415 results about "Decision matrix" patented technology

The invention provides an infrared thermal imaging building facade defect intelligent diagnosis method based on multi-modal fusion, and relates to the technical field of building detection.The method comprises the steps that infrared thermal imaging, visible light images and three-dimensional point cloud data are synchronously collected to construct a multi-modal data set; segmenting a hot spot region by adopting an improved morphological watershed algorithm and extracting contour and temperature features; recognizing a surface crack and peeling area based on a double-branch attention network to generate a texture defect feature map; curvature distribution and thermal deformation gradient are calculated through space registration constrained by a heat conduction equation; multi-source features are fused to calculate a hot spot form dispersion TSMD and a structure risk quantification factor SRQF; constructing a defect risk decision matrix to output defect types, positions and risk levels; and superposing the diagnosis result to a BIM model to generate a three-dimensional visual report and predicting a thermodynamic evolution trend. The multi-modal data collaborative analysis is realized, the defect risk is accurately quantified, and the problems of poor anti-interference performance, inaccurate segmentation and large registration error of a traditional method are solved.

The invention provides a multi-source heterogeneous distributed computing power fusion scheduling method and system, and the method comprises the steps: carrying out the multi-dimensional collection and preprocessing of heterogeneous scheduling source data, generating a scheduling joint data set, carrying out the key demand prediction processing of a task set based on a preset quantum channel topology, generating a key pre-distribution matrix, and carrying out the key pre-distribution matrix, and generating a real-time task queue according to a task set of the scheduling joint data set, and performing multi-target matching degree calculation processing on the key pre-distribution matrix and the real-time task queue based on a dynamic priority quantification model to generate a distribution decision matrix. Then adaptive key supplement and migration path optimization processing are performed on the allocation decision matrix to obtain a migration task set, and finally hidden node resource prediction and preset quantum channel topology updating are performed on the migration task set, so that the rationality of key allocation is improved, the problem of compatible conflicts of resource scheduling is solved, and the resource scheduling efficiency is improved. Therefore, the task migration success rate is improved.

The invention discloses a multi-source heterogeneous data fusion pipe network intelligent scheduling decision-making system, which comprises a multi-modal data acquisition cabin module, a space-time alignment fusion center module, a digital twin deduction cabin module, a self-adaptive decision-making matrix module, an elastic execution feedback chain module and a credibility tracing platform module, the multi-modal data acquisition cabin module comprises a heterogeneous protocol analysis unit, an unstructured processing engine and an edge preprocessing mechanism, and the space-time alignment fusion center module comprises a space-time reference mapping engine, a federal learning cleaning tower and a dynamic semantic association library. The problem that data of a traditional system cannot be effectively integrated is solved, fusion of multi-source heterogeneous data is achieved, data islands are broken, the response speed is increased, the dynamic response capacity is enhanced, in addition, decision making efficiency and accuracy can be improved, decision making intellectualization can be enhanced, optimal configuration of pipe network energy efficiency can be achieved, and the system is suitable for popularization and application. And the energy efficiency of the pipe network is greatly optimized.

The invention relates to the technical field of charging pile group load intelligent regulation and control, and particularly discloses a charging pile group load intelligent regulation and control method and system based on dynamic power equalization, and the method comprises the steps: collecting the oil temperature of a transformer in real time, calculating a total output power threshold value, and correcting the actual output power of a charging pile through combining the line loss and the equipment aging degree; a multi-dimensional load regulation and control decision matrix including user priority, equipment health degree and power regulation sensitivity is established, a dynamic power strategy is allocated through matrix weight, power allocation is inclined to high-priority users and health equipment, emergency power allocation and progressive readjustment during newly-added demands are supported, and the power regulation and control efficiency is improved. Impact of sudden power change on a power grid is avoided, system stability is ensured when newly added loads are accessed, refined intelligent regulation and control of loads of the charging pile group are finally realized, transformer safety, charging efficiency and user experience are improved, and power grid stability and resource optimization configuration are ensured.

The invention discloses a fine-grained access control method and system based on risk identification, and belongs to the technical field of information security. According to the method, user subject attributes, behavior attributes and system environment attribute information are collected in real time, a standardized decision matrix is constructed, an interval type-2 fuzzy set (IT2FS) is used for conducting fuzzy modeling on the attributes, and an upper membership matrix and a lower membership matrix are generated. And calculating the dynamic weight of the attribute index in combination with a CRITIC method, introducing a time decay factor to dynamically correct a risk score through an improved TOPSIS method, calculating the Euclidean distance between an access request and a positive / negative ideal solution, and generating a normalized risk closeness degree. And based on the risk score and a preset threshold value, dynamically matching a hierarchical permission strategy, and adopting a static rule and a priority coverage mechanism to eliminate permission conflicts. According to the method, multi-dimensional risk assessment and dynamic weight adjustment are fused, the problems of insufficient real-time performance, subjective weight dependence and weak uncertainty processing capability in a traditional method are solved, the accuracy and security of access control are remarkably improved, and the method is suitable for scenes with high security requirements such as cloud computing and finance.

The invention discloses a grassroots society digital governance method and system, and the method comprises the steps: collecting multi-source heterogeneous data in real time through an Internet of Things sensing network disposed in a grassroots community, and generating a standardized multi-mode sensing data flow; based on the multi-modal perception data stream, outputting a time-space associated cleaned data set; inputting the cleaned data set into a multi-scale space-time encoder, and generating a feature tensor containing regional hotspot distribution and a risk propagation path; based on the feature tensor, constructing a dynamic risk knowledge graph, and outputting a decision matrix including a risk level and an optimal intervention path; inputting the decision matrix into a strategy optimization engine to obtain a hierarchical governance instruction set; and on the basis of real-time governance feedback data after the hierarchical governance instruction set is executed, a conflict instruction in the strategy chain is autonomously corrected through a fuzzy reinforcement learning algorithm. By utilizing the embodiment of the invention, an efficient, intelligent and traceable digital governance scheme can be realized, so that the social governance efficiency and the service quality are improved.

The invention provides a machine vision defect real-time detection and classification method and system based on deep learning, and relates to the field of machine vision detection.The method comprises the steps that regional enhancement weights are determined by calculating local entropy and gradient direction consistency, and regional self-adaptive enhancement is carried out; establishing a feature transfer sequence and progressively fusing features; generating and correcting a defect area probability distribution diagram; and constructing a dynamic decision matrix to calculate a comprehensive score for defect grading. According to the method, the defect detection accuracy under a complex background can be improved, false detection and missing detection are reduced, and real-time defect positioning and accurate classification are realized.

The invention relates to the technical field of intelligent transportation control, in particular to a tomato transportation speed self-adaptive adjustment method based on path road condition feedback, which comprises the following steps: acquiring road images, vibration waveforms and altitude data through a multi-source sensing unit, and constructing real-time road condition information; identifying a driving mode and extracting a corresponding bumping parameter; detecting the maturity grade of the tomato by combining multispectrum and thermal imaging, and querying a maturity-compressive strength corresponding table to calculate a cargo damage threshold value; constructing a dynamic mapping model under multiple working conditions, predicting vibration response and converting the vibration response into equivalent pressure; comparing the equivalent pressure with a damage threshold value to obtain a safety margin, constructing a speed adjustment decision tree and generating a maximum allowable speed value of each road section; and dynamically generating a segmented variable-speed control instruction based on the speed decision matrix, and controlling a throttle valve and a braking system to cooperatively change speed. The method has the advantages of accurate working condition identification, dynamic fruit adaptation, closed-loop speed regulation and control and the like, and is suitable for fine speed control of a high-sensitivity fruit and vegetable transportation scene.

The invention relates to the technical field of data analysis, in particular to a road traffic intelligent operation and maintenance method and system based on multi-source data fusion, and the method comprises the steps: constructing a three-dimensional model through a credibility calculation module by integrating three types of factors, namely a road environment, an equipment state and historical verification, generating a dynamically updated credibility index, and correcting a weight in real time based on feedback; the problem that the reliability of the multi-source data fluctuates dynamically due to the influence of environmental interference, equipment aging and historical deviation is solved; the road feature conflict resolution module maps to feature dimensions corresponding to road topology conflict features through dynamic credibility indexes, constructs a road conflict decision matrix, and fuses and generates a road anomaly decision set with credible labels according to the feature dimensions; the resource scheduling module is used for dividing three-level response areas based on credible indexes, executing accurate scheduling of triple constraints in combination with device priorities and credible labels and generating a resource-decision association graph, and self-adaptive optimal configuration of limited maintenance resources according to data reliability is achieved.

The invention relates to the technical field of communication, in particular to a dynamic priority dual-mode communication fault-tolerant switching method and equipment, and aims to solve the problems of communication interruption and service quality reduction when a main link is degraded in a complex electromagnetic environment. According to the method, a dynamic priority evaluation model and a dual-mode protocol cooperation mechanism are constructed, throughput, bit error rate, delay jitter, task semantic priority and aging constraint data of a main link and a standby link are collected in real time, a priority weight and a communication mode decision matrix are generated through combined modeling, an atomization switching instruction is executed according to the priority weight and the communication mode decision matrix, and a communication mode is switched. And completing path reconstruction and resource redistribution. The system further introduces link health prediction, a resource reservation pool and an online learning feedback loop, and supports fault pre-judgment, key task preemption and model adaptive optimization. According to the method, the limitation of a static threshold is broken through, the task semantics and channel state joint scheduling is realized, and the communication reliability, the service continuity and the intelligent fault-tolerant capability of a distributed system in a high-risk scene are remarkably improved.

The invention provides a multi-agent cooperative processing system and method for multi-scene legal complaint consultation, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving a legal or complaint consultation text inputted by a user, and generating structured consultation request data; automatically generating an evidence obtaining template, and forming a standardized evidence obtaining data packet; constructing a demonstration tree and outputting a multi-scheme decision matrix; performing multi-objective optimization by combining the success rate, the timeliness, the cost and the regional qualification index, and outputting a comprehensive recommendation result; generating a knowledge unit set, and updating a regulation index and agent prompt template library; predicting a re-complaint risk and generating a remedy and optimization suggestion; and outputting review result data, and reversely updating the review result data to the agent configuration strategy in the step of the knowledge construction module. According to the method and the device, the technical targets of multi-agent cooperative processing and dynamic optimization management in the whole legal complaint consultation process can be realized, and the technical effects of improving consultation processing efficiency, enhancing scheme recommendation accuracy, reducing manual participation cost and ensuring data compliance and risk controllability are achieved.

The invention relates to the technical field of network resource allocation, and discloses a network node resource dynamic allocation method and system. The method comprises the following steps: collecting multi-dimensional resource use data of network nodes and executing preprocessing to obtain a standardized resource monitoring matrix and a topological entropy weight matrix; performing nonlinear topology perception calculation to obtain a resource demand prediction matrix; based on the resource demand prediction matrix, performing sectional progressive allocation decision on the network node resources to obtain a first resource allocation decision matrix; performing chaos disturbance fine tuning on the first resource allocation decision matrix to obtain a second resource allocation decision matrix and a resource locking time table; and performing network node resource multi-level scheduling based on the second resource allocation decision matrix and the resource locking time table, and generating a resource execution result log and performance monitoring data. According to the invention, the prediction accuracy of the real resource demand of the network node is improved, and a differentiated, multi-level and smooth transition resource scheduling execution strategy is realized.

The invention belongs to the field of data storage, and discloses a frequency access data storage migration method and device for big data, and the method comprises the steps: obtaining a data access log, carrying out the preprocessing of the data access log, and obtaining a time window statistical matrix; carrying out timeliness attenuation weighting calculation on a plurality of data access times in the time window statistical matrix to obtain a weighted access frequency vector; obtaining a multi-dimensional feature matrix based on the weighted access frequency vector; clustering the feature vector of each time window slice in the multi-dimensional feature matrix through a Gaussian mixture model to obtain a clustering tag vector; inputting the clustering label vector into an access frequency prediction model to obtain an access frequency prediction value of the data in a future preset time step; the migration decision matrix is determined based on the access frequency predicted value and the data storage cost parameter, data migration is carried out based on the migration decision matrix, the data migration complexity can be reduced, and the access speed and the storage cost are balanced.

The invention relates to the technical field of industrial platform data analysis, in particular to a renewable resource recovery data management system based on the Internet of Things, which comprises the steps of synchronously acquiring weight, spectrum and microwave characteristic data of a tested resource through a data acquisition module, executing moisture weight decoupling operation by utilizing a resource matching module, and performing data analysis; then, an inventory evolution module tracks performance loss of resources in real time by using an evolution model of an integrated long and short-term memory network, generates a resource attenuation weight, and constructs a two-dimensional decision matrix containing scheduling priority and preprocessing strength grade instructions in combination with real-time inventory saturation; and finally, the clearance scheduling module executes dynamic pruning and bidirectional optimization through a resource scheduling model, accurately allocates the loading share and the access sequence of each node, and generates a dynamic instruction set containing a delivery sequence. According to the method, feeding homogenization is realized through industrial data multi-dimensional collaborative analysis.

The invention discloses an old people safety monitoring method and equipment based on multi-modal sensor fusion, which are applied to the technical field of data processing, and the method comprises the steps: collecting multi-modal monitoring, environment state and equipment operation data, and carrying out synchronous correction, feature extraction and edge end encryption caching to generate a standardized multi-dimensional feature vector; by means of a dynamic weight multi-modal fusion engine, in combination with adaptive weight distribution and scene association analysis, suspected tumble events are recognized, and then the real tumble situation is confirmed through AI agent voice interaction. Based on an emergency linkage decision matrix, a priority notification and a home custom control rule are fused, an emergency linkage scheme is generated, and finally, based on an edge-cloud collaboration architecture and an adaptive adjustment strategy, the security dynamic protection and continuous optimization of the old people are realized, and the home security of the old people is comprehensively guaranteed.

The invention discloses a security check door security check process optimization scheduling system and method based on big data, and belongs to the technical field of intelligent security check, a whole security check area is divided into a plurality of functional areas and mapped into network nodes according to security check process links and physical space distribution, directed edges among the nodes represent passenger flow paths, and the flow paths of passengers are distributed in the network nodes. A weight matrix of edges is calculated through historical flow data, and a security check area network topology model is constructed; fusing ticket business, historical security check and real-time sensor data, constructing a load evaluation model, and calculating a node load index and an influence conduction coefficient; based on passenger ticket business time and historical behavior records, establishing a time urgency index and risk level model, and forming a two-dimensional decision matrix to dynamically divide priorities; constructing and training a congestion propagation model, predicting a future congestion path in combination with priority distribution, and identifying bottleneck nodes; and according to a prediction result, cooperatively implementing a grooming strategy from four dimensions of personnel, channels, equipment and processes.

The invention discloses a drilling construction intelligent decision support and risk early warning method, device and equipment, and the method comprises the steps: collecting drilling sound wave response data, carrying out harmonic analysis to recognize a reservoir resonance node, and constructing a reservoir energy conduction network; a fluctuation propagation path is tracked based on an energy conduction network, and a construction risk area is identified through stress wave spectrum features; porosity and permeability data are extracted for phase difference analysis, a seepage-construction mismatch factor is generated, and a construction optimization window is actively generated; constructing a geological potential energy gradient field to determine an overflow influence range, and performing tensor coupling on multi-dimensional risk factors to generate a three-dimensional construction decision matrix; an optimal construction scheme is generated through energy minimization and risk-efficiency dynamic balance processing; construction parameter response changes are monitored in real time, abnormal parameter combination symptoms are recognized, a grading risk early warning instruction is generated, and intelligent decision support and risk early warning of drilling construction are achieved.

The invention relates to the technical field of tunnel engineering automation and intelligent control, and discloses a TBM tunneling parameter intelligent optimization decision-making system based on an LSTM network, and the system comprises a data collection and preprocessing module which obtains external data and outputs a tunneling parameter sequence; the probabilistic tunneling trend prediction module is used for outputting a prediction expected value and prediction uncertainty; the prospective geological precursor sensing module is used for matching and identifying known risks and outputting alarm events; and determining an optimal tunneling mode by the dynamic risk avoidance decision matrix. When the prediction uncertainty is too high, activating the prospective template driven by the uncertainty to excavate a new precursor template and update the template library; meanwhile, the decision-efficiency relevance evaluation and strategy self-optimization engine optimizes the decision rule according to the actual tunneling efficiency. According to the method, decision making is carried out through quantitative risk prediction and fusion of multi-source information, and a double learning closed loop of knowledge discovery and strategy optimization is established, so that the reliability, the adaptability and the long-term efficiency of system decision making are remarkably improved.

The invention discloses an aspect emotion triple extraction method for a large language model annotation data set, and relates to the technical field of natural language processing, and the method comprises the steps: carrying out the initial triple labeling of a standardized text data set, calculating a cognitive bias index based on a labeling reference set, and generating a data set with a bias label; a dynamic attenuation suppression method is adopted to generate a bias mask matrix, exponential mask enhancement is performed on samples exceeding a preset bias threshold value, and bias mask enhancement representation is obtained; inputting the bias mask enhanced representation into a differentiable grammar parser, calculating a grammar dependency matrix by using an attention mechanism, optimizing a topological structure of the grammar dependency matrix in combination with structural entropy loss, and generating a boundary judgment matrix; and extracting candidate triple embedding based on a boundary judgment matrix, calculating a contradiction coefficient by using a quantum emotion entangled state, and generating a correction triple set. According to the method, the accuracy and availability of emotion recognition results in the fields of medical evaluation and the like are enhanced.

The invention discloses a multi-modal interaction method and interaction system applied to an intelligent robot. The method comprises the following steps: collecting a scene image and processing the scene image into a three-dimensional point cloud and a two-dimensional texture feature; the Gemini Robotics-ER model is used for extracting features, and the vision-language-action model is used for analyzing a language instruction into a sequence capable of being recognized by a machine; and fusing the features to generate an interactive decision matrix, planning a trajectory, calculating kinetic parameters, driving the robot to execute actions and feeding back in real time. The system comprises a multispectral visual information acquisition and preprocessing unit, a Gemini Robotics-ER model processing unit, a natural language instruction analysis unit, a vision-language-action cooperative processing unit, a trajectory planning and dynamics calculation unit and a motion control and feedback unit, and all the units work cooperatively. According to the method and the system, through multi-modal fusion and closed-loop control, interaction accuracy and real-time performance are improved, and industrial scene requirements are met.

The invention discloses a hydropower station income risk measurement method based on hydraulic energy value, which comprises the following steps: S1, constructing a hydraulic energy value dynamic evaluation model, calculating the hydraulic energy available amount under different space-time scenes by combining a distributed hydrological model, converting the hydraulic energy available amount into an economic value, and obtaining a dynamic hydraulic energy value; s2, establishing a multi-risk factor coupling network, and calculating a synergistic effect weight between risk factors; s3, constructing an income risk dynamic prediction model, updating and predicting a power generation income probability distribution curve in a future preset time period in real time, and identifying a key risk source; s4, constructing a risk-income tradeoff decision matrix through a prediction result and a key risk source output by the income risk dynamic prediction model, and generating income optimization schemes under different risk coping strategies; and S5, displaying the dynamic water energy value, the income risk prediction result and the income optimization scheme by using a visual interface. Accurate evaluation of the dynamic water energy value and real-time prediction of the power generation income risk are achieved.

The invention provides a hybrid model fault early warning method and system based on time sequence prediction and fuzzy logic, and the method comprises the steps: collecting operation and maintenance data of equipment in a continuous operation period, constructing an equipment state feature set, carrying out the feature correlation analysis of the equipment state feature set, generating an equipment state potential vector which reflects a dynamic coupling relation between parameters, and carrying out the fault early warning of a hybrid model. Calling a pre-trained fuzzy logic reasoning model to carry out fuzzy rule matching, and generating a fuzzy state set containing a multi-dimensional fuzzy subset; performing space-time correlation processing on the fuzzy state set to generate a multi-dimensional decision cloud picture, and performing spatial reconstruction on the multi-dimensional decision cloud picture through a quantization weight distribution mechanism to obtain an optimized decision matrix; and generating a fault early warning signal containing a fault early warning level and fault position positioning information based on the confidence distribution characteristics corresponding to the fault types. According to the invention, the accuracy and timeliness of fault early warning can be improved, and reliable decision support is provided for equipment operation and maintenance management.

The invention discloses a multi-scheduling scheme decision-making method and device based on hesitant fuzzy information and a multi-attribute group decision-making theory in the technical field of power grid power generation optimization scheduling. The multi-scheduling scheme decision-making method comprises the following steps: determining a plurality of attribute indexes influencing a power grid power generation scheduling scheme according to the power grid power generation scheduling scheme; performing quantitative processing on each expert evaluation information matrix based on a preset computable hesitant fuzzy language term set to obtain a quantitative data decision matrix; calculating the positive separation degree and the negative separation degree of quantized data corresponding to each power grid power generation scheduling scheme based on the positive ideal point and the negative ideal point of each quantized data decision matrix; and calculating the progress of each power grid power generation scheduling scheme, and selecting the power grid power generation scheduling scheme corresponding to the maximum progress as the optimal scheduling scheme. The method has the advantages that the positive ideal solution and the negative ideal solution can be determined according to the group decision evaluation information, the relative schedule of each scheduling scheme is calculated, the evaluation scheduling schemes are sorted and preferentially selected, and the problem that the decision schemes are difficult to achieve consistency is effectively solved.

The invention relates to the technical field of vehicle control, and discloses a parking start-stop battery intelligent module management system, which comprises a data acquisition and preprocessing module, a driving intention inference module, a self-adaptive transient power capability evaluation module and a multi-dimensional fusion decision and control module, discrete driving intention states such as congestion crawling and intersection waiting are recognized through a finite state machine; according to the intention state, adaptively selecting an evaluation sub-model from an evaluation sub-model library so as to evaluate the transient power capability of the battery, and outputting a transient power capability score and a corresponding confidence coefficient; and the system fuses the driving intention, the transient power capability score and the confidence coefficient, corrects logic through the preliminary decision matrix and the confidence coefficient, performs rechecking in combination with the whole vehicle level constraint condition, and generates and issues a final start-stop control instruction. According to the method, the problems of single decision and poor situation adaptability in the prior art are solved, the intelligence and reliability of start-stop decision are remarkably improved, and the driving experience is optimized.

The invention relates to the technical field of intelligent driving, and particularly discloses a layered dangerous lane changing intervention method and system based on multi-mode intention recognition, and the method comprises the steps: obtaining a multi-mode intention signal of a driver in real time; judging the current lane changing intention state of the driver based on the multi-mode intention signal; environment information behind the side of the vehicle is detected in real time, and the collision risk level of current lane changing is determined based on the environment information; inputting the lane changing intention state and the collision risk level into a pre-stored decision matrix for matching, and outputting a corresponding hierarchical intervention strategy; the decision matrix comprises intervention strategies corresponding to combinations of different lane changing intention states and different collision risk levels, and early warning and / or vehicle control actions corresponding to the layered intervention strategies are executed. The method solves the core problem that in the prior art, intentional lane changing and unconscious dangerous deviation of a driver cannot be effectively distinguished, and consequently false alarm or untimely intervention is caused.

The invention relates to an unmanned aerial vehicle group task allocation and obstacle avoidance method based on a Hungary-APF model. The method comprises the following steps: constructing a task allocation model according to an unmanned aerial vehicle task allocation strategy and a cost value of completing a task by an unmanned aerial vehicle; a cost value matrix is constructed according to cost values of all unmanned aerial vehicles in the unmanned aerial vehicle group for completing tasks, and a decision matrix is constructed according to task allocation strategies of all unmanned aerial vehicles in the unmanned aerial vehicle group; and taking the decision matrix as the input of an unmanned aerial vehicle task allocation strategy of the task allocation model, taking the cost value matrix as the input of the cost value, and solving the task allocation model by adopting a Hungary algorithm to obtain an optimal unmanned aerial vehicle task allocation result. Constructing an APF obstacle avoidance model, wherein the APF obstacle avoidance model comprises static repulsive force, dynamic repulsive force and gravitational force; and inputting the task allocation result into the APF obstacle avoidance model, and solving to obtain a flight path planning result of obstacle avoidance of each unmanned aerial vehicle in the unmanned aerial vehicle group. By adopting the method, the cargo distribution efficiency of the unmanned aerial vehicle group and the obstacle avoidance path precision can be effectively improved.

The invention belongs to the technical field of medicine inventory management, and discloses a Western medicine intelligent inventory optimization and automatic replenishment decision-making method and a Western medicine intelligent inventory optimization and automatic replenishment decision-making system. Comprising the steps of collecting environment data, inventory information and historical inventory consumption data of inventory drugs, and integrating the environment data and the inventory information to obtain a health degree index of each drug; based on the drug health degree index and the consumption prediction result, generating a replenishment decision matrix, and outputting replenishment opportunity, replenishment amount and replenishment priority; in combination with an operation audit result and inventory area division, differential inventory management scheme configuration is realized; and after external information is obtained, a replenishment strategy is dynamically adjusted, and a target inventory optimization decision is formed. According to the method, accurate evaluation of the inventory state and intelligent decision of replenishment response are realized, and the safety, efficiency and refinement level of medicine inventory management are improved.

The embodiment of the invention relates to the technical field of large model data analysis, and discloses a large model evolution multi-agent investment decision matrix system. The investment Transform module is used for acquiring financial data and performing feature extraction and feature fusion on the financial data in combination with a context learning enhancement function and a financial domain knowledge enhancement function; the interpretability analysis module is used for acquiring the feature representation in the investment Transform module and carrying out feature relation mapping and interpretability analysis; the multi-agent decision-making module is used for carrying out collaborative decision-making through multiple agents; the optimization module is used for providing interpretation optimization for the interpretability analysis module and providing strategy optimization for the multi-agent decision-making module; and the knowledge base module is used for providing an investment template for the investment Transformer module, providing causal relationship knowledge for the interpretability analysis module and providing rule constraints for the multi-agent decision-making module. The technical problem of investment decision analysis can be at least solved.

The invention relates to a method for predicting the corrosion rate of a natural gas pipeline, in particular to the field of natural gas pipeline corrosion prediction.The high-precision dynamic early warning is achieved through the four-step cooperative technology, firstly, visible light and radar data are fused to generate a three-dimensional corrosion base film fully covering the pipeline, and blind areas caused by the complex environment are effectively eliminated; secondly, speculating corrosion probability distribution of a shielding area based on a physical constraint generative adversarial network, and solving a hidden area prediction problem; then, in combination with the stress field and historical data, deducing a space-time diffusion path of corrosion through a graph neural network, and outputting a future corrosion thermodynamic diagram; and finally, dynamically adjusting model parameters according to actually measured data to form a corrosion risk decision matrix of closed-loop optimization, thereby realizing the transformation of pipeline corrosion from passive protection to intelligent prevention in a breakthrough manner.

The invention discloses a local power distribution method for an energy storage power station. The method comprises the following steps: acquiring and preprocessing data information of a battery module of a target energy storage power station; performing clustering analysis on the battery modules of the target energy storage power station based on a DBSCAN algorithm; according to a clustering analysis result, constructing a decision matrix according to the charge state, the health state and the residual capacity of the battery module, and calculating the priority of each clustered battery module cluster in combination with an entropy weight method; and constructing a local power distribution model of the target energy storage power station by taking the loss, the aging cost, the charge state balance degree and power distribution optimization based on the priority of the battery module as targets, solving the local power distribution model, and completing local power distribution of the target energy storage power station according to a solving result. The invention also discloses a system for realizing the local power distribution method of the energy storage power station. According to the method, local power distribution of the energy storage power station can be achieved, the characteristics of the battery modules are considered, and the scheme is higher in reliability and better in safety.