chain network nodes and the global structure entropy, establishing an evolution constraint function, and dynamically updating the topological evolution strategy parameters; and the elasticity and the expandability of the network structure are effectively improved.

The invention relates to the technical field of computer science and industrial engineering, in particular to a tool workshop scheduling method, which comprises the following steps of: acquiring production characteristics of a current tool workshop, generating an optimal batch scheduling strategy according to the production characteristics of the current tool workshop based on a preset evolutionary strategy, and automatically designing an algorithm by utilizing a preset large model, and calculating the minimum completion time and the maximum completion time of the optimal batch scheduling strategy, and completing tool workshop scheduling according to the minimum completion time and the maximum completion time based on the optimal batch scheduling strategy. Therefore, the problems of high workshop scheduling complexity and the like caused by strong coupling of batch division and working procedure sorting, strict constraint between working procedures and high resource networking degree in workshop scheduling are solved, an automatic algorithm design framework based on a large model is introduced, the expert algorithm design time is shortened, and the workshop scheduling efficiency is improved. Therefore, the efficiency and feasibility of aircraft tooling production scheduling are improved.

The invention discloses an unmanned aerial vehicle subsystem health assessment method and system, and relates to the technical field of unmanned aerial vehicle health management, and the method comprises the steps: obtaining the data of a multi-source sensor of an unmanned aerial vehicle, screening the features strongly correlated with a fault state through a Spearman rank correlation coefficient, and obtaining key monitoring parameters; according to the self-adaptive mutation mechanism, the virtual evolution strategy and the double-objective optimization strategy, an improved multi-objective genetic algorithm optimization model is constructed, then key monitoring parameters are input, and a visual report of a health state assessment result and confidence rating is obtained. According to the method, the problems that traditional single-target optimization neglects the misjudgment rate, the parameter search efficiency is low and the evaluation credibility is insufficient are solved, accurate evaluation is achieved, the evaluation accuracy is improved to 84.86%, the key misjudgment rate is reduced to 0.009%, the convergence speed is improved by 40% compared with a traditional method, the safety and real-time performance of unmanned aerial vehicle health state recognition are remarkably optimized, and the method is suitable for popularization and application. The method is suitable for embedded system deployment.

The invention provides a comprehensive solution for a medical ultrasonic image diagnosis task, which comprises two innovative parts, namely a CAPT parameter efficient fine tuning method based on a convolution adapter and embedded prompt tuning and a model lightweight method based on evolution pruning. Aiming at double challenges of scarcity of data and difficulty in model adaptation in the field of medical ultrasonic images, on one hand, the CAPT method introduces a convolution module into a traditional adapter to enhance the fine-grained feature extraction capability by fusing adapter tuning and prompt tuning mechanisms, and dynamically generates a prompt vector embedded with attention calculation by using adapter learning context information; the adaptability and the small sample generalization ability of the Transform model in an ultrasonic image classification task are obviously improved; on the other hand, aiming at a model edge deployment requirement, designing an evolution pruning algorithm, taking DenseNet-121 as a basic framework, inheriting parent strong neuron connection by adopting an asexual reproduction mechanism, and through a channel importance evaluation method for coupling a BN layer scaling factor and a weight L1 norm and in combination with a sparse evolution strategy guided by environmental constraint, constructing a model edge deployment model. And the classification precision is maintained, and meanwhile, the model parameters and the calculated amount are greatly compressed. The two technologies respectively break through the technical bottlenecks of medical image diagnosis from two dimensions of parameter efficient fine tuning and model structured pruning, the former improves the adaptability of the model field through feature extraction optimization, and the latter balances network lightweight and performance stability by means of an evolutionary algorithm. And an innovative technical path is provided for efficient deployment of an ultrasonic image auxiliary diagnosis system in a data limited scene and an edge computing environment.

The invention belongs to the technical field of machine learning models, particularly relates to a personnel performance evaluation method based on IWOA-SVM, and solves the problems that a traditional support vector machine (SVM) is low in precision, difficult in parameter selection and the like in performance intelligent evaluation. The method comprises the steps that Tent chaotic mapping and a pseudo-opposition learning strategy are utilized to increase the diversity and quality of an initial population, and the whale algorithm (WOA) is prevented from falling into local optimum; the global optimization capability of the WOA is improved by adopting a differential evolution mechanism; a penalty factor and kernel function parameters of the SVM are optimized through an improved whale algorithm (IWOA), and performance evaluation can be effectively carried out while optimal parameters are obtained. According to the method, the whale algorithm can be improved by using Tent chaotic mapping, pseudo-opposition learning and a differential evolution strategy, SVM parameters are searched in a global range, and better model performance is obtained.

The invention discloses an active power distribution network power flow optimization method based on a large language model, and belongs to the field of power system optimization. The method comprises the following steps: firstly, realizing optimal power flow problem modeling according to topology and equipment parameter data of an active power distribution network to be subjected to power flow optimization; designing structured cue words through an optimal power flow problem, and driving a large language model zero sample to generate a diversified heuristic algorithm initial population; and then a thinking chain evolutionary strategy is adopted, calculation errors serve as judgment criteria, another large language model is guided to simulate selection, intersection and mutation operation to achieve heuristic algorithm iterative optimization, output needed by all distributed energy sources of the active power distribution network is obtained based on the heuristic algorithm with the minimum calculation error, and power flow optimization of the active power distribution network is completed. According to the method, the core problems of low design efficiency and high dependence on expert experience of a heuristic algorithm in the complex optimal power flow problem of the active power distribution network are solved, and automatic generation of a high-quality algorithm can be realized for a user-defined problem scene.

The invention relates to a quadruped robot control method, which realizes efficient and stable control of a quadruped robot by combining a basic behavior controller (BBC), a task specific controller (TSC) and an evolutionary strategy simulator optimization method. The BBC learns diverse and natural behavior patterns through a semi-supervised information maximized generation adversarial imitation learning method; the TSC generates a control instruction through privileged learning and a self-supervised robust optimization method in combination with the depth image and proprietary perception information so as to realize efficient control of the quadruped robot; according to the evolutionary strategy simulator optimization method, by combining the ideas of the evolutionary strategy and the generative adversarial network, efficient optimization of simulator parameters is achieved, and the gap between the simulator and the real world is reduced. According to the method, the adaptability and task execution capability of the quadruped robot in a complex environment are remarkably improved.

The invention discloses a virtual power plant scheduling method for evolutionary deep reinforcement learning, and belongs to the technical field of power control. According to the method, a hydrogen-containing virtual power plant low-carbon economic dispatching model is constructed, hydrogen energy gradient utilization is realized through electric hydrogen production, electric-to-gas and hydrogen-to-ammonia technologies, a stepped carbon trading model is improved, a hydrogen energy green certificate trading model is introduced, and an evolutionary soft action device-evaluator (ESAC) algorithm is adopted to carry out optimized dispatching. According to the algorithm, population optimization and deep reinforcement learning of an evolutionary strategy are fused, and the mutation rate is dynamically adjusted through an automatic mutation adjustment mechanism. According to the method, the optimization precision and robustness of virtual power plant scheduling are remarkably improved, the operation cost is effectively reduced, and low-carbon operation of a multi-energy system is promoted.

The invention discloses an intelligent food storage tank internal environment adaptive control system and control method, and belongs to the technical field of artificial intelligence and Internet of Things control. The system specifically comprises a multi-mode sensing module, a feature extraction and preprocessing module, a reinforcement learning module, an instruction adaptive control module and a digital simulation module. The multi-modal sensing module deploys a sensor and an environment adjusting device in an array mode; the feature extraction and preprocessing module carries out filtering, standardization and feature extraction on the data; the reinforcement learning module generates an optimization control strategy by using an algorithm; the instruction self-adaptive control module converts the strategy into an instruction and accurately adjusts parameters of the environment adjusting device; the digital simulation module constructs a digital model for simulation learning and evolution of a strategy agent. Compared with a traditional monitoring system, the method has the technical advantage of generating an optimization strategy, solves the problem of insufficient adaptive control capability caused by a fixed strategy of the traditional monitoring system, and provides a more efficient monitoring service.

The invention belongs to the technical field, and particularly relates to a multi-target particle swarm algorithm applied to active power distribution network energy storage optimization configuration. In combination with typical daily curves of wind energy, photovoltaic energy and user loads, a multi-objective optimization model containing node voltage of a power distribution network, grid-connected point load power fluctuation ratio and energy storage rated capacity configuration is established, an improved multi-objective particle swarm optimization algorithm is provided, and in order to balance diversity and convergence in the iteration process, the optimal optimization model is provided. A double-population coevolution strategy is adopted, particles are divided into a convergence population and a diversity population according to a convergence distance, iterative evolution is carried out, and the problem that an algorithm is prone to falling into a local optimal solution is solved. A dynamic inertia weight updating rule based on Euclidean distance optimal similarity is used for solving, so that the particles have better global search capability and local search capability in the optimization process. According to the method, the solving efficiency and precision of the optimization algorithm of the energy storage system of the power distribution network are improved, and a more reasonable optimization scheme is obtained.

The invention relates to a robot simulator optimization method, which realizes efficient optimization of simulator parameters by combining an evolutionary strategy and a generative adversarial imitation learning thought. According to the method, through optimization of simulator parameters, the difference between the simulator and the real world is reduced, and the control performance of a robot control strategy in a real environment is improved. The method specifically comprises the steps of parameter initialization, data acquisition, adversarial training, parameter updating, iterative optimization and the like. A new parameter sample is generated through parameter selection, variation and crossover operation of an evolutionary strategy, and parameters of the simulator are optimized through adversarial training, so that the simulator is most similar to the real world.

The invention discloses a development management system and method for an API interface, and relates to the technical field of software engineering. The system comprises: an intention understanding and design engine, which analyzes a multi-modal service demand into a structured API development task; the agents collaboratively develop a network, and the multiple AI agents are dispatched to generate API specifications, codes, test cases and deployment configurations in parallel; the API ecological dynamic map construction module is used for automatically constructing and updating a dynamic map of dependency and data flow direction between APIs based on a generated product; a continuous learning and evolution engine analyzes the atlas and operation data to identify optimization points and generate or execute evolution policies. All the modules form a closed loop, and output of the evolution engine is fed back to the intention understanding engine to optimize subsequent design. The corresponding method comprises the steps of demand analysis, intelligent collaboration, atlas construction and closed-loop optimization. According to the method, automatic development, intelligent collaboration and continuous architecture optimization of the API are realized, and the development efficiency and the system maintainability are improved.

The invention discloses an image super-resolution reconstruction method based on a double-domain chimeric attention mechanism, and belongs to the technical field of image super-resolution reconstruction. The method comprises the steps that an image is collected and preprocessed; constructing an image processing model; the image processing model is trained by adopting the preprocessed image, a self-adaptive attention distribution strategy is adopted in training, local attention weight is dynamically adjusted, an edge perception multi-constraint loss function is adopted, overall reconstruction and edge quality are dynamically coordinated, and detail definition and contour naturalness of a reconstructed image are improved; and carrying out image super-resolution reconstruction by adopting the trained image processing model. According to the method, the ViT module based on the double-domain chimeric attention mechanism is embedded into the bottleneck layer of the U-Net network, the edge perception multi-constraint loss function based on the gradient alignment course evolution strategy is adopted, and the obtained model has good image super-resolution reconstruction performance.

The invention discloses a linear guide rail lightweight optimization design method and device, a medium and a program product, and the method comprises the steps: (1) constructing a lightweight optimization mathematical model on the basis of a linear guide rail structure and load characteristics under the condition of satisfying frictional resistance and first-order modal constraints; (2) quantizing a parameter effect based on a PCE model and constructing an effect space to generate a population; (3) designing an evolutionary strategy guided by a bidirectional information individual; (4) constructing a double-layer Stacking integration model based on DBSCAN clustering, and screening an optimal filial generation guide rail; and (5) if the current optimal filial generation guide rail meets the optimization requirement, outputting an optimal guide rail parameter value, otherwise, returning to the step (3) until the optimization requirement is met. According to the method, the weight of the guide rail can be minimized for the effect space of high-effect guide rail parameters, transition optimization for redundancy and low-effect parameters is avoided, and better lightweight performance is achieved.

The invention discloses an insulation defect feature detection method and system based on a switch cabinet, and relates to the field of insulation defect feature detection, and the method comprises the steps: installing a sensor array in the switch cabinet, collecting an original data stream of a multi-modal space-time physical field, and generating a reconstructed four-dimensional space-time field tensor through a multi-modal space-time cooperative sensing network; based on the four-dimensional space-time field tensor, generating an enhanced sample set conforming to a physical rule through physical regularization; generating an optimized detection parameter combination through gradient-evolution collaboration based on the enhanced sample set conforming to the physical law; digital twin enhanced closed-loop adaptive optimization is adopted, and the optimized detection parameter combination is converted into verified stable parameter configuration; according to the verified stable parameter configuration, real-time optimization parameters are obtained through embedded real-time acceleration optimization and solidification; the detection parameters are effectively adjusted and optimized by adopting a multi-target covariance evolutionary strategy to optimize a parameter combination process based on a space-time gradient characteristic spectrum.

The invention relates to the technical field of artificial intelligence question answering systems, and discloses an interactive question answering system based on multi-model parallel reasoning. The system comprises an interactive interface module, a query cognition construction module, a hierarchical index module, a multi-model parallel reasoning module, an interactive answer synthesis module and a tool calling adaptation module. The system constructs query cognition mapping by deeply analyzing a time sequence query stream containing texts and media of a user, and drives dynamic evolution of hierarchical indexes according to the query cognition mapping. The multi-model parallel reasoning is based on evolution strategy coordination processing, and knowledge slices with state vectors are generated. And finally, synthesizing a natural language answer attached with the interaction intention unit, and adapting the natural language answer to an external tool calling instruction. According to the system, the cognition and retrieval precision under complex query is improved through intention-driven dynamic indexing, and automatic closed loop from information question answering to business operation is realized through executable answers.

The invention discloses a user-side shared energy storage optimal configuration method considering an evolutionary game, and the method comprises the steps: obtaining typical power load curves of peak-facing type, peak-flattening type and peak-avoiding type users; according to the typical electrical load curve, constructing an industrial user evolution strategy set, and establishing a payment income model corresponding to a shared energy storage joint co-construction strategy and a self-construction energy storage strategy; building a user participation shared energy storage evolution game model, modeling the strategy evolution process of each user into a replicator dynamic equation, and realizing discretization processing; and solving evolutionary game equilibrium based on an evolutionary iterative algorithm, optimizing user-side shared energy storage configuration in combination with an improved grey wolf algorithm, determining a planning and operation scheduling strategy of each user, and obtaining the optimal investment construction capacity of shared energy storage. According to the shared energy storage optimal configuration method, the influence of individual behavior differences and finite rationality factors is considered, the determined optimal shared energy storage capacity can optimize the investment cost on the basis of reducing a large amount of peak demand electric charge of a user, and resource waste is avoided.

The invention discloses a saline-alkali soil water-salt-fertilizer real-time monitoring system and method based on the Internet of Things, and relates to the technical field of saline-alkali soil monitoring. Multi-parameter sensor nodes are arranged in a preset area to collect soil salinity, moisture, conductivity, pH value and ground temperature information; acquiring a remote sensing image, terrain elevation and land utilization type data, and performing preprocessing and spatial registration; based on the spatial position relation, the hydrological connectivity and the irrigation and drainage structure, establishing a spatial graph structure required by graph neural network input; deploying a model on the constructed graph, and predicting the future salinity trend or saline-alkali risk grade of each monitoring unit; utilizing adjacent node features and an edge weight propagation mechanism to realize prediction extrapolation of a data sparse region; based on a prediction result and an agronomic rule, generating a multi-objective optimization regulation and control scheme through an evolutionary strategy algorithm; and displaying the prediction map, the risk map and the regulation and control suggestions, and triggering early warning and control linkage when the threshold value exceeds the limit.

The invention discloses a social media harmful information identification method and device based on large-small model collaborative optimization, and the method comprises the steps: firstly, carrying out the feature analysis of social media information through an LLM, and automatically matching an optimal professional small model; secondly, an automatic deployment engine is utilized, model deployment codes are generated through LLM, and localized deployment is completed; then, constructing a dynamic code generation unit, automatically generating a code and a fine tuning code for calling a professional small model to identify social media harmful information according to the model ID and deployment parameters, and performing grammar verification, performance evaluation and safety detection on the generated code by adopting LLM; further, a social media information pipeline is designed, and functions of data slice input, recognition result classification, challenging sample screening and fine tuning data set construction are included; and finally, implementing a model persistent evolution strategy, and completing model version upgrading by iteratively executing a recognition-screening-fine tuning process. Through a collaborative decision-making mechanism of the LLM and the professional small model, end-to-end automation of a harmful information identification process is realized, the manual intervention cost is remarkably reduced and the identification efficiency is improved on the premise of ensuring the identification quality, and the method is particularly suitable for a large-scale harmful information identification scene of multi-field heterogeneous data.