24 results about "Decision-making models" patented technology

This invention provides an industrial control method and system based on anthropomorphic thinking chain and hybrid expert model, including: Step S1: Based on the operator's thinking decision points and decision chain when controlling the equipment, construct a decision model based on anthropomorphic thinking chain and multi-layer hybrid expert model for each process segment in the complete production chain; Step S2: Train the decision model of each process segment using historical data to obtain the trained decision model; Step S3: Use the trained decision model to obtain the control setpoint based on the real-time sensing data of the corresponding process segment.

Reliance on cloud-based decision-making presents several challenges. To address at least some of these technical challenges, an example system is provided. The system includes an edge computing device including a decision-making model. The system also includes at least one local sensor coupled to the edge computing device through a localized network, wherein the at least one local sensor is disposed in a physical environment. The system also includes at least one local device coupled to the edge computing device through the localized network, wherein the at least one local device is disposed in the physical environment. The edge computing device is configured to: receive, from the at least one local sensor, audio data associated with the physical environment; determine, responsive to the audio data, a state associated with the physical environment using the decision-making model; and determine, based on the state, an instruction for the at least one local device.

This invention provides a multi-level automated data governance system based on knowledge graphs, relating to the field of knowledge graph technology. The system includes: a knowledge graph module for constructing a knowledge graph, wherein the knowledge graph is used to represent multiple entity data and their relationships, and the entity data includes data generated by device entities, system components, and software modules; a graph information module for acquiring graph information based on the knowledge graph; an importance weight module for determining the importance weight of each entity data in the hierarchical structure based on the knowledge graph; a state evaluation module for determining the state evaluation value of each entity data based on the importance weight and graph information; and a final governance module for processing the importance weight and graph information through a trained decision model to generate a governance strategy for the corresponding entity data if the state evaluation value exceeds a preset state evaluation value threshold. According to this invention, the effectiveness and accuracy of multi-level automated data governance can be improved.

A virtual character action decision-making method includes: obtaining state information, the state information representing a game battle state of a game battle in which a first virtual character is involved; inputting the state information to an action decision-making model, to obtain n target sub-actions serially outputted by n action output heads in the action decision-making model, different action output heads corresponding to different action types, the n action output heads being serially connected based on a dependency relationship between the action types, and the dependency relationship representing a dependency restriction situation between sub-actions under different action types; and controlling the first virtual character to execute a target action formed by the n target sub-actions.

This invention discloses a spacecraft autonomous mission decision-making method for complex stochastic tasks, belonging to the field of spacecraft mission decision-making technology. The method includes the following steps: S1, establishing a spacecraft mission decision-making model considering disjoint robustness; S2, transforming the model into a two-stage optimization framework problem; S3, introducing fuzzy sets to perform cone optimization transformation on the second-stage decision; S4, transforming the model into a numerically solvable cone optimization problem based on duality theory; S5, solving the cone optimization problem to complete mission scheduling. This invention adapts uncertainty through WKS-format fuzzy sets, combines resource consumption matrices and affine decision rules to avoid resource mismatch, significantly improving the efficiency and robustness of spacecraft mission decision-making and meeting the requirements of real-time dynamic scheduling.

The application discloses a method for training a construction management decision model based on reinforcement learning, comprising: obtaining initial construction parameters of a target construction project and historical environmental parameters of a region where the target construction project is located; wherein the target construction project is a construction project to be planned for worker hours and material purchase quantity; constructing a construction project simulator based on the initial construction parameters and the historical environmental parameters as basic data; simulating observation trajectories, action trajectories, state trajectories and incentive sequences related to the construction process according to the construction project simulator; and optimizing a decision model of a preset structure according to the observation trajectories, the action trajectories, the state trajectories and the incentive sequences, so that the optimized decision model can be used for planning worker hours and material purchase quantity. The application also discloses a method for planning worker hours and material purchase quantity based on reinforcement learning, a construction project simulator and a computer readable storage medium.

The application provides a kind of ontology driven multi-agent decision-making method and device, comprising: collecting the multi-source heterogeneous data of disaster site and related business system;Based on the disaster emergency ontology constructed in advance, the multi-source heterogeneous data is processed to form a unified object model;According to the unified object model, the state space, action space, objective function and constraint condition of the multi-agent decision-making model are constructed, and the agent participating in decision-making is established;Based on the multi-agent decision-making model, drive multiple agents to carry out collaborative deduction, generate at least one candidate disposal scheme;According to the preset multiple evaluation indexes, the candidate disposal scheme is solved, screened and sorted to obtain the target decision scheme;The target decision scheme is issued to the execution node, and the state feedback is continuously recycled in the execution process, and incremental updating is carried out based on the recycled state feedback, and the local re-solution or global re-planning of the multi-agent decision-making model is triggered, to form a closed-loop emergency disposal decision.

This invention relates to the fields of computer technology and railway construction technology, specifically to a method for constructing an AI-powered intelligent auxiliary decision-making model for early intervention in railway construction. The method includes the following steps: constructing an intelligent question-answering model, constructing an intelligent data mining model, constructing an intelligent algorithm model for intervention mechanisms, and integrating the algorithm models with an information platform. This invention solves the problem of low efficiency in manual management and retrieval by intelligently summarizing and integrating key information through an intelligent question-answering model; it solves the problem of difficulty in mining and deeply analyzing the intrinsic value of data by constructing an intelligent data value mining model that is seamlessly integrated and efficiently linked with a knowledge base; it improves the auxiliary decision-making capability by constructing an intelligent algorithm model for intervention mechanisms; and it solves the problem of the lack of data security and data governance guarantee mechanisms by deeply integrating the intelligent question-answering model, the intelligent data value mining model, and the intelligent algorithm model for intervention mechanisms and constructing a distributed platform architecture.

The present disclosure provides systems, methods, and computer program products for explaining decision models. An example method may comprise (a) using a decision model to predict an action that a sales representative should take to maximize a target variable, wherein the decision model comprises a plurality of sub-models comprising a channel affinity sub-model and a content affinity sub-model; and (b) applying an explainability model to the decision model to generate one or more predictors or drivers of the output of the decision model, wherein the one or more predictors or drivers (1) are features of the channel affinity sub-model and / or the content affinity sub-model and (2) provide an explanation of an effect of the action on the target variable.

The embodiment of the application provides a kind of policy claim data screening method and device, electronic equipment and storage medium, belong to artificial intelligence technical field, apply to financial scene.The method comprises: obtaining policy claim multi-modal data, wherein the policy claim multi-modal data includes policy claim event data and claim result data;Based on the pre-constructed claim decision model, the policy claim event data is predicted, and the model claim decision is obtained;Based on the claim result data and the model claim decision, causal effect evaluation is carried out, and the causal effect evaluation data is obtained;The positive and negative fact difference of the policy claim event data is calculated, and the positive and negative claim difference data is obtained;Based on the causal effect evaluation data and the positive and negative claim difference data, high-quality data screening is carried out on the policy claim multi-modal data.The quality of the screened policy claim data is improved.

This invention relates to the field of financial data processing and discloses a method and system for investigating corporate economic crimes. The method includes: structuring raw transaction data; extracting multi-dimensional behavioral features such as transaction time, monetary value, and sentimental comments; constructing a psychological decision-making model based on behavioral economics prospect theory and generating a psychological graph of the transaction subject using Bayesian network inference; matching the psychological graph with known suspect feature templates to identify controlled accounts; reconstructing the virtual fund control path based on the logical association of physical breakpoints in the similarity of psychological decision-making patterns and outputting a report. The system includes a data acquisition module, a preprocessing engine, a psychological feature extraction unit, a behavioral economics inference module, an association comparison engine, and a report output terminal. This invention improves investigative efficiency.

The invention relates to a method for determining the recruitment process of pilots using artificial intelligence-based fuzzy multi-criteria decision-making models, which creates an artificial intelligence-based decision-making model by considering numerous criteria such as socio-cognitive abilities, performance competencies, communication skills, visual perspective perception, and spatial working range in the selection process of airline pilots; processes and evaluates uncertain, vague, and subjective data with fuzzy logic techniques (fuzzy TOPSIS, fuzzy VIKOR, and fuzzy PROMETHEE) and enables the ranking of candidates; transforms non-numerical linguistic terms into fuzzy mathematical models; ensures the integration of qualitative and quantitative data and the transformation of uncertain data into reliable results in pilot selections; facilitates the successful ranking of candidate pilots and the selection of competent personnel for safe operations by companies; improves the recruitment process of pilots and utilizes an artificial intelligence-based decision-making model application in their selection

The application provides an autonomous finance and tax intelligent agent system based on an ontology matrix and an implementation method. The system comprises: a dispatching hub module for receiving a finance and tax task request, generating a task context comprising a task identifier, an enterprise identifier and an accounting period, and arranging a task execution process; an ontology service module for storing and managing the ontology matrix; a decision service module for storing and executing a decision model, the decision model comprising finance and tax business rules and human-machine collaboration boundary rules; an audit service module for generating, storing and verifying a full-process decision evidence chain, the decision evidence chain being implemented by a hash chain to prevent tampering; and an execution layer module for executing specific finance and tax operations according to the output of the decision service module. The application separates the ontology matrix and the DMN decision model, so that the finance and tax rules are independently stored and dynamically updated in the form of standardized decision models, and the policy changes can be quickly responded without modifying the code, thereby greatly reducing the maintenance cost.

Reliance on cloud-based decision-making presents several challenges. To address at least some of these technical challenges, an example system is provided. The system includes an edge computing device including a decision-making model. The system also includes at least one local sensor coupled to the edge computing device through a localized network, wherein the at least one local sensor is disposed in a physical environment. The system also includes at least one local device coupled to the edge computing device through the localized network, wherein the at least one local device is disposed in the physical environment. The edge computing device is configured to: receive, from the at least one local sensor, audio data associated with the physical environment; determine, responsive to the audio data, a state associated with the physical environment using the decision-making model; and determine, based on the state, an instruction for the at least one local device.

This invention provides an auxiliary decision-making method and system for the renovation of cultural relic-related water conservancy facilities, belonging to the field of water conservancy engineering management technology. The decision-making method achieves quantitative collaborative decision-making for the dual objectives of engineering safety and cultural relic protection, transforming the qualitative requirements of cultural relic protection into structured data that can be calculated alongside engineering indicators, thus overcoming the previous decision-making dilemma of separating these two dimensions. It establishes a complete technical closed loop from assessment to design, decomposing complex decision-making problems into three logically clear stages: functional zoning, strategy optimization, and structural matching, ensuring the rigor and traceability of the decision-making logic. The introduction of a dual-loop feedback mechanism significantly improves the rationality throughout the entire lifecycle. The inner loop feedback ensures the mechanical consistency between the design scheme and the decision-making objectives, avoiding performance deviations during the design phase; the outer loop feedback uses actual operation and maintenance data to back-optimize the initial decision-making model, enabling the system to have self-learning and self-evolution capabilities.

The application relates to a zero-carbon park electric-carbon transaction and multi-agent collaborative decision-making method, and belongs to the technical field of power systems and multi-agent game, which comprises the following steps: establishing a park multi-agent collaborative optimization decision-making model based on asymmetric Nash bargaining; establishing a target function and operation constraint of the model, and introducing a coalition cost minimization problem and an individual payment benefit maximization problem as model equivalent problems; in the solving process of the model equivalent problems, a penalty parameter is dynamically adjusted in a specific local range according to the relative relationship between original residual errors and dual residual errors; and after the coalition cost minimization problem and the individual payment benefit maximization problem are sequentially calculated to convergence, the operation decision of each zero-carbon park is obtained, optimal resource allocation is realized, and the electric-carbon collaborative transaction, multi-agent game and distributed optimization theory are combined, so that the system operation efficiency and the low-carbon operation level are improved while the fairness of the interests of all participants is ensured.

The application discloses a kind of ship selective maintenance decision-making method under the condition of multi-resource constraint multi-stage task, comprising the following steps: step A: constructing ship multi-stage task description model;Step B: constructing ship equipment reliability model;Step C: constructing ship maintenance decision-making model framework;Step D: based on ship maintenance decision-making model, solve maintenance scheme.The application also discloses a kind of ship selective maintenance decision-making system under the condition of multi-resource constraint multi-stage task.The application provides scientific basis for subsequent ship selective maintenance decision-making, guarantees the successful execution of maintenance task, and can be widely applied in the field of digital technology.

The application discloses a power spot market bidding decision-making method considering bias assessment, and belongs to the technical field of power market transaction decision-making. The method comprises the following steps: acquiring benchmark transaction parameters of arbitrage bidding and market bias income recovery rules; constructing a settlement net income model of arbitrage bidding, wherein the net income model models the bias income recovery rules as a function affecting net income; constructing a distribution robust optimization model considering market price difference prediction uncertainty, wherein the distribution robust optimization model is based on the net income model and takes arbitrage bidding quantity as a decision variable; and solving the distribution robust optimization model to output the optimal arbitrage bidding quantity. The application embeds market segmented bias income recovery rules in the decision-making model, and adopts a distribution robust optimization framework to cope with uncertainty, thereby achieving the technical effect of significantly improving decision-making robustness and income calculation accuracy under the premise of strict compliance.

This specification provides a training method and a decision-making method for a decision model. The training method includes: acquiring training sequence data; inputting the training sequence data into an initial decision model to obtain predicted sequence data output by the initial decision model, wherein the predicted reward parameter is predicted based on multiple reward parameters; determining the target loss of the initial decision model based on the training sequence data and the predicted sequence data, wherein the target loss includes action loss, multi-attribution loss, and quantile loss, the action loss being determined based on action parameters and predicted action parameters, and the multi-attribution loss and quantile loss being determined based on reward parameters, predicted reward parameters, and predicted surplus parameter information; and adjusting the parameters of the initial decision model based on the target loss of the initial decision model to obtain a decision model. According to this specification, the bidding method is optimized through the decision model.

This invention discloses a decision-making method and system for power generators in the carbon market that considers cash flow, relating to the field of decision optimization in the power market and carbon trading market for power companies. It addresses the collaborative decision-making problem and cash flow modeling problem in the power market and carbon market for power companies. The method includes the following steps: establishing a year-round stochastic decision-making model for the power-carbon market with cash flow constraints; then, using mixed time-step modeling to reduce decision variables while still describing the cash settlement cycle, and simplifying the multi-stage stochastic optimization model into a two-stage stochastic optimization model for easier solution; finally, addressing the problem of frequent speculative trading in the second stage of the traditional two-stage model by adding a one-way carbon market trading rule, and addressing the problem of the two-stage model's underestimation of future carbon purchase costs by adding a timing trading rule. This method fully utilizes the characteristics of the power-carbon market decision-making process, ensures cash flow security, effectively reduces the carbon purchase costs for power generators, and improves overall profitability.

The application relates to the technical field of group decision-making, and discloses a group decision-making model based on enterprise management and preference relation relative projection, which comprises a data acquisition and initialization module, a group synthesis and consensus evaluation module, a double-drive dynamic weight calculation module, an expert mutual evaluation relation updating module and an iterative convergence and decision generation module, and can acquire an initial preference relation matrix and a mutual evaluation matrix; a group synthesis preference matrix is constructed based on current expert weights, and a global consensus level is analyzed; the objective consensus contribution degree and the subjective social trust degree of the experts are calculated, then the expert weights are updated by fusion, and the mutual evaluation matrix is updated; iteration is performed until convergence, a decision scheme ranking and an expert weight distribution report are generated based on the final group synthesis preference matrix; and the group decision-making efficiency based on enterprise management and preference relation relative projection can be improved.