104 results about "Initial distribution" patented technology

The invention relates to a heterogeneous unmanned ship task dynamic optimization method based on intelligent distributed CBBA, and relates to the technical field of unmanned autonomous cooperative control, the method comprises the following steps: firstly, using an intelligent distributed CBBA algorithm to realize task initial allocation, and constructing a cost function integrating distance cost, time cost and time window default penalty; and a task sequence is adjusted through a greedy strategy so as to meet strict time window constraints. And secondly, in the task execution process, a real-time monitoring and dynamic re-planning mechanism is established, and emergencies can be rapidly dealt with. A redistribution mechanism is introduced, the weight of a cost function is dynamically adjusted through a genetic algorithm, and loss and scheme optimization benefits caused by task execution subject change are balanced. Compared with the prior art, the task execution efficiency, reliability and adaptability of the heterogeneous unmanned ship cluster in a complex dynamic environment are effectively improved, and the method is suitable for complex application scenes such as maritime search and rescue, material delivery, patrol monitoring and the like.

The invention relates to the field of combinatorial optimization and artificial intelligence, and discloses a group logistics transportation scheduling method and system based on a role interaction graph neural network, and the method comprises the following steps: S1, dividing agent nodes and position nodes, and generating initial features; s2, iteratively updating node embedding by using a multi-channel attention mechanism of a graph neural network; s3, generating a delivery point distribution probability based on node embedding, and determining an initial distribution scheme; s4, local redistribution optimization is performed on the delivery points with low confidence distribution; and S5, performing parallel path planning on the optimal scheme, and outputting a result for reinforcement learning feedback. In the invention, through modeling of a graph neural network multi-channel attention mechanism on a complex interaction relationship and a synergistic effect of local redistribution optimization and parallel path planning, a second-level generation of a high-quality scheduling scheme is realized, cross-scale scene migration of the model is achieved, and group logistics transportation scheduling efficiency and robustness are improved.

The invention provides an irrigation district water diversion quantity multistage distribution method under total quantity index constraint, comprising the following steps: dividing an irrigation district into a plurality of calculation units based on an administrative division boundary and a canal system network; respectively calculating the initial water demand of each calculation unit under the living water demand, the industrial water demand, the agricultural water demand and the ecological water demand; based on the initial water demand and according to multiple water resource rigid constraint indexes, performing at least one round of checking and pressure reduction on the initial water demand of each calculation unit to obtain an initial distribution water amount of each calculation unit; and carrying out secondary distribution on surplus water generated after checking and pressure reduction, and compensating the calculation units of which the water demand is not met to obtain the final distribution water of each calculation unit. According to the method, fair, reasonable and efficient distribution of water resources in a complex system with cross coupling of administrative division and canal system networks is realized, and the problems of conflict between a scheme and actual management requirements, water consumption contradiction and the like caused by a traditional single-dimension distribution method are avoided.

The present disclosure provides a method for managing allocation of compute resources in a distributed database. Each request on every task is allocated a certain number of tokens when it arrives, such as by using a token bucket algorithm. This initial allocation may be the per-request maximum usage permitted in the system. This request is made to a central quota server in the region to coordinate allocations between tasks. As the task runs, the system evaluates how much of the limit the request is using, and adjusts its limit up or down to keep the quota allocation tight on the actual usage of the request. If there aren't enough tokens to keep the request active, the request can be evicted.

The embodiment of the invention provides an unmanned aerial vehicle distribution path planning method, device and equipment, and the method comprises the steps: constructing a plurality of distribution paths according to a distribution region of an unmanned aerial vehicle and distribution points included in the distribution region; obtaining topographic data, coordinate information of a plurality of distribution points, cargo weight information of the plurality of distribution points, initial environment data and unmanned aerial vehicle initial state data; according to the coordinate information of each distribution point and the cargo weight information of each distribution point, screening an initial distribution path from the distribution paths based on a load near-point priority strategy; determining cost information of each initial distribution path according to an arrangement sequence of distribution points included in each screened initial distribution path, topographic data, coordinate information of each distribution point, cargo weight information of each distribution point, initial environment data and unmanned aerial vehicle initial state data; and determining a target distribution path according to the cost information of each initial distribution path. The optimal distribution efficiency of the unmanned aerial vehicle under the complex road condition is ensured, the energy consumption of the unmanned aerial vehicle is lowest, and the distribution is safer.

The invention discloses a resource allocation method and system based on a product technology guarantee index, and relates to the technical field of maintenance guarantee, and the method comprises the following steps: 1, based on a task demand set, an available guarantee resource set, a priority weight set, a task time factor and an initial strategy set, defining a task utility function, and obtaining a game model; 2, solving a Nash equilibrium point of resource allocation based on a game model through a hybrid optimization method, and generating an initial resource allocation scheme; step 3, optimizing the initial allocation scheme through a reinforcement learning feedback mechanism and a dynamic priority adjustment method to generate an optimized resource allocation scheme; and step 4, evaluating the optimized resource allocation scheme based on the task completion rate and the resource utilization rate to obtain a final resource allocation scheme. According to the invention, dynamic optimization and fair distribution of technical support indexes are realized based on resource competition and cooperative distribution of the game model.

The invention relates to the technical field of artificial intelligence, can be applied to the medical field and the financial science and technology field, and discloses a state diagram-based task cooperation method, device and equipment and a storage medium, and the method comprises the steps: receiving initial task data and the real-time states of a plurality of agents through a global management and control node, and creating an initial task; performing semantic analysis on the initial task data to obtain a task demand, and determining a task allocation object; routing the initial task to a corresponding task processing node according to the task allocation object through the initial allocation condition edge; processing the initial task through the task processing node to obtain a processing result, and updating a task state based on the processing result; and judging the updated task state through the routing control condition edge, and if the updated task state is judged to be a blocked state, performing task processing again until the task state becomes a completed state. The method has the remarkable advantages of dynamically adapting to task demand changes and improving the task execution reliability.

The invention discloses a building construction resource constraint allocation optimization method based on big data, particularly relates to the field of building engineering resource management, and is used for solving the problems of on-duty waiting, equipment idling, channel congestion and scheduling and field rhythm departure caused by the fact that material in-place, working plane admission, channel release and mutual exclusion control are not synchronously met in the existing scheduling. Reading an operation window through a unified time mark, and subscribing a material in-place event to generate a time anchor point; according to anchor point extraction constraint fragments, transcription channel release records and mutual exclusion rules, forming a constraint fragment set for a working plane admission condition; constructing a resource feasible region, and executing a four-state closed decision to screen candidate time periods and output an initial allocation table; checking the initial distribution table in a landing manner, marking mismatch and writing the mismatch back to the constraint fragment set; and according to mismatch, triggering rolling recalculation, retaining a local rearrangement non-executed segment of the main closed segment, outputting a stable distribution table, and solidifying criterion reference.

The invention discloses a wafer grinding control method and system, and the method comprises the steps: carrying out the prediction of an initial grinding parameter through a pre-established thickness-grinding rate model according to the thickness initial distribution data of a wafer; the thickness-grinding rate model is constructed according to grinding process data of a wafer with a groove isolation structure; sending the initial grinding parameters to grinding equipment so as to control the grinding equipment to grind the grinding film layer; monitoring thickness allowance distribution data of the grinding film layer in the grinding process; the initial grinding parameters are adjusted according to the thickness allowance distribution data, and adjusted grinding parameters are obtained; and the adjusted grinding parameters are sent to the grinding equipment so as to control the grinding equipment to dynamically adjust the grinding rate. By adopting the method, the grinding parameters are dynamically adjusted in the grinding process, the process stability is improved, and the chip yield is improved.

Method and system for DC power distribution for charging stations based on a chaotic topology. The invention relates to a method for DC power distribution for charging stations based on a chaotic topology, comprising: according to user requirements, establishing an initial chaotic topology distribution network for charging station power based on a matrix topology network (S1); using a Gaussian kernel function to extend one dimension of the initial distribution network to a high-dimensional surface to obtain a distribution network with multiple charging nodes (S2); based on the distribution network, the required energy of each charging point, and an energy distribution strategy, controlling the opening and closing of contactor switching units to direct the output energy from power conversion units (S3). Figure 1

The invention provides an air volume dynamic cooperative control method and system for a multi-scene dust removal system, and the method comprises the steps: collecting multi-source detection data in real time, inputting the multi-source detection data into an initial distribution model, and outputting an initial air volume distribution strategy through the initial distribution model; the initial air volume distribution strategy is optimized through an optimization model in the two dimensions of the minimum total power consumption and the minimum dust removal efficiency, and an optimized distribution strategy is obtained; adjusting corresponding equipment according to the optimal distribution strategy, and obtaining feedback data; performing optimization iteration on the initial distribution model and the optimization model through the feedback data; through the design, efficiency and energy consumption are both considered in the dust removal scene, and the air volume distribution scheme is dynamically adjusted according to the external environment change, so that a relatively excellent scheme is effectively output, the dust removal efficiency in the dust removal scene is effectively improved, and the energy consumption is reduced.

The invention discloses a multi-agent cooperative grouping and income distribution method, which comprises the following steps of: introducing an improved HCS algorithm to reasonably initialize tasks and each agent, calculating sub-task priorities according to skill requirements and prediction workload distribution, optimizing cross-task resource distribution by combining income prediction and cost constraint in an inter-task competition stage, and optimizing the task resource distribution. And calculating the marginal contribution of the intelligent agent based on a Shapley value, carrying out income distribution in combination with a dynamic excitation coefficient, adjusting an income distribution proportion according to parameters, and carrying out iterative strategy updating on a formed initial grouping result until the initial grouping result is converged to Nash equilibrium after the individual rational constraint and the overall income maximization are met. According to the method, initial allocation is intelligentized, the resource utilization rate and the total task income are remarkably improved based on skill demand prediction and the workload priority, fair and efficient income allocation is ensured, and the method is suitable for industrial automation, smart cities and other scenes.

The invention relates to an intelligent decision-making and collaborative guidance integrated design method, in particular to an intelligent decision-making and collaborative guidance integrated design method. The method aims at solving the problems that in an existing task scene that multiple interception projectiles cooperatively intercept multiple targets, the overall interception efficiency of a projectile group and a target group cannot be maximized, the calculation complexity is high, iteration time consumption is remarkable, and guidance instruction updating is lagged. The method comprises the following steps of: 1, obtaining a reachable domain of each interception bullet for each target; 2, averaging the three-dimensional coordinates of each interception missile for the reachable domain range of each target, and solving the aiming point of each target; based on the aiming point of each target, the total overload of the interception projectile is obtained; thirdly, target distribution is conducted on the interception bombs; 4, constructing a hybrid optimization index based on the strike benefit index and the overload index; and 5, further adjusting the initial allocation result in the step 3 to obtain a global optimal allocation scheme. The method is applied to the field of integration of intelligent decision and collaborative guidance.

The invention belongs to the technical field of computers, and particularly discloses an intelligent distribution system for distributing dynamic red envelopes for consumers, which comprises a grade management module, a fund pool configuration module, a matching distribution module, a fund monitoring module and a dynamic allocation module, according to the method, the initial budget allocation weight of each consumption level is calculated based on the red envelope conversion efficiency, and the initial allocation amount of each level fund pool is obtained by combining the total budget amount, so that marketing funds are preferentially input to a user group with higher red envelope conversion efficiency; meanwhile, by comparing the predicted fund depletion time point with the activity end time point, a gap and a surplus fund pool are judged, according to the comparison result of the total fund gap amount and the total surplus fund amount, sufficient allocation or shortage allocation is triggered, and a corresponding priority ranking and fund allocation algorithm is executed; the problems that traditional budget distribution is rigid and market changes cannot be responded in real time are solved.

This invention relates to the fields of distributed computing and artificial intelligence, and particularly to a task scheduling method, system, device, and medium for edge-cloud intelligent agents. The method includes: constructing a global load topology and an intelligent agent capability feature set; decomposing the target task into multiple sub-tasks and determining temporal dependencies and execution constraints; inputting a pre-trained policy model to output an initial allocation policy; constructing a causal graph based on the allocation policy to generate an interpretable basis chain; performing simulation pre-runs of the policy; if the policy fails verification, analyzing the basis chain to locate local optimal interference and triggering policy self-correction for iterative pre-runs; if the policy passes verification, issuing the policy and adjusting routing weights in real time to implement traffic smoothing and task filling. Therefore, this invention, by constructing a three-level collaborative architecture of edge-cloud, not only achieves deep collaboration from macro-architecture to micro-algorithm, but also significantly improves the flexibility and scalability of equipment management in complex scenarios such as smart stations and industrial parks.

The invention discloses a high-precision wind tunnel nozzle profile design method, and belongs to the technical field of wind tunnel nozzle profile design based on a computer. The problems that in the prior art, a traditional wind tunnel nozzle molded surface design method is poor in process feasibility, and the number of molded surface correction iterations is large are solved. According to the method, modeling software is adopted to construct an initial profile mathematical model, geometric constraints are integrated, a wall thickness initial distribution model is established, and wall thickness distribution is optimized; s2, quantizing an objective function according to the constraint and the model parameters in the step S1, optimizing the objective function, and refining the constraint to obtain refined constraint conditions; and according to the wall thickness initial distribution model and the wall thickness parameters, design software is combined with the refined constraint conditions to carry out parametric modeling, a process feedback mechanism is constructed to carry out correction compensation on initial molded surface modeling, and high-precision wind tunnel nozzle molded surface design is completed. The pneumatic performance and the material utilization rate are effectively improved, and the method can be applied to high-precision pneumatic verification tests.

The invention provides a big data task scheduling optimization method and system based on heterogeneous computing, and relates to the technical field of big data process.The big data task scheduling optimization method comprises the steps that multi-source big data and transmission parameters of corresponding transmission links are obtained, and associated information is extracted from the multi-source big data; obtaining a target transmission link based on the transmission parameter; based on the associated information, obtaining a plurality of processing sub-items with identifiers and a corresponding execution sequence; obtaining an initial allocation scheme based on the associated information; obtaining running state information of the heterogeneous computing resources to obtain a verification result, and adjusting the initial allocation scheme in combination with the execution sequence to obtain a final allocation scheme; and based on the target transmission link and the final allocation scheme, the processing subitems with the identifiers are processed through the heterogeneous computing resources, and efficient, safe and ordered scheduling optimization of the multi-source big data in the heterogeneous computing environment is realized.

The application relates to the technical field of factory scheduling, in particular to a multi-factory collaborative scheduling optimization method and system considering resource constraints. The method comprises the following steps: analyzing historical order delivery information of each factory, determining order delivery capacity values of each factory, and distributing orders of the multiple factories according to the order delivery capacity values to determine initial distribution order values of each factory; analyzing collaborative scheduling information of each factory to obtain supplementary scheduling order values and cancellation scheduling order values of each factory to other factories, wherein the collaborative scheduling information is used for representing idle order values and new order values of each factory in a current scheduling period; and based on the supplementary scheduling order values of each factory to other factories, the cancellation scheduling order values of each factory to other factories and the initial distribution order values of each factory, target distribution order values of each factory are determined. The application can improve the utilization effect of production resources of a production cluster composed of multiple factories.

The invention relates to a mapping method and device based on a wafer-level chip, equipment, a medium and a product. The method comprises the following steps: obtaining form parameters of each calculation core to be distributed; the form parameters are used for describing static attributes and structures of the calculation cores; determining initial distribution of execution parameters of each calculation core according to the calculation power and the form parameters of each calculation core; and determining target distribution of the execution parameters of each calculation core according to the connection relationship between the calculation cores, the initial distribution of each form parameter and each execution parameter and the cost model, so as to allocate the calculation resources of the wafer-level chip to each calculation core based on the target distribution. In the embodiment of the invention, the computing power characteristic of the wafer-level chip is considered, so that the mapping algorithm is closer to the resource characteristic of the wafer-level chip when the mapping algorithm is realized, calculation is carried out based on the cost model, the calculation complexity can be reduced, and the high efficiency of the mapping algorithm is improved.

This application provides a method, apparatus, equipment, and medium for production line load balancing. The method includes the following steps: generating an initial allocation scheme; selecting an initial optimized allocation scheme; searching and updating to generate a search-optimized allocation scheme; comparing to obtain a search-determined scheme; performing advanced updates to generate an advanced optimized allocation scheme; comparing to obtain an advanced determined scheme; and iteratively executing until a target number of iterations is reached to generate a target determined scheme. This application generates initial allocation schemes for multiple production devices based on a task list; and performs multiple global, local, and advanced updates and optimizations on the initial allocation schemes to select the final target determined scheme. This method can achieve effective global and local balance; it can dynamically adjust task allocation according to the actual load of the production line, ensuring load balance among production devices, and has significant effects on improving production efficiency and balancing the load of various production devices, and is applicable to production lines of different sizes.

The invention relates to a task information processing method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring initial distribution task information of a first distribution object; under the condition that the initial distribution task information indicates that the initial distribution task meets the task cooperation condition, obtaining a task cooperation rule of the first distribution object; performing task allocation on the initial delivery task according to a task cooperation rule to obtain a first delivery task of the first delivery object and a second delivery task of the second delivery object; wherein the second delivery object and the first delivery object have a task cooperation relationship; sending the first distribution task information to the first distribution object, and sending the second distribution task information to the second distribution object; the first distribution task information is used for prompting the first distribution object to execute the first distribution task, and the second distribution task information is used for prompting the second distribution object to execute the second distribution task. By adopting the method, the logistics distribution efficiency can be improved.

The invention provides a method for planning and generating downstream receipts based on a quota protocol, and relates to the technical field of enterprise resource planning and purchasing management. The quota agreement comprises providable suppliers of each material in different organizations, a minimum batch, a maximum batch and a price of each supplier, an initial distribution proportion of each supplier and a unique identifier of the quota agreement; creating a purchase plan, wherein the purchase plan comprises purchase organizations, material IDs, the total number of plans and other purchase information; querying and matching quota protocols according to the purchase plan information, and screening out quota protocols meeting conditions; optimizing the allocation proportion of the quota protocol based on Markov decision to obtain an optimized allocation proportion; and associating the purchase plan with a quota protocol, dividing the total quantity of the purchase plan into a plurality of parts according to the optimized distribution proportion, and generating a corresponding downstream document for each divided part.

The invention discloses a flow-thermal coupling topological optimization method based on fractal structure guided evolution, which comprises the following steps: constructing a fractal geometric initial structure with spatial self-similar characteristics according to geometric boundary conditions and heat flux density distribution of an optimization domain; the branch level, the scale ratio and the space embedding position of the fractal geometry initial structure are controlled through adjustable parameters, and a multi-scale perturbed material initial distribution field is formed; establishing a single-phase or multi-phase flow and heat transfer coupled topological optimization model, coupling a material initial distribution field with physical parameters, and performing material distribution optimization by taking a fractal geometry initial structure as a starting point and adopting an iterative solution method to obtain an optimized density field; and carrying out binarization processing on the optimized density field, extracting a continuous structure boundary curve, and generating a multi-scale thermal management structure with engineering realizability. Precision optimization and performance enhancement of structural design under the working condition of high heat flux are achieved.

The invention provides a data scheduling method and device of a distributed storage system, electronic equipment, a storage medium and a program product, and relates to the technical field of big data management. The method comprises the following steps: predicting a state change trend of each node based on multi-source state data of the nodes of the distributed storage system; determining an initial allocation scheme and a reward score of the target task to determine a task allocation scheme; and scheduling the data blocks of the distributed storage system based on the task allocation scheme. According to the method, the state change trend of the node is predicted according to the multi-source state data, the state data of the node in multiple different dimensions are fully considered, and accurate prediction of the current state and the future state of the node is realized. The task allocation scheme is determined through the state change trend and the features of the target task, the task allocation scheme is made in advance in combination with the future resource demand change of the node and the features of the to-be-allocated task, and the utilization rate of the node at the current moment and in the future time period can be improved.

The present disclosure provides a method, a system and a storage medium of resilient human-on-the-loop range-only cooperative positioning of a plurality of unmanned aerial vehicles (UAVs). The method includes computing an initial exploitability using an initial distribution and an initial policy; performing a forward updating of a distribution of a portion of the plurality of UAVs, and performing a backward updating of a Q function of each UAV of the plurality of UAVs; for each time step, calculating a dual variable at an (i+1)-th iteration and calculating a policy at an (i+1)-th iteration; computing a ratio of an exploitability at the (i+1)-th iteration over the initial exploitability; and if the ratio is less than or equal to a pre-defined tolerance value, maintaining a policy at the i-th iteration; and if the ratio is greater than the pre-defined tolerance value, using the policy at the (i+1)-th iteration.

The application provides a method for generating downstream bills based on a quota agreement, relates to the technical field of enterprise resource planning and procurement management, and comprises the following steps: initializing a quota agreement, the quota agreement comprising available suppliers of each material in different organizations, minimum batch quantity, maximum batch quantity and price of each supplier, initial allocation proportion of each supplier, and unique identification of the quota agreement; creating a procurement plan, the procurement plan comprising a procurement organization, a material ID, a total quantity and other procurement information; querying and matching the quota agreement according to the procurement plan information, and screening quota agreements meeting the conditions; optimizing the allocation proportion of the quota agreement based on Markov decision, to obtain an optimized allocation proportion; associating the procurement plan with the quota agreement, and dividing the total quantity of the procurement plan into multiple parts according to the optimized allocation proportion, and generating corresponding downstream bills for each divided part.

The application provides a kind of agricultural product order dynamic processing and distribution method based on real-time data, and relates to logistics and supply chain management technical field, it is clustered to order distribution address, and initial distribution cluster is obtained, then initial distribution cluster is sorted according to freshness decay rate, then vehicle is planned in combination with knapsack algorithm, to generate optimal distribution route. In this way, it can reduce the rotting of agricultural products caused by uneven temperature in the carriage during distribution, and the problem of high loss of fresh agricultural products in the distribution link caused by not considering freshness priority when loading agricultural products in the distribution vehicle.

The invention discloses an exhaust system control method. The exhaust system control method comprises the steps that the total exhaust amount Qreq needing to be completed currently of an exhaust system is obtained; the working period of the exhaust system is called; the exhaust air rate is distributed based on the exhaust capacity of the exhaust system and the initial distribution strategy, and the first exhaust air rate Q1 in the valley period and the second exhaust air rate Q2 in the peak period are obtained; based on the total air exhaust amount Qreq, the first air exhaust amount Q1 and the second air exhaust amount Q2, the third air exhaust amount Q3 of the ordinary period is obtained; performing executable judgment on the third exhaust air rate Q3, and respectively confirming target exhaust air rates in a low ebb period, a peak period and a normal period on the basis of a judgment result; and the working time of the exhaust system is monitored, and the corresponding target exhaust air rate is executed according to the working time period to which the working time belongs. According to the invention, on the premise that the exhaust demand is realized, excessive power resources and power consumption cost are not wasted additionally, and under the condition that the distribution strategy is executable, the power consumption peak avoidance demand is considered, and the power consumption safety is further realized.

The present disclosure provides a method for managing allocation of compute resources in a distributed database. Each request on every task is allocated a certain number of tokens when it arrives, such as by using a token bucket algorithm. This initial allocation may be the per-request maximum usage permitted in the system. This request is made to a central quota server in the region to coordinate allocations between tasks. As the task runs, the system evaluates how much of the limit the request is using, and adjusts its limit up or down to keep the quota allocation tight on the actual usage of the request. If there aren't enough tokens to keep the request active, the request can be evicted.

This invention relates to the field of space debris environment modeling technology, specifically to a short-term evolution method for continuum disintegration debris based on numerical methods. The method includes: Step 1, establishing an initial distribution model of disintegration debris, including a disintegration debris velocity increment model and a numerical model of the initial distribution of disintegration debris; Step 2, sampling feature points of the continuum using a gradient-based sampling method, selecting the top N samples with the highest L2 norm scores of the gradient vectors as feature points of the continuum to be evolved; Step 3, processing the continuum equations using numerical solutions, considering the six orbital roots and four perturbation factors to perform short-term evolution of feature points; Step 4, reconstructing the final state distribution of disintegration debris using a Student's t-mix model. This invention fills the gap in previous research in this field, which only focused on ultra-short-term and long-term evolution, and has the beneficial technical effects of requiring fewer samples, having lower computational costs, shorter computation time, higher result accuracy, and stronger robustness.