1896 results about "Instruction set" patented technology

The invention provides an AI-based laboratory equipment scheduling optimization method and system, and the method comprises the steps: firstly obtaining a state monitoring data set containing the characteristics of equipment operation power consumption, idle time length, environment interference factors and the like in real time, and then carrying out the multi-dimensional analysis of the state monitoring data set; generating an availability evaluation index set containing characteristics of equipment load fluctuation, maintenance period prediction, compatibility matching and the like, and an experiment task priority queue, performing cross decision analysis on the availability evaluation index set and the experiment task priority queue based on a preset dynamic resource allocation model, and obtaining a scheduling strategy set containing a task allocation path, a cooperative operation rule and a conflict resolution mechanism; scheduling strategy parameters are calibrated according to experimental task operation log data, an optimized execution instruction set is generated, instructions are fed back to an equipment control system to adjust the equipment state, a dynamic resource allocation model is iteratively updated according to execution feedback data, and efficient scheduling optimization of laboratory equipment is achieved.

The invention relates to a multi-mode large language model fine tuning method, system and device and a medium, and belongs to the technical field of artificial intelligence and computer vision crossing. The fine tuning method comprises the steps that an original business scene image is acquired and preprocessed, and a preprocessed image is obtained; performing bounding box coordinate labeling and semantic label definition on the entity target in the preprocessed image through a labeling tool, and outputting a structured labeling file; based on the preprocessed image and the structured annotation file, constructing a training sample set comprising multiple rounds of image-text dialogues; loading the pre-trained multi-modal large language model, configuring low-rank matrix decomposition parameters, and generating a fine tuning instruction set; and inputting the training sample set into a pre-trained multi-modal large language model, carrying out joint training operation based on the fine tuning instruction set, and outputting the fine-tuned multi-modal large language model. According to the method, the identification accuracy, the interaction capability and the system availability of the visual question-answering system in an actual application scene are improved.

The invention relates to a concrete temperature-stress two-parameter cooperative monitoring and early warning method and system, and belongs to the technical field of concrete structure health monitoring, and the method comprises the steps: activating a composite sensor network disposed at a preset position of a concrete structure, and executing a sensor self-calibration mode; the method comprises the following steps: synchronously acquiring temperature and stress original monitoring data of each node, processing based on an altitude air pressure compensation algorithm, and outputting a temperature gradient field matrix and a stress tensor sequence with aligned time domains; the method comprises the following steps: separately calculating a thermal stress component and an effective stress component, performing integral calculation on hydration reactivity, generating a multi-dimensional feature vector set, inputting a pre-constructed prediction model, executing time sequence evolution prediction, calculating a crack probability value, performing environment correction in combination with real-time environment parameters, outputting a risk level identifier, and matching a preset regulation and control strategy. And generating an equipment control instruction set and executing corresponding regulation and control actions. According to the invention, the accuracy and timeliness of crack risk prediction can be improved.

The invention provides a greenhouse environment adaptive regulation and control method and system, and relates to the technical field of environment control, and the method comprises the steps: collecting multi-dimensional environment parameters in a greenhouse; based on the environmental parameters, a preset crop growth period database and weather prediction data, taking minimization of a preset cost function as a target, and adopting a model prediction control algorithm to generate an equipment linkage instruction set in a future preset time period, the preset cost function fusing environmental regulation and control deviation and operation cost; issuing the equipment linkage instruction set to each execution equipment, and executing linkage regulation and control; wherein when the equipment linkage instruction set is generated, a conflict resolution mechanism based on a dynamic priority is adopted to determine an execution sequence of a plurality of equipment instructions; the adaptive regulation and control method integrating multi-source data verification, multi-scale prediction, dynamic priority conflict resolution and multi-target cost optimization improves the accuracy, economy and crop suitability of greenhouse environment regulation and control.

The invention relates to the technical field of virtualization management, in particular to a virtual machine operation management system based on RISC-V. The system comprises an instruction set mapping module, a resource scheduling optimization module, a virtual machine monitoring integration module, an operation tuning update module and an operation configuration distribution module. According to the method, by analyzing the operation instruction of the virtual machine and combining the RISC-V underlying characteristics, accurate instruction mapping is achieved, the processing efficiency and accuracy are remarkably improved, the performance loss and conversion delay caused by too high abstraction level of a traditional virtual machine on the instruction level are overcome, the optimal allocation scheme is screened, the resource utilization rate and the system response speed are effectively improved, and the system performance is improved. The operation state and performance indexes of the virtual machine are integrated, anomaly detection and resource recovery are embedded, system stability and effective resource reutilization are ensured, basic configuration is continuously and incrementally updated, operation configuration refinement and automatic management and updating are achieved, the overall operation efficiency and management flexibility are improved, and the manual intervention cost is reduced.

The invention relates to the technical field of industrial platform data analysis, in particular to a renewable resource recovery data management system based on the Internet of Things, which comprises the steps of synchronously acquiring weight, spectrum and microwave characteristic data of a tested resource through a data acquisition module, executing moisture weight decoupling operation by utilizing a resource matching module, and performing data analysis; then, an inventory evolution module tracks performance loss of resources in real time by using an evolution model of an integrated long and short-term memory network, generates a resource attenuation weight, and constructs a two-dimensional decision matrix containing scheduling priority and preprocessing strength grade instructions in combination with real-time inventory saturation; and finally, the clearance scheduling module executes dynamic pruning and bidirectional optimization through a resource scheduling model, accurately allocates the loading share and the access sequence of each node, and generates a dynamic instruction set containing a delivery sequence. According to the method, feeding homogenization is realized through industrial data multi-dimensional collaborative analysis.

The invention discloses a cross-platform virtual-real fusion scene construction method and system based on AI space calculation, and relates to the technical field of artificial intelligence and space calculation, and the method comprises the steps: carrying out the multi-scale feature fusion based on a received cross-modal conversion instruction set, and generating an initial image sequence; carrying out implicit field coding on a target object by combining a three-dimensional reconstruction algorithm to obtain an initial parameterized model; performing space-time alignment on the multi-view video stream, loading a digital scene asset package in combination with physical sensing data and a preset spatial index structure, and establishing a bidirectional data channel between a virtual scene and a physical sensor; performing rendering and illumination parameter adjustment on the initial parameterized model to obtain an optimized parameter model; performing differential coding processing on the optimization parameter model to obtain a target virtual-real scene fusion model; and distributing the target virtual-real scene fusion model to a preset terminal. The invention provides a virtual-real fusion construction method for end-to-end collaborative optimization, which is suitable for cross-platform live broadcast or dynamic interaction scenes.

The invention discloses a heterogeneous computing power resource dynamic cooperative scheduling method and system and a computer device. The method comprises the steps of obtaining multi-dimensional feature information of a to-be-scheduled task, current state information of each node in a heterogeneous computing power resource pool and scheduling environment state information; training a time sequence model by adopting historical associated data, inputting the multi-dimensional feature information, the current state information and the scheduling environment state information into the trained model to obtain associated trend information in a future preset time window, and then combining the multi-dimensional feature information and the current state information of all the nodes to obtain the scheduling environment state information. A multi-objective optimization function fusing task delay, cost consumption and energy consumption is constructed, the function is optimized based on a preset strategy, a target decision strategy is obtained, a scheduling instruction set is generated after analysis, allocation information and target nodes are determined according to the scheduling instruction set, and tasks are issued. According to the method, dynamic collaborative scheduling of heterogeneous computing power resources can be realized, and the overall utilization efficiency of the resources is accurately, efficiently and effectively improved.

The invention relates to the technical field of resistor chips, in particular to a method and a system for optimizing a manufacturing process of a thermistor chip. According to the method, multi-scale process entropy analysis is carried out on a process parameter dynamic flow, the coupling strength between key processes is analyzed, and a process parameter cluster with strong non-monotonic correlation and a process system entropy increase path of the process parameter cluster are identified, so that a collaborative stability domain boundary model is constructed; according to transient fluctuation characteristics extracted from a process parameter dynamic flow obtained in real time, in combination with the collaborative stability domain boundary model, determining a parameter subset exceeding a collaborative stability operation interval as a drift parameter cluster, executing an optimization instruction set to perform trial production, synchronously collecting collaborative trajectory data of a process parameter cluster, and performing collaborative trajectory prediction; and the collaborative stability is verified by calculating the entropy change rate of the process system and is fed back to the collaborative stability domain boundary model for boundary toughness strengthening, dynamic collaborative convergence of relevant parameters such as the sintering gradient and the electrode pressure is achieved, and the product consistency and the yield stability are improved.

The invention discloses a water-cooling energy consumption adaptive regulation and control method suitable for a data center, and the method comprises the following steps: obtaining a multi-dimensional operation parameter set of the data center in real time, and generating a real-time thermal load density distribution diagram reflecting the heat distribution condition in a machine room; calculating the overall thermal deviation degree and the local hot spot intensity, and solving through a dynamic energy efficiency optimization function to obtain a target system supply and return water temperature difference and a target cooling liquid flow; inputting into a hydraulic and thermodynamic simulation model, and generating an optimal multi-device coordinated regulation instruction set; and executing the multi-device coordinated regulation instruction set, and then performing parameter calibration on the hydraulic and thermodynamic simulation model. The method has the following advantages and effects that the thermal environment of the machine room can be sensed in real time, the energy consumption and heat dissipation requirements can be intelligently balanced, and multiple devices in the cooling system can be cooperatively regulated and controlled, so that the overall energy consumption of the cooling system is optimized while the local overheating risk of the machine room is thoroughly eliminated.

The present application relates to the technical field of safety management, in particular to a mine air compressor safe operation management method and system based on deep learning, comprising the following steps: collecting output pressure and input current, calculating slope change rate and direction switching frequency, clustering fluctuation amplitude and frequency by time period, generating working condition fluctuation label, identifying state mutation point and duration, calculating risk level label, analyzing load fluctuation coefficient, judging periodic fatigue early warning, combining synchronous rate to identify abnormal section, judging the need to switch state and generating instruction set. In the present application, by constructing the load risk level sequence on the basis of state duration and mutation point identification, the quantitative identification of multi-period load deviation is realized, the early warning period is marked by combining risk level and fatigue deviation ratio, and the abnormal load trend is judged according to the change direction of pressure and return gas flow, which strengthens the capture ability of abnormal operation section and improves the accuracy of operation safety risk identification and the adaptability of response strategy.

The invention discloses a source network load storage oriented regional collaborative scheduling method and system, and relates to the technical field related to power resource scheduling, and the method comprises the steps: traversing target region source network load storage to carry out real-time data collection, and constructing a source network load storage multi-dimensional data set to carry out multi-scale layered optimization; operation constraint conditions are set, limitation is carried out in combination with a power grid topological structure, a cooperative scheduling instruction set is determined, cooperative control feedback is carried out, and regional power scheduling feedback parameters are generated; and multi-channel dynamic correction is carried out, and a cooperative scheduling optimization strategy is generated to carry out energy balance cooperative scheduling on the source network load storage in the target area. The technical problems that in the prior art, intermittent fluctuation of new energy is difficult to consume, the collaboration of all links of source network load storage is poor, the dispatching flexibility of a power system is insufficient, and the resource configuration efficiency is low are solved. The technical effects of optimizing regional energy resource allocation and improving the clean energy consumption level, the power grid operation stability and the source grid load storage cooperative response capability are achieved.

The invention discloses a fire alarm linkage system for fire engineering based on the Internet of Things. The operation process of the system specifically comprises the following steps: generating a dynamic risk probability distribution diagram based on a building three-dimensional point cloud model and multi-source data, and deploying a differential sensor array; environment multi-physical field parameters are collected in real time through a differential sensor array, and a multi-mode fire behavior sensing signal set is generated; building a fire situation credibility map: calling a multi-criterion decision module to calculate a linkage equipment weight distribution matrix based on the fire situation credibility map, and generating a multi-stage linkage control instruction set in combination with the building topological structure model and the personnel distribution thermodynamic diagram; and performing multi-cross-system cooperative execution and closed-loop optimization. The method has the following advantages and effects that the inherent limitation of a traditional system can be broken through by constructing an intelligent prevention and control framework combining risk quantification, situation deduction and decision closed loop, the personnel evacuation efficiency is effectively improved, and damage caused by major accidents such as detonation is reduced.

The invention relates to the technical field of hydraulic engineering monitoring, and discloses a hydraulic engineering operation risk monitoring management system based on multi-sensor fusion. The system comprises a data acquisition module, a data fusion module, an early warning and instruction generation module, and an instruction distribution and verification and correction module. The data acquisition module acquires structural deformation, water flow pressure and environment temperature and humidity data in real time through multiple types of intelligent sensors; the data fusion module inputs the collected data into a dynamic weighted fusion model, and generates a comprehensive monitoring index in combination with a sensor confidence coefficient weight and a historical data deviation rate; the early warning and instruction generation module triggers multi-stage early warning and generates an equipment regulation and control instruction set according to the comprehensive monitoring index and a preset safety threshold value; the instruction distribution module distributes the instruction to an execution terminal through a distributed message queue; and the verification and correction module checks terminal feedback signals by using a back propagation verification mechanism, and corrects the confidence coefficient weight of the model.

The invention relates to the technical field of agricultural equipment, in particular to a hybrid tractor whole machine dynamic property evaluation method fusing multiple working condition parameters, which comprises the following steps: acquiring an environment working condition parameter set, an operation task parameter set and an energy flow dynamic parameter set in real time; a dynamic coupling relation mathematical model is constructed based on the parameter set, the whole machine dynamic property characteristic values of the steady state working point and the transient working point are calculated respectively, and a whole machine dynamic property evaluation index set is generated; inputting the evaluation index set into a hardware-in-the-loop simulation platform, and verifying the effectiveness of the evaluation indexes through multi-modal working condition simulation; and constructing a three-dimensional dynamic property evaluation map based on the verified evaluation indexes, dividing dynamic property partitions, outputting the dynamic property partitions to the vehicle-mounted intelligent terminal in real time, and generating a self-adaptive control instruction set when entering a failure area. According to the invention, multi-source information fusion modeling, all-working-condition dynamic response evaluation and visual map feedback can be realized, and the dynamic adaptability and regulation and control intelligence of the hybrid tractor in a complex operation scene are improved.

The embodiment of the invention provides a turning and milling combined machining deformation control method and system for a special-shaped part, and is used for the technical field of numerical control machining. The turning and milling combined machining deformation control method for the special-shaped part comprises the steps that structural feature analysis and process association marking are conducted on design data of the special-shaped part to generate a feature association data set, and clamping and process planning are conducted according to a machining constraint database and the feature association data set to generate initial turning and milling combined machining process data; cutting parameter multi-objective optimization solution is carried out on the initial turning-milling combined machining process data to obtain a turning-milling cutting parameter set, and multi-axis linkage analysis and instruction collaborative planning are carried out on the turning-milling cutting parameter set according to the equipment operation feature set to generate a combined machining control instruction set. According to the method, through part key feature recognition and risk marking, combined machining control instructions are generated after layered digital twinning verification in combination with process multi-objective optimization, and the one-time qualified rate of special-shaped part machining and turn-milling combined machining process stability are improved.

The invention relates to the field of document processing, and particularly provides a document format processing method, system, terminal and medium based on a large language model.The method comprises the steps that a generation instruction containing a target document type and a source material are received, and original text content is generated through the large language model integrating domain knowledge; obtaining a matched structured format template, and analyzing the style rule into a format instruction set; identifying logic elements and hierarchical relationships thereof in the original text based on a natural language processing technology; performing association mapping on the format instruction and the logic element, and performing automatic style rendering by calling a document object model interface to generate an intermediate document with a standard format; and finally, outputting after quality verification. According to the method, an automatic process of content generation and intelligent formatting is constructed, and the document writing efficiency and normalization are improved.

The invention discloses a sewage treatment whole-process operation regulation and control calculation system based on deep learning, and relates to the technical field of intelligent control, and the system comprises a strategy optimization module which optimizes a future pollution trend prediction sequence and a regulation and control factor weight table by using a reinforcement learning strategy network in combination with a genetic algorithm optimizer, dynamically generating an aeration, dosing and backflow operation parameter combination aiming at a regulation target to form a dynamic regulation instruction set; the instruction execution module is used for issuing a dynamic regulation and control instruction set to the programmable logic controller by utilizing an industrial control interface, and collecting response information and real-time effluent quality data as execution feedback information; and the model updating module carries out error comparison on execution feedback information and a future pollution trend prediction sequence, constructs a weighted error sequence, and dynamically corrects deep network parameters through an online fine tuning strategy to form a prediction control model. According to the method, the generalization ability and robustness of the predictive control model are remarkably improved.

The invention provides a self-adaptive spraying mechanical arm based on multi-mode perception and a control method of the self-adaptive spraying mechanical arm. The method comprises the steps that multi-source perception data of a to-be-repaired area is obtained through a dual-mode vision system and a laser scanning device, a two-dimensional repairing area segmentation map is generated, and space registration and local geometric modeling are achieved in combination with three-dimensional point cloud; on the basis of local geometric features extracted by the model, retrieving matched process parameters from the knowledge graph, generating a digital spraying instruction set containing tracks, postures and dynamic process parameters, and performing simulation verification in a digital twin environment; the mechanical arm state and the virtual model are synchronized in real time in the execution process, the paint film thickness is dynamically monitored, and compensation adjustment is triggered; and after spraying is completed, the coating quality is detected, and a result is fed back to the knowledge graph to update the parameter mapping relation. According to the method, closed-loop control from sensing, decision making, execution, evaluation to learning is achieved, and the spraying uniformity, the self-adaptability and the intelligent level under the complex working condition are improved.

The invention provides a heat supply digital twinborn intelligent regulation and control method, and relates to the technical field of intelligent regulation and control, and the method comprises the steps: executing millisecond-level high-concurrency numerical simulation according to a dynamic digital twinborn body, so as to obtain a simulation result; based on the simulation result, coupling the electricity price fluctuation data and the weather prediction data, performing future heat supply system multi-working-condition deduction, and dynamically optimizing a heat source unit start-stop combination and pipe network valve opening strategy to obtain a deduction result and an optimization strategy; generating an equipment regulation and control instruction set according to the deduction result and the optimization strategy; and an equipment regulation and control instruction set is issued to an edge computing node, a variable-frequency circulating pump and an electric control valve executing mechanism are controlled, and dynamic closed-loop regulation of the flow and the pressure of the heat supply pipe network is achieved. According to the invention, the pipe network flow and pressure regulation response time can be shortened to a second level.

The invention relates to the technical field of computer data processing, and discloses an automatic format conversion and incremental synchronization method for cross-platform heterogeneous document data. The method comprises the following steps: capturing an atomic data change event from a source system transaction log; aggregating into logic transaction units according to the transaction identifiers; converting into a unified intermediate normal form; generating a target system operation instruction set based on the metadata mapping rule; the synchronization sites are executed and persisted in a transactional manner. According to the method, through log-level capture and transactional synchronization, data integrity, sequence and high consistency are ensured, and efficient and reliable data synchronization between heterogeneous systems is supported.

The invention relates to a situation awareness network vulnerability defense method and system, and the method comprises the steps: extracting a multi-mode traffic feature, inputting the multi-mode traffic feature into a fusion twin network model, and outputting security event information; constructing a preliminary control strategy matrix based on the security event information, and performing optimization adjustment to generate an access control strategy matrix; converting the access control strategy matrix into a network control instruction set, and sending the network control instruction set to each execution device; performing network situation monitoring on the execution equipment, performing evaluation through a game theory evaluation model, and dynamically adjusting and optimizing parameters based on an evaluation result; in conclusion, abnormal traffic behavior pattern recognition is realized by fusing the twin network model, the problems of static strategy stiffness and low resource scheduling efficiency in the traditional defense technology are effectively solved by combining multi-objective optimization and a dynamic strategy adjustment mechanism, accurate recognition of the abnormal traffic behavior pattern and optimization of resource scheduling configuration are realized, and the method is suitable for the implementation of the defense technology. The method has the effect of improving the network protection adaptivity.

The invention provides a vision-based cross-network interaction method and system, and relates to the technical field of intelligent interaction, and the method comprises the steps: obtaining a visual interaction sequence, constructing multi-modal feature representation, achieving cross-domain semantic alignment, deconstructing visual information into a hierarchical control instruction set, and transmitting the hierarchical control instruction set to a target network environment for execution after security classification. And a bidirectional mapping relation graph is constructed to realize incremental optimization. According to the method, semantic bridging between heterogeneous networks can be established, the cross-domain control precision is improved, and meanwhile safe interaction in a network isolation environment is guaranteed.

The invention relates to the technical field of building intelligent control and energy saving, and discloses a building equipment intelligent control optimization management system based on a green low-carbon building. The system comprises five subsystems, wherein an environmental parameter sensing subsystem is used for acquiring temperature and humidity gradients, illumination intensity distribution and personnel activity thermodynamic diagram data inside and outside a building through a distributed sensing network to form a multi-dimensional environmental state vector; the equipment operation state acquisition subsystem acquires an operation power curve, an energy efficiency conversion rate curve and an equipment health degree index of heating ventilation air conditioning, illumination and renewable energy equipment in real time; the dynamic load prediction subsystem establishes an energy consumption load space-time distribution prediction model according to historical data time sequence relevance; the control strategy generation subsystem is used for generating an optimized instruction set containing an equipment start-stop time sequence, a power regulation gradient and an energy distribution weight in combination with the current environment vector and a predicted load; the execution terminal adapts the subsystem to convert the instruction into a device compatible signal and calibrate a response delay.

The invention discloses a rotating machine vibration protection method and system of an adaptive resonance neural network, and the method comprises the steps: collecting a millisecond vibration acceleration signal of a rotating machine through a distributed piezoelectric sensor array, obtaining the real-time working condition parameter of equipment, and generating a time-work synchronous vibration signal flow; inputting the time-work synchronous vibration signal flow into a resonance neural network, and dynamically generating a frequency domain-time varying adaptive threshold group in combination with the working condition parameters; extracting a weak impact resonance characteristic tensor by using a multi-scale resonance kernel of the resonance neural network; projecting a weak impact resonance characteristic tensor to an orthogonal fault subspace through a tensor decomposition algorithm, and separating out a decoupling fault characteristic matrix; and generating a real-time protection decision instruction set based on a comparison result of the decoupling fault feature matrix and the equipment operation historical database. According to the embodiment of the invention, the method can improve the detection sensitivity and positioning precision of a weak fault under an unsteady working condition, and achieves the real-time adaptive optimization of the vibration protection of the rotating machine.

The invention relates to the technical field of intelligent building AI construction monitoring, and discloses a high-rise building construction monitoring method and system based on intelligent AI. The method comprises the following steps: acquiring construction physical signals, and fusing to generate multi-dimensional state sensing information; constructing a digital twinborn body comprising a structure topology and a material parameter evolution path; deducing a construction process by using an AI agent, and outputting a risk situation map and a behavior intervention instruction set; and acquiring a field real-time resource state, carrying out matching verification on the instruction, and starting AI reconstruction on an unmatched instruction to generate a final executable instruction set. Through dynamic evolution modeling of material parameters, the structural state simulation and risk prediction precision is improved; through the real-time verification and reconstruction mechanism of the instruction, the performability of intervention measures is ensured, and closed-loop intelligent control from risk perception to accurate intervention is realized.

The invention relates to the technical field of intelligent manufacturing, and discloses an industrial processing production line adaptive control method and system based on reinforcement learning. The method comprises the following steps: collecting a processing monitoring signal and environment state data to construct a comprehensive processing state vector; deducing the comprehensive processing state vector by using a preset depth time sequence learning model to obtain an error evolution trend vector; determining an initial strategy parameter and a strategy matching state according to the error evolution trend vector; according to the strategy matching state and the initial strategy parameter, parameter iteration optimization based on a preset comprehensive error prediction model is carried out, and a target compensation control quantity is obtained; machine tool dynamics constraint verification is carried out according to the target compensation control quantity, and a final compensation instruction set is obtained; and performing instruction mapping and execution according to the final compensation instruction set to obtain processing feedback data, and performing reinforcement learning updating on the model based on the processing feedback data. According to the invention, high-precision self-adaptive compensation under complex dynamic working conditions can be realized.

The invention relates to a pre-training language model fine tuning method, an inference service system, equipment and a medium, and the method comprises the steps: obtaining an original instruction of a target field and related fields, the original instruction comprising a language understanding task; evaluating and screening the original instruction according to a multi-dimensional index, and constructing a first high-value instruction set; extracting instructions in related fields from the first high-value instruction set, and performing filtering and mobility evaluation on the extracted instructions by using a pre-training language model to obtain a second high-value instruction set; adopting a pre-training language model to perform labeling, screening and enhancement processing on the second high-value instruction set in sequence, and generating a structured training sample; and training a pre-training language model according to the structured training sample to enable the pre-training language model to adapt to the target domain. Through the method and the device, the field annotation data quantity is reduced.

The invention relates to a smart campus comprehensive energy-saving regulation and control method and system based on AI decision making. The method comprises the following steps: constructing a spatial-temporal feature tensor based on campus multi-source heterogeneous data; according to the spatio-temporal feature tensor, performing prediction processing through a dynamic spatio-temporal diagram neural network, and generating a global state tensor including an energy consumption prediction baseline and an environment change gradient; inputting the global state tensor into a hierarchical reinforcement learning model for processing, and generating an equipment-level control instruction set; and inputting the equipment-level control instruction set into the digital twin environment model for simulation safety verification to obtain a verification result, and generating an equipment control instruction and a strategy interpretable report which pass verification according to the verification result. According to the method, by fusing multi-source heterogeneous data and combining a dynamic space-time diagram neural network and a hierarchical reinforcement learning model, the energy consumption prediction precision and the scientificity of regulation and control decision are improved, and by means of simulation verification of a digital twin environment model, the safety of an equipment control instruction and the interpretability of a strategy are enhanced.

The invention relates to a gesture recognition and projection fusion non-contact interaction method and device, equipment and a medium. The method comprises the steps of obtaining multi-user gesture original image data, extracting geometric features and boundary features of a hand contour after image preprocessing and noise removal, and generating recognition result data; secondly, on the basis of three-dimensional coordinate information in the recognition result, a tracking trajectory is analyzed through trajectory continuity, a user identity identifier is matched in combination with a user identity feature library, and user space positioning information is generated; then, a three-dimensional track point sequence is extracted from the user space positioning information, an initial projection area is divided by adopting a dynamic area segmentation algorithm, and an operation area mapping relation is formed; and finally, analyzing the operation area mapping relation to extract gesture action features, generating a control instruction set in combination with a preset rule, and scheduling a conflict instruction to generate an instruction execution sequence. By adopting the method, the scene limitation of traditional contact type interaction can be broken through, and the stability and practicability of non-contact interaction in a multi-user environment are improved.