20 results about "Selection strategy" patented technology

The present application provides a memory management method and a storage device. The method comprises: based on an operation event, obtaining a selection strategy corresponding to the operation event through a performance mapping table; determining a target virtual block combination from a plurality of candidate virtual block combinations according to the selection strategy; and responding to the operation event using the target virtual block combination. Thus, the performance and / or operation stability of the storage device can be effectively improved.

The invention discloses a full-coverage path planning method. The method comprises the following steps: determining a grid map of an area to be subjected to path planning, and determining a transition probability matrix corresponding to the grid map; an initial population corresponding to the grid map is determined according to the transition probability matrix and preset selection strategies, and the preset selection strategies comprise a greedy selection strategy and a fuzzy selection strategy; determining a local distance contribution value of a target path in the initial population, executing a multi-modal disturbance operation on the target path according to the local distance contribution value, and generating a filial generation population corresponding to the initial population; and performing iterative optimization according to the initial population and the offspring population until an optimal path corresponding to the grid map is determined. According to the invention, technical problems of path redundancy, slow convergence speed and poor adaptability to a complex environment existing in a path planning algorithm in a complex obstacle scene in the prior art are solved.

The application discloses an active domain adaptation semantic segmentation method, system, device and storage medium, selects and labels taking superpixels as units, which is different from image-level and pixel-level labeling methods, and the superpixel-level labeling greatly improves labeling efficiency by only assigning a semantic category to each superpixel; in addition, different from the existing scheme based on the uncertainty selection labeling strategy, the application focuses on difficult example samples in the domain adaptation scene, and proposes a selection strategy based on domain information quantity to label superpixels most valuable for domain adaptation learning; by adopting the superpixel-level labeling method and the selection strategy based on the domain information quantity, the application greatly reduces the labeling cost while improving the labeling quality, and guarantees the performance of the domain adaptation semantic segmentation.

The invention belongs to the technical field of transport capacity scheduling, and provides a ship transport capacity configuration optimization decision-making method and system, a medium and a server, and the method comprises the steps: predicting the transport price of each route in each plan period in the future through employing Neuro-ARIMA based on the historical transport price data of energy and bulk material waterway transportation; constructing a transport capacity configuration optimization model by taking net income maximization in a planning period as a target; and solving the transport capacity configuration optimization model by adopting an improved genetic-greedy strategy transport capacity optimization algorithm of domain knowledge guided coevolution to obtain an optimal transport capacity configuration strategy, including an optimal allocation scheme of each transport capacity source, a selection strategy of ship types, a contract signing number and a route allocation plan. According to the method, the coupling model of the task requirements and the transport capacity resources is constructed, collaborative allocation of multi-source transport capacity is realized under the condition that the transport price is uncertain, the adaptability and the utilization efficiency of a transport capacity structure are improved, decision support is provided for enterprises, and reasonable allocation of the transport capacity resources in a dynamic environment is realized.

According to the federated learning optimization method based on the self-adaptive loss threshold, the threshold is dynamically calculated and adjusted according to the error change trend in the training process, so that the client selection strategy is optimized. Secondly, the invention provides a two-factor selection strategy which can select different selection strategies according to different training stages. And finally, a historical information interaction mechanism is provided, so that the client selection is not only based on the current performance index, but also can be flexibly adjusted according to the change trend of the historical performance. According to the mechanism, the client selection process can adapt to the requirements of different training stages, and the training stability and convergence efficiency can be remarkably improved. Experimental results show that compared with a Pow-d method, the global model accuracy rates of the AHIBCS on the three public data sets of COVID-19, FMNIST and CIFAR-10 are improved by 2.1%, 2.4% and 2.7% respectively.

The application discloses a distributed process planning and workshop scheduling integrated optimization method. The application firstly classifies four decision sub-problems of the distributed process planning and workshop scheduling integrated optimization problem into two categories: selection problem and sequencing problem. Then, the selection problem is regarded as a main problem, and the sequencing problem is regarded as a sub-problem, and the two problems are solved respectively, and two groups of Benders optimality cuts and a Benders optimality cut selection strategy are designed to feed back the solving condition of the iteration to the main problem, so that the iteration between the main problem and the sub-problem is realized until the convergence rule is satisfied. The application is not only suitable for the production scene with high requirement on the calculation time, but also suitable for the production scene with high requirement on the quality of the solution. A large number of simulation experiments verify that the application can realize the fast solution of the distributed process planning and workshop scheduling integrated optimization problem, and ensure the quality of the solution.

This application belongs to the field of ultra-high-speed electromagnetic launch design analysis, specifically disclosing a design method for a wound-type electromagnetic launch system. The method includes: analyzing the electromagnetic performance of the wound-type electromagnetic launch system based on its thrust model to determine a first selection strategy for the capacitor in the system's excitation source; analyzing the system thrust, capacitor discharge in the system's excitation source, and changes in the pulse power device current to determine a second selection strategy for the number of turns in the drive coil and the number of turns in the launcher's armature coil; performing parameter selection analysis on the repetitive peak voltage, pulse peak current, critical rate of rise of the on-state current, and current pulse width of the system's excitation source to determine a third selection strategy for the pulse power device in the system's excitation source; and designing the wound-type electromagnetic launch system based on the first, second, and third selection strategies. This application enables the efficient and high-precision rapid design of wound-type electromagnetic launch systems.

The application relates to a prompt word optimization method and device of a text evaluator and a storage medium, and belongs to the technical field of artificial intelligence. The application first initializes a selection strategy cluster, which comprises a plurality of design factor selection strategies of an evaluation prompt word. In each iteration, each selection strategy in the selection strategy cluster is disturbed to generate a new selection strategy. The evaluation prompt word is determined based on the new selection strategy, and an evaluation result is generated on a verification set with artificial evaluation by using a large language model. The correlation coefficient of the evaluation result and the artificial evaluation is calculated, and based on the correlation coefficient, the selection strategy cluster is updated from the current selection strategy cluster and the new selection strategy. The application adopts an iterative search method guided by a heuristic function to optimize the selection strategy, and the selection strategies of a plurality of design factors in the prompt word are optimized, the search range of the prompt word is expanded, and the evaluation performance of the text evaluator is improved.

This invention provides a multi-objective design method for medium-thick plate billets, relating to the field of automation technology. The invention extracts the design process characteristics of medium-thick plate billets, transforms production objectives and process constraints into mathematical expressions, and establishes a multi-objective system optimization model for the design process of medium-thick plate billets. Orders are grouped according to thickness and steel quality codes. Heuristic algorithms are designed to generate initial medium-thick plate billet design schemes. Different heuristic algorithms are constructed according to objective priorities to cover the generation process of different initial feasible billet design schemes. A billet sub-plate crossover strategy and a billet sub-plate mutation strategy are designed to improve the initial feasible design schemes through crossover and mutation processes. A design scheme selection strategy selects the Pareto optimal scheme in the calculation process to form a scheme pool. A scheme reduction strategy is used to reduce the number of schemes in the scheme pool and adjust the sub-plate distribution on different medium-thick plates within the same design scheme. Finally, a design scheme within a limited number of schemes is given.

This invention relates to the field of autonomous driving technology and provides an intelligent quadtree decomposition path planning method for complex dynamic scenarios. The method includes: modeling the quadtree decomposition depth selection problem as a Markov decision process and extracting environmental features as state input; employing an improved Q-learning algorithm to learn the optimal depth selection strategy and constructing a composite reward function that balances planning success rate, path quality, computational efficiency, and depth adaptability; based on the learned strategy, adaptively selecting the quadtree decomposition depth according to environmental features, constructing the quadtree, and performing path planning, while simultaneously combining global planning and local replanning to avoid dynamic obstacles. This invention achieves adaptive matching between quadtree decomposition depth and environmental complexity, solving the problem that a fixed depth cannot adapt to dynamic environmental changes, and significantly improving computational efficiency and robustness in dynamic scenarios while ensuring planning accuracy.

The application discloses a distributed learning method for edge image recognition in intelligent transportation, comprising the following steps: step 1: the server selects a distributed learning task and a deep learning model under an intelligent transportation application scenario; step 2: the server performs model preprocessing; step 3: the server starts a tth round of distributed model training process; step 5: the server selects an edge device based on a selection strategy; step 6: according to information feedback in the existing training, the edge calculates a utility value δ and sends the utility value to the server; and step 7: steps 3 to 8 are repeated until the model parameters converge. k The application has the advantages that fine control granularity and high-performance image recognition model joint training are realized; the number of participants can be reduced and the energy cost can be reduced according to the model training effect and the adjustment of the edge selection frequency; the participation of the edge can be reduced while the accuracy is maintained by dynamically adjusting the selection frequency, and the robustness of the system is effectively improved.

The application discloses a container multimodal transport scheduling method and system based on timeliness, and through optimization of a whale algorithm, scheduling timeliness and scheduling cost are taken into account, and scheduling efficiency is improved.The technical scheme is as follows: starting point and target point coordinates generate a global optimal path through an improved whale algorithm capable of avoiding local optimization, and the global optimal path is used as a container multimodal transport scheduling scheme to increase diversity and improve optimization capability.An optimal whale position updating parameter is introduced to expand a local optimization range, a regulation threshold parameter is classified and adjusted according to whale fitness conditions to adjust a decay degree, and a whale position selection strategy is additionally added to replace random selection, and a whale with high fitness is selected to update a population.In the application, an adaptive multimodal transport scheduling model is established, the model considers timeliness and cost, and weights of two models are determined first.In the application, customer special requirements are considered preferentially, if there is no special requirement of the customer, an experience switching mode is established, weights of a timeliness model and a cost model are set according to historical transportation goods experience, and the target function can be determined according to specific requirements when used.

The application discloses a value perception-based model mid-term training sample selection method and device, and relates to obtaining a candidate training sample set of a large language model and a vertical field question and answer system in a mid-term training stage. The value perception reasoning is performed on the candidate sample set through the parameters and the intermediate state of the current large language model, and the in-domain value representation of the sample is constructed. According to the potential training value and the multi-dimensional features of the sample, the dynamic weighting algorithm is adopted to allocate weights in combination with the mid-term training demand of the vertical field question and answer system, and the high-value sample is selected for incremental training. The model performance evolution result is obtained through the update of the model parameters and the change of the intermediate state, and the sample selection strategy is dynamically optimized. The method can improve the question and answer accuracy and matching efficiency of the large language model in the vertical field, and is widely applied to professional problem retrieval matching, accurate answer and field knowledge output scenes.

The invention discloses a value perception-based model middle-term training sample selection method and device, and relates to acquisition of a candidate training sample set of a large language model and a vertical domain question-answering system in a middle-term training stage. And through the parameters and the intermediate state of the current large language model, performing value perception reasoning on the candidate sample set, and constructing intra-field value representation of the samples. And according to the potential training value and the multi-dimensional features of the samples, weight distribution is carried out by adopting a dynamic weighting algorithm in combination with the mid-term training requirement of the vertical domain question-answering system, and the high-value samples are selected for incremental training. And a model performance evolution result is obtained by updating model parameters and intermediate state changes, and a sample selection strategy is dynamically optimized. The method can improve the question and answer precision and matching efficiency of the large language model in the vertical field, and is widely applied to professional question retrieval matching, accurate question answering and domain knowledge output scenes.

This disclosure relates to a method, equipment, and program product for recommending construction inspection tasks. The method includes: selecting a first set of projects from a construction project database that meets preset inspection conditions; further determining a second set of projects from this first set based on a preset selection strategy; verifying the acceptance status of each construction project in the second set at its current project node; and recommending inspection tasks only to the construction inspectors for construction projects that have not yet passed acceptance. This achieves automated screening and precise delivery of construction inspection tasks, enabling construction inspectors to efficiently conduct on-site inspections based on the recommended tasks, promptly identify and address potential problems, thereby ensuring the quality and progress of construction projects, improving the efficiency of construction inspections, and normalizing construction quality risk management.

The application relates to an analysis method, device and equipment of a componentized software system and a storage medium. The componentized software system comprises n types of components, each type of component corresponds to an index set, and the index set comprises multiple candidate indexes arranged according to index size; the method comprises the following steps: selecting a candidate index from the index set of each type of component according to a preset selection strategy to obtain a first candidate index strategy; determining whether the first candidate index strategy satisfies a constraint condition of a preset trade-off optimization model according to the trade-off optimization model, wherein the constraint condition comprises that the reliability of the componentized software system obtained by purchasing according to the current candidate index strategy is maximum, and the cost is less than a maximum cost; if the constraint condition is not satisfied, a new first candidate index strategy is determined according to the selection strategy again, and the new first candidate index strategy is determined as a target index strategy. The method can improve the trade-off efficiency of the componentized software system.

The application provides a kind of analog integrated circuit multi-objective parameter optimization design method, system and medium, belongs to analog integrated circuit design optimization technical field.The method includes: obtaining circuit performance index measured value and constructing constraint multi-objective optimization model;Initialize population and calculate state characteristic vector representing feasibility, convergence and diversity;Build a reinforcement learning model with state characteristic vector as state space and multiple environment selection strategies as strategy space, dynamically select the optimal strategy;Execute the selected strategy to filter the next generation population, while maintaining three archives to retain the eliminated potential excellent individuals under different preferences;Iterative optimization until the termination condition is met, and output the Pareto optimal solution set.The application realizes adaptive decision of environment selection strategy through reinforcement learning, effectively balances feasibility, convergence and diversity, improves the efficiency and solution set quality of analog integrated circuit transistor size optimization, and the output scheme can be directly used for tape-out.

The application provides an intelligent adaptive traffic signal control method combining reinforcement learning and model predictive control, and belongs to the technical field of intelligent traffic.The application uses a Q-Learning algorithm to continuously optimize an MFD combination selection strategy through online learning, so that the system can dynamically adapt to different traffic flow modes and changes.The Q-Learning algorithm combines an epsilon-greedy selection strategy, gradually improves the control effect through a reward mechanism, and effectively improves the timing efficiency of the boundary signal light.In the signal optimization of the internal area, the application adopts a Cyclic MaxPressure algorithm to dynamically adjust the signal timing according to the real-time traffic flow distribution, so that the signal timing can quickly respond to the randomness and complexity of the traffic flow, thereby effectively relieving the congestion at the local intersection.

The application discloses a method for aircraft task allocation in a three-party cluster confrontation scene based on game theory, and belongs to the technical field of aircraft cluster confrontation decision-making. The application solves the problem that the prior art cannot make unified decision on target allocation and opponent selection of an attacking aircraft. The method comprises the following steps: step one, establishing a zero-sum matrix game model for target allocation of an attacking aircraft and an intercepting aircraft; step two, solving the zero-sum matrix game model established in the step one by using a DO algorithm to obtain a target allocation result of the attacking aircraft; step three, establishing an opponent selection model, and determining an opponent selection strategy of the attacking aircraft according to the opponent selection model and the target allocation result in the step two to obtain the opponent selection strategy of the attacking aircraft; and taking the target allocation result and the opponent selection strategy of the attacking aircraft as a task allocation scheme of the attacking aircraft in a three-party cluster confrontation scene. The application can be applied to optimizing the strategy of the attacking aircraft.

The application discloses a single budget multi-round federated learning incentive mechanism method, device, equipment and medium, and the method comprises the following steps: receiving the total budget of a task publisher, a learning task and a standard small data set; according to the standard small data set, the quality of the local model of all task participants in the round is evaluated; according to a selection strategy and a payment function, in combination with the quality evaluation value of the local model of each task participant in the round, the task participants participating in the federated learning in the round are selected, and the remuneration of the task participants is determined; if the total budget is greater than 0 after the payment of remuneration, the global model is sent to the selected task participants, so that the local model of each task participant is locally trained; the local model trained by each task participant is received, and the global model is aggregated by using an aggregation method. The application designs a feasible incentive mechanism for non-independent and identically distributed federated learning, and can further promote the landing use of federated learning application.