13 results about "Decision problem" patented technology

The application belongs to the technical field of natural language processing and knowledge graph, and discloses a kind of multi-modal acquisition and evolution graph analysis method and system of policy text. In view of the passive decision problem caused by the rigidity of existing policy analysis, semantic understanding and lack of dynamic correlation, the application adopts visual and DOM feature weighted fusion and reinforcement learning agent to realize multi-modal adaptive acquisition and joint alignment in anti-crawling environment;Use large language model for semantic deconstruction, and convert implicit logic into computer-readable explicit logic expression through thought chain reasoning;Construct a policy evolution knowledge graph with time and validity level attributes, perform satisfiability analysis to output conflict detection results;Map the target object portrait to the graph and the logic expression to evaluate item by item, and output intelligent decision deduction results combined with quantitative dimensions. The application realizes the whole life cycle intelligent analysis of policy data acquisition, deep logic analysis and active deduction.

The application discloses a kind of 6G network multidimensional resource AI model dynamic deployment optimization methods based on category theory, belongs to intelligent collaborative optimization technical field;Method is: the cross-layer consistency dependency of end-to-end AI reasoning service is formalized by functor form;Establish the joint optimization model with long-term average end-to-end delay minimization as target, while being constrained by multidimensional resource and service quality;Convert long-term random optimization problem into time-slot online decision problem;Get AI model dynamic deployment and task scheduling result.The application realizes cross-layer consistency description to task scheduling and model deployment through category theory unified modeling and functor composite mechanism, reduces the inconsistency and redundant constraint caused by hierarchical modeling, improves the structured degree and explainability of joint decision;Under the constraint of multidimensional resources such as calculation, memory, storage and bandwidth, dynamic adaptive optimization is realized, node resource over-limit and load imbalance are effectively avoided, and congestion and queuing delay are reduced.

The application relates to a kind of adaptive video streaming method and system based on serverless computing, belong to streaming media transmission technical field.System is realized by fine-grained serverless pipeline Video delivery, use stateless function to strengthen the response to video request event, use a kind of near-end strategy optimization PPO of three-end clipping based on deep reinforcement learning algorithm to solve the bit rate adaptive sequence decision problem in video playing process.In addition, dynamic video block quality factor is included in user experience QoE index, to configure QoE model, for each video block is assigned a priority weight, improves the robustness of video bit rate decision, thereby reduces video streaming delay, improves user viewing experience.

The application discloses a cold and hot data recognition method and system based on streaming learning, and belongs to the field of computer storage. The system regards cold and hot recognition as a decision problem, extracts multi-dimensional features including data flow, control flow and system information through a feature extraction module to construct a feature vector, realizes online hotness evaluation and real cold and hot label generation through an online label module, adopts a streaming learning algorithm in a cold and hot recognition module, predicts the cold and hot state of a data block in the future in real time according to the feature vector, and regularly updates a model to cope with concept drift. In addition, the system adopts a dynamic adjustment mechanism of cold and hot perception threshold, can adaptively guide data migration, realizes online judgment and labeling of data cold and hot, and provides efficient and adaptive cold and hot data recognition services for user applications.

The application relates to the technical field of artificial intelligence, and discloses a RAG and preference alignment collaborative optimization method and system for the electric power field. The method comprises the following steps: performing text segmentation on an electric power business decision knowledge base, and generating electric power business adaptation texts by vectorizing and representing each text block obtained through retrieval enhancement; based on the electric power business adaptation texts, combining a first large language model and retrieval enhancement to generate a plurality of electric power business decision problems and expert decision texts and ordinary decision texts corresponding to each electric power business decision problem; and based on a preference data set, fine-tuning a pre-trained second large language model by using a direct preference optimization and a probability ratio preference optimization weighted fusion mode to obtain a target large language model. The application provides a reliable intelligent modeling tool for complex decision-making of an electric power system, and provides a reusable optimization paradigm for landing of professional field modeling of reinforcement learning.

The application relates to the technical field of smart city living decision support, and particularly discloses a city space trade-off method and system. The official data is processed by a three-level cascading algorithm engine to solve core decision problems: first, a living cost safety interval dynamic generation engine calculates and outputs candidate regions and cost safety intervals that are matched with the income of a user and are financially sustainable based on the income of the user and official fluctuation housing price and rent data through an income and debt stress test model; then, a region convenience resilience index calculation engine accesses time sequence traffic and facility load data, quantifies the public service accessibility and service resilience of each candidate region in different time periods through a space-time accessibility resilience model, and generates a convenience resilience index; finally, a long-term living risk pre-evaluation engine mines future city planning policy texts, predicts the probability and level of negative drift of the living attributes of each region by using a risk transmission model, and generates a final recommendation list with risk warnings.

The present application relates to the technical field of smart grid, and discloses a MARL topology control method and system for promoting renewable energy grid connection, comprising: constructing a topology control problem and a multi-agent decision problem under a large-scale power grid, obtaining power grid operation data and constructing a data set according to a reverse power flow index; constructing a joint graph capable of capturing the complete operation range of a dynamic power grid based on the data set, and dividing agents based on topology distance; constructing the observation, action space and heterogeneous reward and punishment function of each agent, and calculating the advantage function of each agent according to the same, optimizing the strategy and value network of the agent through the centralized training and distributed execution paradigm to obtain an optimized multi-agent topology. The present application can meet the needs of scalability under a large-scale network, operation safety in real-time decision-making and effectiveness of the control strategy.

The application discloses a kind of polygon quadrilateral grid automatic subdivision methods based on deep reinforcement learning, it is related to the field of computational geometry and grid generation, the application constructs a kind of automatic subdivision framework of fusion geometry priori knowledge and data-driven strategy.The method predefines 9 kinds of basic topological filling templates covering triangle to hexagon as discrete action space, converts continuous geometry segmentation into sequence decision problem;The mapping relationship between polygon state characteristics and optimal template selection strategy is learned using deep Q network, and exploration and utilization are balanced through dynamic epsilon-greedy mechanism;Combining vertex number priority scheduling strategy and multidimensional quality reward function, guide agent to adaptively generate high-quality quadrilateral grid.The application realizes the full-automatic, high robustness subdivision of complex polygon region, significantly improves the grid orthogonality and aspect ratio quality, avoids manual intervention, and is suitable for finite element analysis and other engineering scenarios.

This invention discloses an order batch processing method and system for intelligent warehousing, comprising: a modeling step: constructing a semi-Markov decision process model for the dynamic order batch processing decision problem; a state awareness step: collecting warehouse operation data in real time and encoding it into a structured state vector containing order queue characteristics, equipment load characteristics, and global monitoring characteristics; an action decision step: based on a trained deep reinforcement learning agent, adaptively selecting a target heuristic rule from multiple preset underlying order batch processing heuristic rules according to the current state vector; and a task execution step: calling the selected heuristic rule to batch process the current order pool, generating picking tasks and driving the physical system to execute. This invention, through an adaptive decision-making mechanism based on deep reinforcement learning, enables the warehousing system to perceive the environment in real time and dynamically select the optimal batch processing strategy from multiple rules, thereby intelligently balancing efficiency and timeliness.

This invention relates to a dual-timescale task offloading and resource allocation method for multi-timeslot MEC systems, comprising: establishing a long-term average energy consumption minimization model for a multi-user, multi-server MEC network; solving the long-term average energy consumption minimization model at two timescales; on the one hand, at a smaller timescale, decoupling the long-term stochastic task offloading and resource allocation problem into a series of online optimization deterministic problems by invoking the Lyapunov method, obtaining closed-form solutions for offloading decisions and resource allocation at each timeslot; on the other hand, at a larger timescale, formulating the server active / sleep mode selection and user-server association decision problem as a constrained Markov decision process, and employing a bi-adversarial deep Q-network (D3QN) from deep reinforcement learning to learn the mode selection and association decisions. Compared with existing technologies, this invention can effectively reduce the computational complexity of multi-timeslot systems and improve the solution speed.

The application provides a model prediction control-based unmanned carrier aircraft trajectory planning and launching decision method and system, and belongs to the field of unmanned aircraft trajectory planning. In order to solve the problems that the existing sub-aircraft launching timing decision problem is difficult to be mathematically modeled and is difficult to be combined with the carrier aircraft flight trajectory planning, the application combines the carrier aircraft trajectory planning task and the sub-aircraft launching task, constructs a cost function related to the carrier aircraft flight and the sub-aircraft launching state according to the task requirement, models the carrier aircraft flight and the sub-aircraft launching in a prediction time domain as a mixed integer programming problem, and solves the optimal flight trajectory of the carrier aircraft and the launching instruction of the sub-aircraft through rolling optimization to generate the optimal flight trajectory of the carrier aircraft and the launching instruction of the sub-aircraft. The application establishes a solving framework for the combined unmanned aircraft sub-aircraft launching decision problem, unifies the trajectory planning problem and the launching decision problem, and improves the autonomy and intelligence of the unmanned aircraft.

The application discloses a kind of oil-immersed power equipment risk assessment and regulation method based on digital twinning, to solve the technical problems that current monitoring system cannot form complete closed loop, lack online calibration and causal identification, cannot answer key decision problem.The method comprises: obtaining the current state snapshot of oil-immersed power equipment and multi-physical field model;Parameter calibration is carried out on the multi-physical field model using the current state snapshot, and a digital twin model is obtained;Based on the digital twin model, multi-physical field coupling solution is executed, and multi-physical field key indicators are obtained, and candidate action set is constructed according to multi-physical field key indicators, combined with comprehensive risk assessment;The optimal control scheme is determined by executing candidate action set through digital twin model, combined with multi-objective optimization decision;Control oil-immersed power equipment to execute optimal control scheme, and optimize digital twin model based on regulation result.

This invention discloses a non-periodic dynamic detection and maintenance method for multi-state systems based on Gaussian demand and customized PPO (Progressive Point of Action), comprising the following steps: A) System and demand modeling: including a multi-state system model, time-varying demand modeling, and definition of detection and maintenance actions; B) Continuous-time MDP modeling: constructing the dynamic detection and maintenance decision problem as a continuous-time Markov decision process, including state space, action space, state transition probabilities, reward function, and objective function; C) Customized PPO algorithm framework: designing a deep reinforcement learning framework based on PPO, adapting to the hybrid action space, and efficiently solving the MDP model. The demand modeling of this invention is accurate: by using a Gaussian process to model time-varying demand, it can simultaneously capture the expected trend, random fluctuations, and time correlation of demand. Compared with traditional constant, linear, or simplified Markov demand modeling, it is more in line with actual industrial scenarios and effectively reduces the risk of supply-demand mismatch.