5 results about "Demand modeling" patented technology

This invention relates to the field of artificial intelligence technology and discloses a method and system for optimizing feed formulation for caged laying ducks. The method includes collecting multidimensional dynamic data and environmental parameter data of caged laying ducks; preprocessing and extracting features from the collected multidimensional dynamic data and environmental parameter data to generate standardized dynamic feature data and environmental stress factor data of laying ducks; and constructing a process flow that includes data collection, feature extraction, demand modeling, formula optimization, precise execution, feedback evaluation, and iterative updates, and building a corresponding collaborative system to achieve closed-loop optimization from perception, decision-making, execution to feedback, so that the feed formulation can be dynamically adjusted according to the real-time status of the laying ducks and environmental changes.

The application provides a modeling and model conversion method for automatic driving demand analysis, comprising the following steps: step 1, defining a UML extension meta-model; step 2, obtaining an intermediate model; and step 3, generating a target extension model. The application combines the abstracted concepts with the UML analysis model by analyzing and extracting the automatic driving related terms and concepts and the behavior characteristics of the automatic driving vehicle, realizes the extension of the UML class diagram and the activity diagram in the automatic driving field, formulates the model conversion rules according to the automatic driving concepts of the automatic driving system limited use case modeling language, and realizes the model conversion method based on the model conversion engine written in the Java language, so that the defects that the general model conversion method cannot process the RUCM4ADS model are made up, the efficiency and accuracy of the model conversion in the automatic driving field are promoted, the subsequent analysis and testing of the system demand are facilitated, and the accuracy of the demand modeling in the automatic driving field is improved.

This invention discloses a method for optimizing the operating costs of low-altitude infrastructure based on a quantitative engineering model, comprising the following steps: obtaining a structured dataset; constructing a set of operating elements for low-altitude infrastructure; establishing a quantitative engineering model; performing demand modeling and load analysis to obtain the demand distribution of the service area set on a time series set; establishing an operating cost optimization model; solving the operating cost optimization model using a symplectic geometrical structure-preserving optimization algorithm to obtain resource allocation results and operation scheduling results; performing simulation evaluation to obtain operating cost results and resource utilization rate indicators, and updating the parameters of the quantitative engineering model; outputting the operating cost optimization results to improve resource utilization and demand satisfaction rate, and enhance the stability and intelligence level of the low-altitude infrastructure system operation.

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.