Patents
Literature
16 results about "Discrete choice" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
In economics, discrete choice models, or qualitative choice models, describe, explain, and predict choices between two or more discrete alternatives, such as entering or not entering the labor market, or choosing between modes of transport. Such choices contrast with standard consumption models in which the quantity of each good consumed is assumed to be a continuous variable. In the continuous case, calculus methods (e.g. first-order conditions) can be used to determine the optimum amount chosen, and demand can be modeled empirically using regression analysis. On the other hand, discrete choice analysis examines situations in which the potential outcomes are discrete, such that the optimum is not characterized by standard first-order conditions. Thus, instead of examining “how much” as in problems with continuous choice variables, discrete choice analysis examines “which one.” However, discrete choice analysis can also be used to examine the chosen quantity when only a few distinct quantities must be chosen from, such as the number of vehicles a household chooses to own and the number of minutes of telecommunications service a customer decides to purchase. Techniques such as logistic regression and probit regression can be used for empirical analysis of discrete choice.
Resource aggregation scheduling method and device for multi-element flexible resource virtual power plant and medium
The invention discloses a resource aggregation scheduling method and device for a multi-element flexible resource virtual power plant and a medium, and relates to the field of power system operation control, and the method comprises the steps: constructing a virtual power plant multi-target collaborative aggregation optimization model; decision variables of the optimization model comprise a discrete selection variable, a continuous power variable and a satisfaction variable; on the basis of the model, a hybrid architecture combining a deep Q network and near-end strategy optimization is adopted, and a virtual power plant aggregation decision-making agent is constructed; the mixed action space of the intelligent agent is jointly formed by a discrete selection variable and a continuous power variable; in the virtual power plant operation simulation platform, training an intelligent agent through experience playback and a target network mechanism, and constructing real-time state data of the virtual power plant into an instance of a state space; and inputting the instance of the state space into the trained agent to generate a target aggregation scheduling strategy. According to the method, joint optimization of two types of decisions is realized through an intelligent agent of a hybrid architecture, and a scheduling strategy scheme is ensured to approach global collaborative optimization.
Owner:STATE GRID SICHUAN ECONOMIC RES INST
Black box code search model backdoor attack method based on learnable discrete code transformation
PendingCN121659308APlatform integrity maintainanceNeural learning methodsGeneration processAlgorithm
A black box code search model backdoor attack method based on learnable discrete code transformation comprises the steps that a learnable backdoor generator is constructed, and malicious codes with backdoors are generated on the premise that internal parameters of a damaged model are not accessed through the learnable discrete code transformation. Firstly, an agent model capable of simulating victim model behaviors is trained through query-response data; secondly, on the proxy model, a discrete selection process is differentiable by using a re-parameterization sampling technology, and a backdoor generator is trained in combination with a multi-objective loss function so as to realize effectiveness and concealment of backdoor implantation; according to the method, the limitation of a black box is successfully bypassed by constructing the proxy model, and a new possibility is provided for an attacker. A backdoor generation process is integrated into a differentiable training framework through learnable discrete transformation, so that end-to-end learnability is realized, and an attack strategy can be automatically optimized.
Owner:NANJING UNIV OF POSTS & TELECOMM
Observation satellite multi-target planning method and system based on mixed action space
The invention provides an observation satellite multi-target planning method and system based on a mixed action space, and the method comprises the steps: describing an agile satellite comprehensive task planning problem, and constructing a satellite comprehensive task planning model based on continuous decision making; providing a multi-target deep reinforcement learning method based on a mixed space, and training a satellite comprehensive task planning model based on continuous decision by using the method; and performing task planning by using the trained satellite comprehensive task planning model based on the continuous decision. According to the method, aiming at the complex and emergent task condition of a target and the characteristics of large solving space and low search speed of an agile satellite task planning comprehensive problem, a multi-target problem model is established based on reinforcement learning, and a reinforcement learning method based on a gradient strategy mixed space is introduced to solve the satellite comprehensive task planning problem; therefore, discrete selection in continuous time is made, and data transmission and observation tasks can be arranged at the same time due to the existence of the mixed action space.
Owner:INNOVATION ACAD FOR MICROSATELLITES OF CAS +1
Multi-agent simulation analysis method for operation optimization of urban parking system
PendingCN120633895AInternal combustion piston enginesForecastingDriver/operatorTransport engineering
The invention provides a multi-agent simulation analysis method for operation optimization of an urban parking system, and the method comprises the following steps: S1, obtaining influence factors which remarkably influence the parking selection behavior of a driver through questionnaire design and experiment based on will survey; s2, through a Binomial Logit discrete selection model, carrying out quantitative analysis on the influence factors of the parking selection behavior of the driver; s3, building a multi-agent parking lot microscopic simulation platform in combination with a Netlogo development environment; and S4, constructing a double-layer model for parking lot operation management optimization, and solving by adopting a simulated annealing algorithm. On the basis of analyzing the parking selection behavior of the driver, the operation efficiency of the parking lot is effectively improved through multi-agent simulation, and a technical tool is provided for operation organization and management strategy evaluation of the parking lot.
Owner:TONGJI UNIV
Charging load probability spatiotemporal distribution prediction method considering random fluctuations of commuting demand
This application belongs to the field of power system management, specifically disclosing a method for predicting the spatiotemporal distribution of charging load probabilistically, taking into account the random fluctuations in commuting demand. This application constructs a multi-dimensional travel strategy set to simulate users' comprehensive decisions regarding energy, time, and space. Uncertainty is introduced from the commuting demand side, and Monte Carlo sampling is used to generate demand fluctuation samples, fundamentally characterizing the random fluctuations in load. A utility evaluation model is constructed based on cumulative prospect theory to correct for users' bounded rationality characteristics. A multi-layered nested discrete choice model is adopted, decomposing the decision into three levels: charging, departure, and route, and iterating to traffic network equilibrium using a heuristic algorithm. In the equilibrium state, the strategy selection ratio is combined with the demand sample, input into the dynamic traffic network model, and the spatiotemporal probability distribution of charging load is output. This achieves more accurate prediction of the spatiotemporal distribution of electric vehicle charging load probabilistically during evening peak hours, providing a scientific basis for charging facility planning and grid dispatching.
Owner:HUAZHONG UNIV OF SCI & TECH
A method for predicting highway transfer traffic volume based on discrete choice model
ActiveCN119479313BDetection of traffic movementNeural learning methodsTraffic predictionPredictive methods
The present invention discloses a method for predicting highway transfer traffic based on a discrete selection model, comprising: obtaining environmental data of a target highway, collecting environmental data and traffic data of a traffic network, and establishing a traffic network model; performing dynamic time window division on the traffic data to obtain window data, and predicting the window data to obtain predicted window data; performing an impact analysis on the window data based on the environmental data to obtain an environmental selection probability, and obtaining predicted highway transfer traffic based on the predicted window data and the environmental selection probability based on a discrete selection model; constructing a highway transfer traffic prediction model based on the predicted highway transfer traffic, inputting the highway data to be analyzed into the highway transfer traffic prediction model, and outputting a prediction result. The method can not only improve the accuracy of highway transfer traffic prediction, but also has good interpretability, and can be directly applied to a highway transfer traffic prediction system.
Owner:TRANSPORT PLANNING & RES INST MINIST OF TRANSPORT
Information processing method and information processing program
To make it easy to learn a discrete choice model capable of accurately estimating which option is chosen by a choosing subject from among a plurality of options.SOLUTION: An information processing apparatus sets an expected value of a probability that a choosing subject that has chosen an option J in the past belongs to a class 501 such that the choosing subject definitely belongs to class 501. The information processing apparatus sets an expected value of a probability that a choosing subject that has not chosen the option J in the past belongs to the class 501 such that the choosing subject probabilistically belongs to class 501 and class 502 and that the probability that the choosing subject belongs to the class 501 decreases as the effect of the option J increases. The information processing apparatus estimates parameters of a choice model 511 and a choice model 512 based on the record representing an option chosen by each choosing subject in the past and each set expected value.SELECTED DRAWING: Figure 5
Owner:FUJITSU LTD
A civil aviation passenger profiling method integrating discrete choice model and knowledge graph
ActiveCN117876000BComprehensive recognitioncomprehensive collectionKnowledge representationCommerceCivil aviationKnowledge graph
The present invention proposes a civil aviation passenger portrait method that integrates discrete choice models and knowledge graphs, including: determining the entities and relationships in the field of civil aviation passenger portraits, and constructing the knowledge ontology of the civil aviation passenger portrait graph; designing a virtual waiting experimental system to collect information while simulating the geographical environment and waiting situation of a virtual terminal; calibrating and analyzing the parameters of civil aviation passenger needs based on a discrete choice model, and forming a preliminary selection probability annotation; processing information, and constructing a visualized civil aviation passenger portrait knowledge graph; using a query language to query and analyze the civil aviation passenger portrait knowledge graph, and characterizing and analyzing the individual and group portraits of civil aviation passengers based on knowledge graph technology. This method has a strong explanatory power for civil aviation passenger behavior decisions, while linking the airport environment and individual passengers, accurately perceiving passenger needs, and comprehensively characterizing individual and group portraits of civil aviation passengers.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
A low-carbon oriented multi-category vehicle route guidance method under MaaS background
This invention discloses a low-carbon-oriented multi-category vehicle routing induction method under the MaaS (MaaS) context, comprising the following steps: S1, calculating the marginal travel time of multiple vehicle categories; S2, determining a carbon emissions formula and then calculating marginal carbon emissions; S3, constructing routing pricing rules that meet the carbon reduction induction requirements; S4, determining factors influencing customer choices and then constructing a discrete choice model using a binomial logit model; S5, using simulation software to simulate an actual road network and then evaluating key indicators. This invention can effectively reflect the impact of changes in platform pricing strategies on transportation carbon emissions.
Owner:SOUTHEAST UNIV
Method for machine learning and computer-readable recording medium having stored therein machine learning program
A method for machine learning includes training a neural network including parameters, at least some of the parameters having a structure corresponding to an order and a coefficient of an explanatory variable of a utility function of a discrete choice model, using training data including a value of the explanatory variable and a choice result; and specifying the utility function in the neural network after being subjected to the training.
Owner:FUJITSU LTD
A modeling method for passengers' connection mode selection behavior under sudden subway disruption
ActiveCN118798062BBreak through the limitations of incompletenessComprehensive behavioral explanationDesign optimisation/simulationNeural learning methodsSimulationBehavioral modeling
The present invention relates to a modeling method for passenger connection mode selection behavior under sudden subway interruption, and belongs to the technical field of passenger emergency connection mode selection behavior. The method obtains the attribute information of sudden subway interruption, determines various types of central stations in the urban subway network, analyzes the explanatory variables that affect the selection of passenger connection modes under sudden subway interruption, calculates the standardized influence weights of various psychological latent variables on the selection behavior of passenger subgroups with various attributes, analyzes the nonlinear relationship between the explanatory variables and the passenger psychology, identifies the key explanatory variables that affect the overall passenger psychology to divide the blocked passenger subgroups, constructs the discrete choice model utility function of the heterogeneous passenger subgroups, and further establishes a connection mode selection behavior model that considers the passenger psychology. The present invention can reveal the impact mechanism of sudden subway interruption events on the psychology of different passenger groups, and realize the reasonable prediction of the passenger connection mode selection behavior after the subway interruption.
Owner:FUZHOU UNIV
Methods and apparatus to reduce signal-to-noise ratio (SNR) of monadic scores
Methods and apparatus disclosed herein reduce signal-to-noise ratio (SNR) of monadic scores. An example apparatus to reduce a signal-to-noise ratio (SNR) of monadic scores, the apparatus includes memory, machine readable instructions, and processor circuitry to execute the machine readable instructions to at least identify a discrete choice probability of selection corresponding to a first product, generate a scale question corresponding to the first product, calculate a monadic probability corresponding to the first product based on the scale question for the first product, and reduce the SNR of the monadic probability by joining the discrete choice probability of selection of the first product with the monadic probability of selecting the first product.
Owner:NIELSEN CONSUMER LLC
A comprehensive traffic assignment method based on mobile phone signaling
The present invention discloses a comprehensive traffic distribution method based on mobile phone signaling, which uses mobile phone signaling data to solve the parameter estimation and parameter calibration problems of the comprehensive traffic random user equilibrium model, specifically including: mobile phone signaling preprocessing; extracting travel OD and travel chain data; building a comprehensive integrated traffic network and travel cost function; generating a travel path selection set; building a discrete choice model based on generalized selection; estimating parameters using the maximum likelihood estimation method; building a random user equilibrium model and using the MSWA algorithm to solve it; building and training a support vector regression model, if the accuracy does not meet the requirements, adjusting the parameters and retraining; combining the trained model with the STA_GA algorithm to solve the optimal parameters. The present invention can give full play to the advantages of mobile phone signaling data, improve the accuracy of traffic distribution of the comprehensive traffic random user equilibrium model, improve the efficiency of model parameter calibration through machine learning, and better provide a scientific basis for regional traffic planning and management.
Owner:CHINA DESIGN GROUP CO LTD
A method for generating travel activity chains based on nested dynamic discrete choice
The present invention discloses a travel activity chain generation method based on nested dynamic discrete choice, comprising the following steps: S1, defining the parameters of a dynamic discrete choice model, and constructing a traveler's full-day travel activity chain model; S2, defining a state transfer matrix, and establishing a connection between the state-choice pairs of consecutive stages; S3, deriving the expected utility function of the traveler in each stage based on the rational traveler and the utility maximization decision criterion; S4, defining the distribution of disturbance terms, and obtaining a nested dynamic discrete choice model with a closed form; S5, defining an immediate utility function according to the selection characteristics, and calculating the option-specific utility function; (6) estimating the parameters of various immediate utility functions in step (5), and generating a travel activity chain. The present invention introduces the distribution of disturbance terms based on the nested choice model to characterize the choice correlation of travel modes, and can better predict the complete travel activity chain of travelers.
Owner:SOUTHEAST UNIV
Graphical User Interfaces and Computing Systems for Contextual Discrete Choice Experiments
A computing system obtains multiple factors for a first environment in a first experiment. The multiple factors include one or more profile factors and one or more subject factors. Each profile factor of the one or more profile factors specifies multiple candidate features for the first environment. Each subject factor of the one or more subject factors specifies multiple candidate levels categorizing different subjects interacting with the first environment. The computing system obtains a predictive model for predicting probabilities of multiple candidate outcomes for the first environment. The predictive model has weighted model terms. The computing system receives a selection of a first level for a first subject factor of the one or more subject factors. The computing system generates a computer-generated representation of a fixed-factor model. The fixed-factor model predicts multiple candidate outcomes for a second environment with subjects defined by the selection of the first level.
Owner:JMP STATISTICAL DISCOVERY LLC
Hybrid action space based multi-target planning method and system for observation satellites
The application provides a kind of observation satellite multi-objective planning method and system based on hybrid action space, wherein the method comprises: describing agile satellite integrated task planning problem, constructing satellite integrated task planning model based on continuous decision;A multi-objective deep reinforcement learning method based on hybrid space is provided, which is used to train the satellite integrated task planning model based on continuous decision;The trained satellite integrated task planning model based on continuous decision is used for task planning.The application is aimed at the characteristics of complex and sudden task conditions and the large search space and slow search speed of agile satellite task planning integrated problem, establishes a multi-objective problem model based on reinforcement learning, introduces a reinforcement learning method based on gradient policy hybrid space to solve the satellite integrated task planning problem, and then makes a discrete choice in continuous time.Due to the existence of hybrid action space, data transmission and observation tasks can be arranged simultaneously.
Owner:INNOVATION ACAD FOR MICROSATELLITES OF CAS +1