38 results about "Decision maker" patented technology

The present application relates to the technical field of data analysis, in particular to a SaaS customer renewal prediction method and system based on behavior hidden vector. The method comprises the following steps: collecting multi-dimensional behavior data of decision makers of a target SaaS customer on a collaboration platform, the multi-dimensional behavior data including document collaboration behavior, meeting participation behavior, task collaboration behavior and information retrieval behavior, wherein the decision maker is a senior manager in the target SaaS customer enterprise who undertakes the procurement decision-making responsibility. The present application collects the multi-dimensional behavior data of the senior manager who undertakes the procurement decision-making responsibility in the target SaaS customer on the collaboration platform, trains a collaboration behavior embedding model based on a contrastive learning framework, maps the multi-dimensional behavior data to a behavior hidden vector representation capable of representing the collaboration preference and participation depth of the decision maker, and accurately captures the implicit renewal intention signal of the decision maker without reading any chat content and private data.

This invention relates to the field of electrical digital data processing technology, specifically a TCR measurement method based on high and low temperature region data fusion using an improved particle swarm optimization algorithm. The method inputs the original time-series data from the high and low temperature regions, removes noise and outliers using isolated forest and Grubbs criterion, and maps the data to a unified temperature domain grid using piecewise Lagrange interpolation. An ergodic sequence is generated using Logistic chaotic mapping to initialize the particle swarm position vector, which is then transformed into node coordinate parameters in geometric space, and a cubic basis spline fitting curve is constructed. Particle fitness is evaluated using the sum of squared residuals and curvature smoothness as constraints. During iteration, the average Euclidean distance from the particle to the swarm centroid is calculated to generate a spatial dispersion factor. A multi-interval weighted decision maker based on the Mamdani framework is used to identify probe, development, convergence, and escape states, dynamically adjusting the inertia weights accordingly. This effectively solves the problems of data fragmentation and premature convergence, ultimately outputting a continuous and smooth resistance temperature coefficient distribution across the entire temperature domain.

This application relates to a consensus-based Pareto alliance conflict analysis method, apparatus, equipment, and medium, belonging to the field of emergency rescue decision-making technology. The method includes: constructing a conflict graph model of emergency rescue conflicts; constructing a consensus-based Pareto alliance improvement matrix for focal alliances based on the alliance division results and the conflict graph model; under the condition that the focal alliances do not know the alliances of their opponents, constructing the alliance domain composed of the entire alliance of opponents and the entire alliance set, and constructing a corresponding consensus-based hybrid Pareto alliance improvement matrix, while dividing the alliances into trusted and untrusted opponent alliances; constructing consensus-based Pareto alliance stability judgment rules under hybrid countermeasures, and performing stability analysis to obtain the equilibrium result of emergency rescue conflicts, assisting decision-makers in executing emergency rescue decisions. This method can effectively improve the rationality, feasibility, and practicality of emergency rescue conflict coordination schemes.

This invention discloses a knowledge distillation visual recognition method and system based on distillation weights. The method includes constructing a multi-teacher distillation system comprising multiple teacher networks and one student network, building a corresponding intelligent agent network for each teacher network; pre-training the student network and simultaneously pre-training the intelligent agent network; constructing a multi-dimensional state vector; inputting the multi-dimensional state vector into the corresponding intelligent agent network to generate distillation weights for the corresponding teacher network on the current data sample; constructing a multi-teacher distillation loss function to update the parameters of the student network; after completing a batch of student network updates, calculating a reward signal based on the student network performance improvement index, and updating the parameters of the intelligent agent network based on the reward signal. This invention introduces an intelligent agent network as a weight decision-maker, and by constructing a multi-dimensional state vector containing teacher performance and teacher-student gaps, it achieves dynamic adaptive allocation and closed-loop optimization of distillation weights.

The application discloses a multi-target-oriented power distribution network safety domain operation point screening method, medium and equipment, belongs to the field of power system operation and optimal control, and comprises the following steps: firstly, constructing a static safety domain containing a power flow equation and multiple constraints based on power distribution network nodes, branch information and safety criteria; secondly, accurately obtaining a safety domain boundary through adaptive direction search and error correction; thirdly, generating a candidate operation point by Monte Carlo sampling, combining economic and reliable indexes, and obtaining a Pareto optimal solution set through fast non-dominated sorting; finally, screening an optimal operation point considering safety, economy and reliability through fuzzy multi-attribute decision and decision maker preference analysis; the application realizes three-dimensional target collaborative optimization, is high in calculation efficiency and strong in robustness, can adapt to real-time optimization requirements of high-proportion distributed power distribution networks, and can be widely applied to active power distribution network safety evaluation, energy storage configuration and economic dispatching scenes.

The application relates to a supplier cooperation risk automatic identification method, system, device and medium. The method comprises the following steps: firstly, obtaining supplier decision maker historical text data and historical cooperation event logs, extracting decision maker personality characteristic keywords, sentiment tendency and dividing groups to obtain decision maker portrait labels; combining the portrait labels and the historical cooperation event logs, grouping and classifying delivery delays and quality dispute events to obtain correlation mode data; determining preliminary risk labels based on the correlation mode data, extracting quantitative indicators and obtaining a controlled state score through a weighted fusion algorithm; fusing the preliminary risk label quantitative value and the controlled state score to determine the overall risk level of the supplier; finally, obtaining supplier real-time emergency text, identifying keywords and evaluating the impact degree, and updating the overall risk level to obtain a dynamic risk perception result. The method can improve the risk identification accuracy and timeliness, avoid artificial subjective bias and reduce the control cost.

The application discloses a power distribution network multi-party collaborative planning method and system based on reinforcement learning and double-layer game, constructs a double-layer Stackelberg game framework, sets a distribution network operator (DSO) as an upper-layer decision maker, sets a union (MSC) composed of distributed power, energy storage and users as a lower-layer follower, and describes a multi-party competition and cooperation relationship; heterogenous reinforcement learning algorithms are innovatively adopted; a proximal policy optimization (PPO) algorithm is adopted for discrete planning decisions (such as line and equipment site selection) of the DSO; a deep deterministic policy gradient (DDPG) algorithm is adopted for continuous operation decisions (such as capacity configuration and demand response) of the MSC; two intelligent agents are collaboratively trained through a hierarchical iterative game mechanism, and finally converge to an equilibrium strategy. The application can effectively coordinate the interests of all parties, guarantee the safety of the power grid, and improve the overall economy and renewable energy consumption capacity of the system.

This invention discloses an adaptive generation method for spatial analysis reports and a visual decision support system, relating to the fields of data analysis and visualization technology. By establishing a bidirectional dynamic link between the analysis process and the dynamic report, this invention breaks down the disconnect between the analysis process and report output found in traditional technologies. Decision-makers can trace back to specific analysis units and source data from the report content, and can also directly drive intelligent updates to the report by modifying the analysis process, achieving closed-loop decision support. Furthermore, this invention presents the analysis logic, originally hidden in code or operation history, in an intuitive flowchart format. This not only allows decision-makers to clearly understand the derivation process of the analysis conclusions but also supports real-time analysis by modifying process parameters, greatly enhancing decision-making flexibility.

The application discloses a kind of process engine implementation method based on multidimensional approver computing engine, it is related to enterprise management technical field, to Camunda process engine bit as foundation, this kind of process engine implementation method based on multidimensional approver computing engine, by the method, based on Camunda process engine core builds stable and reliable engine layer, on it new approval person configuration, personnel analysis and rule matching etc. Core extension component, user is configured by process designer to select person type and parameter, when process flows to corresponding node, flexible person selection extension layer is driven by event in real time to receive and process signal, by the operation of routing of person decision maker, each resolver query extraction information, program script engine calculation and personnel result summary processor de-duplication and merging, obtain accurate approval person list and pass to basic engine allocation task, flow process, until end, the method improves the flexibility and adaptability of process engine, ensure that process is smoothly and efficiently executed.

A distributed environmental control system comprises control nodes that communicate via wireless mesh networks to predict user movement and automate loads without centralized coordination. Each node executes a local inference engine (Markov model, HMM / DBN, or reinforcement learning policy) to predict occupancy patterns, broadcasts predictions to neighbors, and makes autonomous actuation decisions based on local and shared data. When multiple nodes control loads in a shared zone, a Runtime Actuation Authority mechanism designates a single decision-maker based on most recent manual interaction, with authority epochs and deterministic total order resolution ensuring distributed consistency. The system prevents feedback loops via causal action identifiers, logical timestamps, and recent action caches. Sensor data is transmitted as compressed waveform encodings. A deterministic policy layer enforces safety and comfort constraints. The reinforcement learning embodiment learns household preferences from user feedback, adapting actuation behavior to optimize satisfaction, comfort, and energy efficiency while maintaining safety guarantees.

The application generates a prospective candidate scheme by constructing a dynamic simulation environment fusing vehicle trajectory, node state and repayment willingness and running a sequence decision maker for multi-step deduction; uses a distributed constraint optimizer to couple global benefits and collaborative costs, outputs resource binding and synchronous contracts to realize efficient collaboration; through an online re-planning and incremental instruction issuing mechanism, combined with a concurrent control protocol based on operation transformation, ensures strong consistency in the execution process in dynamic changes; the sequence decision maker is trained adversarially and supplemented with Monte Carlo simulation risk assessment and degraded backup scheme, enhancing the system robustness; finally, the scheme is compiled into node-specific machine code and packaged as an atomic task package for issuance, realizing seamless and efficient conversion from decision to execution, and comprehensively improving the accuracy, collaboration, adaptability and reliability of the collection.

The present application belongs to the technical field of space planning, and discloses a land space planning suitability evaluation system based on space-time big data; by constructing a projection zone distribution topology graph and an anisotropic distortion tensor field, coordinate distortion at the junction of projection zones is accurately identified and corrected. By using a spatial autocorrelation analysis method, systematic deviation areas in the residual system in the process of digitizing historical maps are identified, and a residual propagation influence domain model is established, so that accurate coordinate correction of each position point is realized. Through an adaptive fusion mechanism of compensation components, the fusion accuracy of multi-source space-time data is improved. A coordinate correction confidence evaluation mechanism is introduced, data uncertainty information is included in the suitability evaluation process, and more scientific and reliable evaluation results and confidence intervals are provided for decision makers.

The application discloses a human-like cognitive reasoning framework for user demand prediction in a pension situation, belongs to the field of information technology, artificial intelligence and man-machine interaction, and discloses the human-like cognitive reasoning framework for user demand prediction in the pension situation, which comprises a resource storage, an encoder, a decoder, an evaluation updater, an intuition generator, a cognitive device, a training updater and a decision maker. The application provides the human-like cognitive reasoning framework for user demand prediction in the pension situation, which can be applied in the pension situation, enables the service robot to have accurate and efficient reasoning capability, and can predict the specific demand of the old people under the premise that limited external conditions are provided, so that the humanization of the service robot is of great significance and has a wide application prospect.

The present application relates to, but is not limited to, the technical field of autonomous driving. Disclosed are a generator training method and apparatus, a vehicle control method and apparatus, and a device and a medium. The generator training method comprises: acquiring a plurality of first training samples, wherein each first training sample comprises first state information of a vehicle and a first behavior sequence of the vehicle corresponding to the first state information, the first behavior sequence is obtained on the basis of the output of a pre-acquired target decision maker, and the target decision maker is configured to simulate decision-making behaviors of a human expert; and using the plurality of first training samples to train an initial generator, so as to obtain a first target generator. A target decision maker is used to assist in the training of a generator, and the output of the target decision maker is used as training samples, such that the generator can learn decision-making behaviors that are substantially the same as those of the target decision maker, thereby achieving a better training effect for the generator, accelerating the learning process, and improving the decision-making accuracy.

The application discloses a flexible interconnection device optimal operation method, system, equipment and medium, and the method comprises the steps of obtaining basic data of a power distribution network, constructing a target function and a constraint condition by using the basic data, obtaining a double-layer planning model comprising an upper-layer site selection model and a lower-layer constant-volume operation model according to the target function and the constraint condition, introducing a key constraint in the lower-layer constant-volume operation model, checking the action behavior of each protection device under a preset fault scene, obtaining a checked double-layer planning model, iteratively solving the checked double-layer planning model by using a collaborative evolution intelligent algorithm, obtaining an optimization result, and realizing the optimal operation of the flexible interconnection device, thereby providing a rich selection space for decision makers.

This invention relates to the field of intelligent decision-making technology in emergency management, and provides an intelligent emergency decision support method based on a hybrid agent network. The method includes: constructing a decision knowledge space containing a knowledge system of the emergency domain; storing knowledge units in vector form to create a knowledge base supporting semantic retrieval; upon receiving disaster event information, a planning agent decomposes and orchestrates the decision task, generating a task orchestration scheme containing multiple sub-tasks and their dependencies; an analysis agent performs multi-dimensional analysis of the decision task according to the task orchestration scheme; a generation agent summarizes the analysis results; and, combined with a business knowledge system, generates disposal suggestions and a decision report. This invention achieves deep integration of business knowledge and AI capabilities, collaborative decision-making among multiple types of agents, and adaptive orchestration of the decision process, thereby providing decision-makers with comprehensive, accurate, and scientific decision support during the critical time following a disaster.

The application relates to the technical field of infectious disease epidemic situation, and in particular to a dynamic map visualization method and system for a spatio-temporal evolution process of an infectious disease epidemic situation. The method first superimposes confirmed case coordinates and multi-time sequence risk resource points on an electronic map to construct an initial distribution layer; secondly, the layer is constrained by real-time reporting information to generate spatio-temporal evolution visualization rules; then, the initial layer is optimized in the spatio-temporal dimension based on the rules to obtain a hierarchical dynamic spatio-temporal data set; subsequently, a multi-level time sequence label and a visualized evolution layer are generated based on the data set and dynamically rendered with the electronic map to form a real-time dynamic interactive interface; finally, the interface and the label are combined to provide dynamic analysis support for epidemic prevention and control. The method realizes the transformation of epidemic data from static display to dynamic deduction, improves the data accuracy and the sense of hierarchy through real-time constraint and spatio-temporal optimization, effectively reveals the epidemic transmission context, and assists decision makers in accurately identifying risks, analyzing trends and formulating scientific prevention and control strategies.

The application discloses a new energy vehicle grading recommendation method based on decision maker's incomplete preference, and relates to the technical field of intelligent decision and data processing. The method comprises the following steps: constructing a knowledge and data driven new energy vehicle classification category boundary; determining the weight of each evaluation criterion and the local priority value of a scheme under the incomplete preference of a decision maker; constructing a new energy vehicle standardized evaluation information matrix; filling in the missing values in the new energy vehicle standardized evaluation information matrix; aggregating the weight of each evaluation criterion and the complete evaluation information matrix to calculate the global priority value of each new energy vehicle and classification boundary; comparing the global priority value of each new energy vehicle and classification boundary to divide the new energy vehicles into corresponding recommended grades. The application can realize accurate grading recommendation of new energy vehicles by constructing self-adaptive classification boundaries, reconstructing incomplete preferences and intelligently filling in missing data.

This invention relates to the field of power resource dispatching technology, specifically to a method and device for dynamic aggregation of virtual power plants based on two-layer decision-making and satisfaction. The method includes: using the virtual power plant as the upper-layer decision-maker in a two-layer decision-making architecture, and the corresponding entities of the participants as lower-layer decision-makers, to determine the aggregation scheme; wherein, the upper-layer decision-maker uses a two-layer late-acceptance hill-climbing algorithm combined with a proxy objective function to iteratively optimize internal transaction price information, and distributes it to the lower-layer decision-makers through a blockchain network; the lower-layer decision-makers listen to and obtain information through smart contracts, and when trigger conditions are met, call their local participant model to calculate the optimal operating scheme and calculate satisfaction information based on the Frynell satisfaction model, and upload it to the blockchain network for the upper-layer decision-maker to adjust the internal transaction price information of the dispatching cycle. This effectively improves the flexibility of the virtual power plant in dispatching power resources, thereby improving dispatching efficiency.

The present application relates to a kind of distribution network multi-objective power flow voltage optimization method considering distributed photovoltaic access, on the basis of multi-objective grey wolf algorithm search mechanism, join the disturbance mechanism of balance optimizer algorithm, further expand the search range of multi-objective swarm intelligence algorithm, effectively improve the convergence and distribution of algorithm search result;Compared with the existing swarm intelligence optimization algorithm, the optimization method proposed in the present application can provide better, more flow voltage optimization scheme for decision makers, more can meet the decision needs of decision makers under different target preferences, therefore can meet the scene demand of actual distribution network power flow voltage optimization.

This invention relates to the field of virtual simulation technology, specifically an intelligent virtual simulation and situational awareness system based on serious games. It comprises, from top to bottom, a serious game interaction layer, a situational analysis and decision support layer, and an intelligent virtual simulation layer. The serious game interaction layer provides gamified interaction entry points and incentive mechanisms for users such as trainers and decision-makers, and is responsible for collecting user operations, displaying feedback information, and outputting incentive elements. The situational analysis and decision support layer is responsible for collecting real-time data during the simulation process, performing intelligent analysis and evaluation, and generating situational views and decision suggestions. The intelligent virtual simulation layer constructs a virtual environment and intelligent agents based on artificial intelligence technology, realizing dynamic scene adaptation, entity behavior simulation, and user operation response.

The application relates to an intelligent decision system and method based on an attack-defense game model and belongs to the technical field of network security. The intelligent decision system and method based on the attack-defense game model take network confrontation between the enemy and the self as the background, consider the complexity of the network confrontation environment, abstract the problem into a zero-sum game confrontation problem, construct a network game model, introduce a third-party performance evaluation mechanism to test the attack-defense game model, and help decision makers of the self to more intuitively and intelligently select an optimal confrontation strategy. In order to improve the rationality and accuracy of the network attack-defense game model, the application improves a deep Q network based on a genetic algorithm to approximate an action state value function when the network attack-defense game model is constructed, solves a continuous multi-dimensional state space problem, tests the attack-defense game model through the third-party performance evaluation mechanism, makes the attack-defense game model more accurate, and thus provides decision support for decision makers.

The application discloses a day-ahead electric energy and reserve auxiliary service joint clearing method, comprising the following steps: obtaining parameter data; inputting the parameter data into a pre-constructed robust optimization model considering net load uncertainty to obtain an optimal clearing scheme under the worst scenario; wherein, the robust optimization model is constructed based on a risk cost model and a day-ahead electric energy and reserve market joint clearing model; the risk cost model comprises an upper reserve risk cost model considering unit fault and net load prediction error, and a lower reserve risk cost model considering load unplanned exit and net load prediction error; the day-ahead electric energy and reserve market joint clearing model is constructed with the minimum system operation cost as the target. The application can find the optimal clearing scheme under the worst scenario in the system for market decision makers, and provides a more perfect reference decision for market resistance to the risk of uncertainty.

This invention discloses a method and system for optimizing wind farm layout to balance noise and power generation. The method includes: establishing a multi-objective optimization model for wind farm layout; setting reference points and weight vectors based on decision preference information; and generating... N P A wind farm layout is used to form a parent population; the parent population is divided into several subpopulations and searched to generate mutation vectors; local difference operations are performed on the mutation vectors to obtain candidate layout solutions; based on the candidate layout solutions, a double substitution operation is performed on each target vector to generate a offspring population; the offspring population is merged with the parent population, and the optimal layout is selected. N P This invention involves repeatedly performing an optimization process on individual wind farms, outputting optimization results, and determining whether the decision-maker's preference information needs adjustment based on the optimization results. If not, it outputs the wind farm layout. This invention increases power generation while reducing wind farm noise, and can obtain a wind farm layout scheme that matches the decision-maker's preferences.

The present application relates to the technical field of the cross of bioinformatics, medical genetics and artificial intelligence, and discloses a gene mutation pathogenicity automatic rating method and system based on multi-agent game and thought chain reasoning, which comprises the following steps: searching data related to a target mutation site; based on the related data; performing multi-round iterative gene mutation pathogenicity rating by a proposer agent, a refuter agent and a decision maker agent; monitoring the rating conclusion output by the decision maker agent and the confidence score in real time, and when a preset dynamic truncation condition is met, terminating the multi-agent game step and outputting the final gene mutation pathogenicity rating conclusion. The present application can realize accurate and transparent rating of gene mutation pathogenicity by eliminating model hallucinations through adversarial games and analyzing unstructured documents by using thought chains.

The application discloses a cross-system identity permission adaptive reconciliation method and device of a database management platform, computer equipment and a storage medium, and the method comprises the following steps: constructing a cross-system identity permission reconciliation model; performing conflict detection on the cross-system operation chain perception layer according to a conflict event, and extracting subject features of the cross-system operation chain; performing reverse causal tracing based on the subject features by the causal attribution layer, and outputting causal correlation strength; performing consistency propagation and elimination based on the entity constraint relationship provided by the business entity topology graph and the causal correlation strength provided by the causal attribution layer by the state decision layer, obtaining a global optimal state belief, making a decision and performing by the adaptive reconciliation decision maker based on the global optimal state belief, and producing a composite repair instruction; and adjusting the cross-system identity permission according to the composite repair instruction, and eliminating the conflict event.

The application relates to the technical field of precision numerical control machining, and particularly discloses a CNC machining path residual error analysis compensation method and system fusing twin simulation, which comprises the following steps: extracting a geometric residual error and a dynamic risk characteristic vector through extended digital twin model synchronous simulation; generating candidate compensation instructions and performing lead simulation based on the same, quantitatively evaluating secondary risks to construct a dynamic compensation risk probability field; utilizing a risk-precision multi-target decision maker to generate adaptive compensation instructions according to the risk field, that is, adopting high-gain compensation in a low-risk area and switching to a conservative strategy in a high-risk area; and reversely optimizing the twin model and the risk calculation model by comparing actual risk events with prediction results; and the system comprises four modules corresponding to functions. The application improves compensation from error driving to risk constraint decision, effectively avoids secondary process problems such as overcutting and chatter, and significantly improves machining precision and adaptive capacity under complex working conditions while ensuring stability.

The application relates to a drip irrigation pipe network partition irrigation control method and system based on multi-objective optimization and belongs to the technical field of artificial intelligence. The method comprises the following steps: collecting multi-source heterogeneous data and sampling point spatial coordinates, splicing features and normalized coordinates to form a joint feature vector after abnormal value elimination and normalization processing, and obtaining spatial continuity and feature similar irrigation partitions through K-means clustering; a multi-objective optimization model is constructed with partition irrigation time length and inlet target flow as decision variables; a hybrid strategy multi-objective evolutionary algorithm with chaotic mapping initialization and adaptive hybrid variation is used to obtain a Pareto optimal solution set; finally, optimal irrigation parameters are determined by combining an entropy weight method and a decision maker preference through a good-bad solution distance method, and a real-time soil moisture monitoring feedback correction parameter is introduced. The application can realize accurate partition irrigation of a drip irrigation pipe network, balance multiple optimization objectives, improve irrigation effect and resource utilization efficiency, and reduce system energy consumption.

The application discloses an intelligent arrangement system and implementation method for server virtualization deployment, relates to the technical field of server virtualization, and comprises a unified resource perception and abstraction layer and a predictive preloading and dynamic scheduling engine.The unified resource perception and abstraction layer uniformly describes heterogeneous physical resources of different hardware architectures and virtualization platforms, generates and updates a dynamic resource image; the predictive preloading and dynamic scheduling engine analyzes user operation sequences and predicts resource requirement timing through a multi-dimensional signal perception and behavior analysis module, calculates preloading suitability weight by means of a predictive preloading decision maker of resource perception and executes hierarchical-on-demand hybrid preloading, and realizes multi-target optimization scheduling and prospective resource fragmentation arrangement through a dynamic scheduling and fragmentation arrangement module.The application deeply integrates unified resource perception, future load prediction and intelligent arrangement decision, improves resource utilization and application response speed, and optimizes system operation performance and stability.