98 results about "Decision-making models" patented technology

The invention provides a perception collaborative decision-making method and system based on multi-modal heterogeneous data fusion, and relates to the technical field of artificial intelligence, and the method comprises the steps: inputting a global environment situation perception graph into a pre-trained multi-target collaborative decision-making model; the multi-target collaborative decision-making model forms a multi-target decision-making feature set by analyzing the resource entities and the incidence relation in the graph; based on the multi-target decision feature set, decision optimization is carried out to obtain a comprehensive collaborative scheduling scheme; performing instruction analysis and packaging on the comprehensive collaborative scheduling scheme to obtain an executable instruction sequence; and issuing the executable instruction sequence to a corresponding decision node and a control terminal in parallel through a distributed communication architecture to complete real-time scheduling of resources and collaborative issuing of control instructions. According to the invention, by constructing a linkage mechanism of multi-modal data fusion, dynamic environment perception and collaborative decision execution, intelligent perception and quick response to a complex environment are realized.

The invention discloses a coordinated control method and system for comprehensive energy multi-agent coordinated group control and autonomous decision making. The method comprises the following steps: establishing a relaxation strategy of an agent corresponding to a distributed power supply; the main coordinator iteratively solves to determine a global coordination signal according to the global operation data of the integrated energy system and the operation data of each agent by taking the lowest total cost, the highest system energy efficiency, the minimum carbon emission and the minimum global penalty coefficient meeting the global relaxation constraint as a relaxation global optimization target; the minimum operation cost of each intelligent agent, the minimum response deviation to a global coordination signal and the minimum deviation between an actual state and a reference state are taken as control targets; establishing an electricity price autonomous decision-making model of each agent and a response power boundary autonomous decision-making model for a global coordination signal; and based on the control target of each agent, the electricity price autonomous decision-making model and the response power boundary autonomous decision-making model, predicting to obtain a control target value of each agent, and realizing balance between a global optimization target and local autonomy.

The invention provides a bridge group maintenance priority dynamic decision-making method and device based on reinforcement learning, and relates to the technical field of bridge intelligent maintenance. The method comprises the following steps: constructing a topological structure of a bridge network and a road; defining a state space, a maintenance action space and a state transition matrix of the bridge; defining a reliability index corresponding to the state of the bridge, and designing a comprehensive reward function based on maintenance cost, asset risk and traffic network capacity loss risk based on the topological structure; constructing a bridge maintenance decision problem; the method comprises the following steps of: describing a bridge maintenance decision problem as a Markov decision process, establishing a pointer network strategy model by adopting a pointer network, and training the pointer network strategy model by adopting an Actor-Critic algorithm to obtain a maintenance decision model based on reinforcement learning; and training the maintenance decision model based on reinforcement learning until convergence, and outputting a bridge maintenance action sequence under limited constraints. By adopting the method, the limitation problem of traditional single bridge assessment can be solved.

The invention discloses a multi-robot cooperation interaction control method and system based on deep learning, and the method comprises the steps: obtaining historical interaction data, carrying out the environment state coding and feature extraction, and carrying out the correlation score matrix calculation, and obtaining a dynamic interaction weight coefficient; according to the situation representation vector and the interaction weight coefficient, performing future behavior prediction to obtain intention probability distribution data; performing encryption processing on the sensitive information according to historical interaction data to obtain encrypted shared data, performing weighted average aggregation in combination with pre-trained decision model parameters to generate a global collaborative decision model, and inputting the encrypted shared data into the global collaborative decision model to obtain a collaborative action scheme; and according to the cooperative action scheme and the intention probability distribution data, performing multi-constraint task allocation optimization to obtain an optimal task allocation scheme, and performing adaptive path planning to obtain a final action path. According to the method, real-time efficient collaborative decision making in a high-dynamic complex environment can be realized.

The invention relates to the technical field of patent value evaluation. The invention provides a Markov decision-based patent value evaluation method, which is used for constructing a state-action-reward-transfer decision-making model for patent life cycle dynamic characteristics. Through multi-source data processing, state construction, strategy screening, value function iteration and optimal strategy generation, quantitative evaluation of patent dynamic values and operation suggestion output are realized, and the problem that strategy evolution and dynamic earnings cannot be described by an existing method is solved.

The invention relates to the technical field of artificial intelligence, and discloses a business process configuration method based on Activiti and AI decision, and the method comprises the steps: collecting the historical execution data of a business process through a process instance monitoring module, generating a process behavior feature data set, carrying out the training processing of an AI decision model based on the process behavior feature data set, and carrying out the analysis of the AI decision model. A business process decision tree model is constructed, AI decision routing labels are configured for decision nodes in an Activiti process engine, non-intrusive intelligent decision integration is achieved, and when a process instance is executed to a key decision node, a system automatically calls the pre-trained business process decision tree model to conduct real-time path analysis and generate an optimal dynamic routing instruction. The problem of decision stiffness caused by the fact that a traditional workflow depends on artificial experience configuration is solved, the accuracy and adaptability of flow branch selection in a complex service scene are improved, and meanwhile the compatibility and stability of an original flow engine are guaranteed.

This disclosure provides a method, an apparatus, a device, a medium, and a program product for training a decision model. The method includes: determining a first policy using a supervised learning model and a second policy using a reinforcement learning model within the decision model based on training data; determining an imitation learning loss based on a difference between the first policy and the second policy; and training the decision model based on both the imitation learning loss and a reinforcement learning loss corresponding to the second policy. By combining the imitation learning loss and the reinforcement learning loss, a human-like decision model with excellent performance may be obtained, leveraging the expert data utilization capability of supervised learning and the strong generalization capacity of reinforcement learning. In some embodiments, the trained model is applied to autonomous driving for tasks such as lane-changing.

The invention relates to the technical field of environmental risk assessment, and discloses a regional cumulative environmental risk assessment system and method, and the method comprises the steps: constructing a collection network, and dynamically fusing monitoring data and generated data, and obtaining restoration monitoring data; analyzing and identifying emerging pollutants; a collaborative migration network of emerging pollutants and traditional pollutants is constructed, and the migration probability is calculated; establishing a dynamic conversion kinetic equation, and predicting a newly-emerging pollutant conversion product; in combination with an intergenerational accumulation model, simulating cross-generation accumulation of emerging pollutants in the biocenosis; nonlinear exposure-response mapping is constructed, short-term monitoring data and long-term repair monitoring data are fused, a sudden change early warning index is designed, and a risk critical point is recognized in advance; performing inversion updating on the emerging pollution migration parameters, and optimizing the emerging pollution migration parameters; fusing multi-source evidences, and judging whether the risk of the emerging pollutants exceeds the standard or not; and constructing a full-life-cycle decision-making model, designing a reinforcement learning dynamic strategy library updating strategy, and shortening the measure response time.

The invention discloses a farmland intelligent irrigation and drainage decision-making method and device based on multi-source perception and reinforcement learning, and relates to the technical field of intelligent agriculture. Performing reinforcement learning on the farmland intelligent irrigation and drainage decision process by using a double-delay depth deterministic strategy gradient algorithm to obtain measured data; preprocessing multi-source heterogeneous measured data of a target farmland, and inputting the preprocessed multi-source heterogeneous measured data into the bimodal fusion inference model to obtain a spatial-temporal feature vector of the target farmland; inputting the spatial-temporal feature vector into a decision model to obtain an irrigation and drainage decision instruction; and transmitting the irrigation and drainage decision instruction to an execution layer. Through innovative design of multi-source perception fusion, reinforcement learning decision engine and edge-cloud collaborative architecture, decision intelligence, energy efficiency optimization and high system reliability of farmland irrigation are realized.

The invention relates to the technical field of aircraft scheduling management, in particular to an aircraft push-out and taxiing collaborative decision-making method, which constructs a cosine curve push-out rate control module, a push-out and taxiing collaborative decision-making model construction module and an adaptive algorithm design module. Searching an optimal queuing threshold value on multiple runways; secondly, multiple actual operation constraint conditions are emphatically considered, and a collaborative decision-making model with the dual optimization objectives of minimizing the total push-out time deviation duration and the total take-off time deviation duration of the aircraft and minimizing the total departure penalty cost and the oil consumption cost is constructed; and then fusing a Markov chain algorithm of continuous time, a genetic simulated annealing algorithm and a Q-learning reinforcement learning algorithm, scientifically arranging a departure aircraft scheduling sequence, deducing time, a sliding path and target runway distribution through an algorithm solving model, and finally improving the operation efficiency of the multi-runway airport in a mixed operation mode.

The invention relates to the technical field of computer storage, and discloses an AI enabling storage resource dynamic allocation method and system, and the method comprises the steps: constructing a multi-level Markov decision model, and representing the storage resource management as a local and global state conversion and decision process; a multi-agent reinforcement learning framework is constructed and deployed in an interface layer and a scheduling layer to realize distributed intelligent decision making; a bidirectional information flow mechanism between the interface layer and the scheduling layer is realized, a hierarchical barrier is broken, and efficient transmission of information is realized; based on a multi-scale collaborative optimization algorithm, local autonomy and global consistency are fused, and a self-adaptive storage resource allocation strategy is dynamically generated. Through a multi-level autonomous cooperation mechanism, the technical bottlenecks of hierarchical splitting, rigid boundary, single optimization, lack of autonomous evolution ability and the like of a traditional storage system are broken through, and the system performance is remarkably improved, the adaptive ability is enhanced, the cooperation efficiency is optimized, and decision-making intelligence is achieved.

This invention discloses an intelligent air combat decision-making method combining imitation learning and reinforcement learning, belonging to the field of air combat. The method includes: processing battlefield situation information through an intelligent air combat decision-making model to obtain decision results for guiding the aircraft. The pre-trained intelligent air combat decision-making model is obtained through the following steps: for coarse-grained sparse expert policy data, a behavior cloning algorithm is used to train a neural network architecture for imitation learning and reinforcement learning to obtain a policy network Q1; the policy network Q1 is used as the initial network in a generative adversarial imitation learning algorithm to perform imitation learning on fine-grained dense expert policies to obtain a policy network Q2; the policy network Q2 is used as the initial network in a reinforcement learning algorithm framework for decision network training, and the policy gradient method is used to train the network until convergence to obtain the intelligent air combat decision-making model. This invention is based on the ability to effectively improve sample utilization and reduce cumulative error.

The application provides a kind of perception collaborative decision-making method and system based on multi-modal heterogeneous data fusion, it is related to artificial intelligence technical field, method includes: the global environment situation awareness graph is input to pre-trained multi-objective collaborative decision-making model;Multi-objective collaborative decision-making model forms multi-objective decision-making feature set by analyzing resource entity and associated relationship in graph;Based on multi-objective decision-making feature set, decision optimization is carried out, and a comprehensive collaborative scheduling scheme is obtained;The comprehensive collaborative scheduling scheme is parsed and encapsulated to obtain an executable instruction sequence;Through distributed communication architecture, the executable instruction sequence is parallelly issued to the corresponding decision node and control terminal, and the real-time scheduling of resources and the collaborative release of control instructions are completed.The application realizes intelligent perception and rapid response to complex environment by constructing the linkage mechanism of multi-modal data fusion, dynamic environment perception and collaborative decision execution.

The invention discloses a prejudice detection and visual analysis method and system for a machine learning data set and a computer program product, and the method comprises the steps: receiving the machine learning data set which comprises a plurality of training samples; extracting at least one attribute in the machine learning data set; executing the following steps on each specific attribute in the at least one attribute of the machine learning data set: calculating a prejudice degree of the specific attribute of the machine learning data set under a specified condition; and displaying the specific attribute, the specified condition and the prejudice degree on a visual analysis page. According to the method, the attribute-based prejudice can be efficiently identified and analyzed in a large-scale and diversified data set, meanwhile, the detected prejudice can be visually displayed in a visual mode, and a user can conveniently understand and subsequently eliminate the prejudice, so that the decision-making prejudice is eliminated in a decision-making model, and the decision-making accuracy is improved.

The invention provides a labor demand decision-making method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a to-be-decided demand application, financial data and project basic information of a target project, determining the target project based on the to-be-decided demand application, and calculating a target project amount of the target project based on the to-be-decided demand application; a target work type is determined based on the target work amount, the work amount and a preset work type have an association relationship, and the to-be-decided demand application is judged by combining financial data and project basic information through a preset employment demand decision model based on the target work type to obtain an employment demand decision result; the employment demand decision model is obtained by training historical preprocessing data; through the method, a more practical and more accurate employment demand decision-making method is provided.

Disclosed herein is an agent-first application architecture that facilitates intelligent, metadata-driven interactions across distributed computing environments. The system comprises a Metadata Repository, which defines communication policies, interaction rules, and contextual parameters. An Agent Orchestration Layer governs autonomous software agents, dynamically managing their lifecycle, task delegation, and execution logic. A Self-Learning Engine continuously refines agent decision-making models through real-time metadata updates and adaptive learning mechanisms. The system further incorporates an Event-Driven Middleware, which enables real-time, event-triggered execution of agent actions, ensuring adaptive, scalable, and autonomous decision-making across complex multi-system environments. By eliminating rigid API dependencies and leveraging metadata-centric intelligence, the architecture enhances cross-system interoperability, resilience, and adaptability. The invention is particularly suited for dynamic, multi-agent ecosystems requiring real-time adaptability, self-optimization, and intelligent orchestration of system interactions.

The invention provides a multi-agent robust decision-making method fusing a causal attention network and trajectory prediction, and belongs to the field of multi-agent decision-making control. The problem that a traditional decision model is insufficient in safety, robustness and interpretability is solved. The method comprises the following steps: acquiring historical and real-time observation data of all agents in a target scene; extracting the dynamic behavior characteristics and the interaction dependency relationship of the intelligent agent, and outputting comprehensive spatial-temporal characteristics; constructing a causal discovery network, calculating a causal probability between agents, and outputting a causal probability matrix; constructing a causal self-attention network, extracting space-time causal interaction features, inputting the space-time causal interaction features into a trajectory prediction decoder, and generating agent trajectory prediction features; and fusing the space-time causal interaction features and the trajectory prediction features to form comprehensive feature representation, inputting the comprehensive feature representation to a reinforcement learning decision network based on a PPO algorithm, outputting an intelligent agent behavior decision instruction, and completing online optimization and updating of strategy parameters. The method is used in the fields of robot cluster cooperation and intelligent traffic control.

The application discloses a kind of document compliance decision method, system and equipment, comprising: obtaining heterogeneous policy data in multi-source knowledge base, text segmentation is carried out to the heterogeneous policy data, obtain a plurality of semantic block fragments, and index construction is carried out based on the semantic block fragment, corresponding vector index is generated;Based on the vector index, the received marketing document under review is carried out in the semantic block fragment using ColBERT retrieval model and metadata filtering mechanism fusion retrieval, obtain the highest correlation target compliance basis fragment;The target compliance basis fragment and the marketing document under review are input into the preset expert decision model to carry out compliance analysis, generate the compliance analysis result including risk classification result and modification suggestion.It can improve the efficiency and quality of examination, ensure the compliance of marketing document.

This invention provides an industrial control method and system based on anthropomorphic thinking chain and hybrid expert model, including: Step S1: Based on the operator's thinking decision points and decision chain when controlling the equipment, construct a decision model based on anthropomorphic thinking chain and multi-layer hybrid expert model for each process segment in the complete production chain; Step S2: Train the decision model of each process segment using historical data to obtain the trained decision model; Step S3: Use the trained decision model to obtain the control setpoint based on the real-time sensing data of the corresponding process segment.

This invention discloses a method, device, medium, and product for optimizing a decision model based on a world model, relating to the field of autonomous driving technology. The method involves first training the world model to understand structured traffic conditions, enhancing its ability to understand complex traffic scenarios. Then, the world model is trained to predict future driving scenarios based on structured traffic conditions and driving actions, improving the quality of environmental prediction and generation. Based on the trained world model and the decision model, a closed-loop optimization framework is collaboratively constructed. The driving actions output by the decision model and their corresponding structured traffic conditions are input into the world model. The reward value of the driving actions is calculated based on the obtained future driving scenario sequence, and the decision model is updated based on the reward value. This achieves efficient closed-loop optimization of the decision model, significantly improving the model's perception and decision-making capabilities, enhancing the safety and reliability of autonomous driving decisions, and improving the autonomous driving performance of vehicles in complex traffic environments.

Reliance on cloud-based decision-making presents several challenges. To address at least some of these technical challenges, an example system is provided. The system includes an edge computing device including a decision-making model. The system also includes at least one local sensor coupled to the edge computing device through a localized network, wherein the at least one local sensor is disposed in a physical environment. The system also includes at least one local device coupled to the edge computing device through the localized network, wherein the at least one local device is disposed in the physical environment. The edge computing device is configured to: receive, from the at least one local sensor, audio data associated with the physical environment; determine, responsive to the audio data, a state associated with the physical environment using the decision-making model; and determine, based on the state, an instruction for the at least one local device.

This application relates to the field of mathematical modeling technology and discloses a modeling method for a power business decision-making model. The method includes: constructing a power corpus segmentation library and a power vector knowledge base to determine the power business problem text; performing a hybrid retrieval of the power business problem text using the power corpus segmentation library and the power vector knowledge base to obtain a first similarity score corresponding to candidate corpus segments and a second similarity score corresponding to candidate document representation vectors; filtering the candidate corpus segments and candidate document representation vectors based on the first and second similarity scores to determine the target reference text; and inputting the power business problem text and the target reference text into a target large language model to obtain the target decision model. The target decision model includes a description of the power business problem, an objective function, and its constraints. Its beneficial effect is that, based on hybrid retrieval and the standardized output of the large language model, the reliability and accuracy of the target decision model are significantly improved.

The application relates to the technical field of oil and gas exploration, and discloses a drilling auxiliary decision-making method, a drilling auxiliary decision-making device and a machine readable storage medium. The drilling auxiliary decision-making method comprises the following steps: processing first real-time operation data containing first real-time working parameters and first real-time drilling data by means of a first initial decision-making model trained based on behavior cloning, so as to obtain an initial decision; after a driller determines actual operation according to the initial decision and performs actual application, second real-time operation data containing second real-time working parameters of drilling equipment and second real-time drilling data are generated, and a first intention label used for representing an engineering target of the actual operation is determined according to the second real-time operation data; and the second real-time operation data and the first intention label are input into a decision optimization model determined based on reinforcement learning, so that a drilling decision can be finally obtained efficiently and accurately.

The invention provides a charging operator day-ahead strategy optimization method and system based on future expected cost, and the method comprises the steps: generating a charging operator day-ahead decision scene based on market information rolling prediction; based on the day-ahead decision-making scene, establishing an objective function and constraint conditions of a day-ahead decision-making model considering future expected cost; performing piecewise linearization on a daily decision optimization problem of the day-ahead decision model by adopting a future expected cost function reverse construction method; and solving the linearized optimization problem to obtain a charging operator day-ahead strategy. Through market information rolling prediction, a charging operator day-ahead strategy optimization technology based on future expected cost is realized, continuously updated market information is utilized to the greatest extent, and a future electricity price scene is reasonably predicted; by considering the influence of the maximum demand on the total cost of a charging operator in two aspects of demand electric charge and subsequent optimization boundary, the cost influence of the maximum demand in the whole cycle is accurately modeled.

This invention provides a multi-level automated data governance system based on knowledge graphs, relating to the field of knowledge graph technology. The system includes: a knowledge graph module for constructing a knowledge graph, wherein the knowledge graph is used to represent multiple entity data and their relationships, and the entity data includes data generated by device entities, system components, and software modules; a graph information module for acquiring graph information based on the knowledge graph; an importance weight module for determining the importance weight of each entity data in the hierarchical structure based on the knowledge graph; a state evaluation module for determining the state evaluation value of each entity data based on the importance weight and graph information; and a final governance module for processing the importance weight and graph information through a trained decision model to generate a governance strategy for the corresponding entity data if the state evaluation value exceeds a preset state evaluation value threshold. According to this invention, the effectiveness and accuracy of multi-level automated data governance can be improved.

The present application relates to the technical field of feed storage management, in particular to a feed storage dynamic decision-making method and system based on comprehensive storage system coordination, the method comprising: obtaining storage property data of a feed storage center, feed supply time sequence data of a supplier and breeding cycle data, and preprocessing; predicting feed demand fluctuation based on the breeding cycle data, combining feed storage capacity constraints to generate an initial decision-making scheme including multiple feed plan storage time points; based on the feed supply time sequence data, dynamically adjusting the plan storage time points through compatibility verification and a preset coordination mechanism; constructing a decision-making model with the objective of minimizing comprehensive decision-making cost, and solving the optimal decision-making scheme of the feed storage center in combination with preset constraint conditions. The purpose is to realize dynamic decision-making management of multiple categories of feed in large-scale feed storage centers and improve the decision-making efficiency and accuracy of multiple categories of feed in large-scale feed storage centers.

A virtual character action decision-making method includes: obtaining state information, the state information representing a game battle state of a game battle in which a first virtual character is involved; inputting the state information to an action decision-making model, to obtain n target sub-actions serially outputted by n action output heads in the action decision-making model, different action output heads corresponding to different action types, the n action output heads being serially connected based on a dependency relationship between the action types, and the dependency relationship representing a dependency restriction situation between sub-actions under different action types; and controlling the first virtual character to execute a target action formed by the n target sub-actions.

The invention discloses a bulk commodity transaction-oriented supply and demand matching intelligent decision-making method and device, and relates to the technical field of e-commerce supply chain decision-making. The method comprises the following steps: constructing a supply and demand matching decision model by taking the maximum platform profit and the minimum cash flow risk as targets; based on a chromosome coding method, coding according to the supply data set and the payment information data set; performing population optimization by using a simulated binary crossover operator, a polynomial mutation operator and a differential mutation operator according to the coded data set based on a supply-demand matching decision model; performing offspring evolution by using a hybrid differential evolution algorithm; on the basis of an improved epsilon constraint dynamic adjustment strategy, a knowledge transfer method is adopted to carry out population merging, and a fitness ascending sorting method is used to construct a final population; and based on a population evaluation value calculation method, performing optimization according to the final population to obtain an optimal scheme data set. The supply and demand matching intelligent decision-making method is suitable for bulk commodity transactions and gives consideration to adaptability and robustness.

The invention discloses an enterprise exhaustion report generation method and device, and a storage medium, and the method comprises the steps: carrying out the user portrait analysis of multi-dimensional enterprise data corresponding to a target enterprise, and obtaining an enterprise panoramic portrait; performing risk prediction on the multi-dimensional enterprise data to obtain a risk prediction result; scoring the target enterprise based on the multi-dimensional enterprise data and a preset quantitative decision model to obtain a quantitative decision report; the enterprise panoramic portrait, the quantitative decision report and the risk prediction result are filled according to a preset business demand template, a standard exhaustion dispatch report is obtained, and compared with a traditional exhaustion dispatch mode which takes manual operation as a core and has low data processing efficiency, the method has the advantages that the enterprise portrait and the risk are analyzed, and the data processing efficiency is improved. And automatic report generation is realized in combination with a quantitative decision model and a report template. According to the method, full-flow digital intelligence is realized, the risk identification coverage rate and accuracy are improved, the risk matching degree is enhanced, and the report processing efficiency and the data validity are improved.

The application discloses a kind of decision method and system of power capacity market demand response based on scene method, determine the basic assumption of the participation capacity market of demand side response supplier, based on basic assumption, determine the uncertainty factor of the demand side response supplier decision model to be established;Determine the probability distribution of uncertainty factor, extract the different scene of the demand side response supplier decision model to be established;Determine the number of scenes that need to be removed, remove scene based on preset rule;Based on the scene after removal, establish demand side response supplier decision model;Establishing deterministic decision model, random decision model as contrast model;To demand side response supplier decision model, deterministic decision model and random decision model are solved, obtain the participation capacity of demand side response supplier, income and loss;Calculate the probability of violation, based on the probability of violation and the income and loss of demand side response supplier, determine the optimal number of removed scenes.