268 results about "Interaction model" patented technology

The invention relates to the technical field of action recognition, in particular to a somatosensory action interaction recognition method and system based on skeleton coordinate points. The method comprises the following steps of collecting real-time skeleton coordinate data of a human body and performing multi-modal feature extraction to obtain a real-time skeleton coordinate sequence; obtaining a standard skeleton posture corresponding to the target interaction action, performing pre-recording and feature coding, and generating a target posture skeleton feature template library; performing skeleton time sequence filtering and joint mapping and joint included angle calculation on the real-time skeleton coordinate sequence, performing similarity measurement and dynamic binding tracking at the same time, and starting a binding recovery mechanism when binding loss is detected so as to guide the user to execute a preset binding posture and re-establish a binding relationship; and mapping the joint included angle time sequence data to a corresponding joint of the virtual human shape interaction model in real time, outputting a somatosensory interaction instruction, and driving to repeat a human body action so as to trigger a somatosensory action interaction event. According to the invention, the stability of somatosensory action interaction recognition can be improved.

The embodiment of the invention provides a memory processing method based on an intelligent agent, a storage medium and an electronic device, a memory architecture of the intelligent agent comprises a first memory layer, a second memory layer and a third memory layer, the first memory layer is used for storing historical dialogue information of interactive dialogue between at least one interactive object and the intelligent agent, and the second memory layer is used for storing historical dialogue information of interactive dialogue between at least one interactive object and the intelligent agent. The second memory layer is used for storing structured events extracted from historical dialogue information, and the third memory layer is used for storing pattern induction memory obtained by performing pattern induction on the structured dialogue events; the method comprises the steps that in response to current round dialogue input information of a target interaction object, target storage information associated with the current round dialogue input information is retrieved from at least one memory layer in a memory architecture, and the current round dialogue input information and the target storage information are assembled into a current cue word; and submitting the current prompt word to a specified interaction model through the intelligent agent, and outputting a response result of the specified interaction model to the interaction object.

The invention provides an urban space intelligent processing method based on multi-modal fusion, and the method comprises the steps: taking multi-modal data as input, and constructing a unified data stream processing and feature alignment mechanism; a physical space is used as a core framework, and the multi-modal data is converted into a space behavior graph with space-time position semantics; constructing an entity attribute-relation type-influence weight ternary interaction model on the basis of an interaction layer of the spatial behavior map, and analyzing a human, object and environment ternary interaction relation in the city and the park based on the ternary interaction model; designing a space intelligent engine with time sequence modeling and dynamic prediction capabilities; and constructing a task processing system. According to the invention, through deep combination of multi-modal fusion and a space intelligent technology, full-link upgrading of urban space from data perception to intelligent decision is realized, and powerful technical support is provided for fine management, efficient operation and safety guarantee of complex space scenes.

The invention discloses a power electronic networking equipment stability analysis method, system, equipment and medium, and the method comprises the following steps: building a full-system state space model, carrying out the cross validation of the full-system state space model through employing a modal analysis method, an impedance analysis method and a complex torque analysis method, and obtaining the stability of the full-system state space model; obtaining a multi-mode coupling stability analysis result; according to the multi-mode coupling stability analysis result, constructing a power grid s domain node admittance matrix; establishing a virtual power angle dynamic equation of the network-forming converter, and optimizing control parameters according to an evaluation result; an inertia center reference system is adopted, a dynamic interaction model of the synchronous machine and the network-forming converter is established, and dynamic coupling characteristics between devices are analyzed through a relative motion equation. According to the method, the comprehensiveness, the precision and the engineering applicability of dynamic stability analysis of the novel power system are improved through fusion of a multi-dimensional collaborative evaluation framework and an innovative technical system.

Methods, systems, and computer readable media for rendering context-aware and interactive artificial intelligence-generated videos in real time. A talking face (“TF”) model may traverse from a first node to a second node of a state graph via an edge based on a TF instruction generated by an interaction model. The TF model may retrieve a transition video associated with the edge and a pre-computed video template associated with the second node from one or more TF databases. The pre-computed video template may include a plurality of masked video frames and a plurality of pre-computed mouth positions for each masked video frame. The TF model may inpaint a pre-computed mouth position into a masked region of each masked video frame to form a video frame stream. The interaction model may generate a video from the transition video and the video frame stream and present the video on a user device.

The invention discloses a simulation method, device and equipment for predicting flow and deformation of a porous medium and the medium. The method comprises the steps that a computational domain is selected, a corresponding computational grid is generated, and porosity initialization is conducted on the computational domain; determining a time step length and a discrete format, and setting a non-uniform factor to solve a control equation set which comprises a continuity equation, a fluid dynamics equation, a skeleton mechanics equation and a porosity updating equation; and analyzing and displaying a solving result. According to the porous medium flow and deformation simulation method independent of hypothesis and empirical parameters, the method is based on the basic principle of the microcosmic fluid-solid coupling effect, a porous medium fluid-solid coupling body kinetic equation is adopted, the situation that a traditional modeling method depends on volume averaging hypothesis and depends on a multi-phase interaction model is avoided, and the modeling efficiency is improved. The method has cross-scale applicability, and provides a new theoretical basis and prediction means for the development of technologies related to porous medium multiphase dynamics and multi-field coupling problems.

The invention relates to the technical field of user behavior data processing, and discloses a user behavior analysis and personalized recommendation method and system, and the method comprises the steps: collecting multi-dimensional behavior data of a user, and carrying out the feature extraction of the multi-dimensional behavior data; key features are defined based on behavior data, redundant features are reduced through a feature selection algorithm, the dimension of numerical features is unified through normalization processing, and an input feature vector used for a deep learning model is generated; processing the input feature vector by adopting a hybrid deep learning architecture, and generating a user-commodity interaction model in combination with the user behavior sequence and the commodity features; performing real-time prediction on the new user behavior data based on a deep learning model, and dynamically adjusting a recommendation strategy according to a prediction result; and displaying a user behavior analysis result through a visual interface, and continuously optimizing a recommendation strategy in combination with an A / B test framework. According to the method, the defects of a traditional recommendation system in the aspects of multi-source data processing, recommendation individuation and the like are effectively overcome.

The invention relates to the technical field of ecological remote sensing and image processing, and particularly discloses a method and system for monitoring the ecological restoration state of thinopyrum intermediary grassland in an alpine region. The method comprises the following steps: acquiring a multi-temporal remote sensing image and ground ecological parameters, and constructing a remote sensing-ground combined observation data set; utilizing a semantic segmentation model of a multi-scale attention mechanism to extract a thinopyrum intermedium block mask; vegetation indexes, texture features and ecological factors are extracted from the mask region to construct a multi-dimensional feature sequence; inputting the feature sequence and manual intervention information into a training factor interaction model in a graph neural network and causal modeling architecture, and outputting a repair level and evolution data according to the training factor interaction model; and generating a visual layer in combination with historical data, and updating a remote sensing feature extraction strategy based on model feedback. The alpine grassland ecological restoration state monitoring system realizes intelligent monitoring and dynamic feedback of the alpine grassland ecological restoration state, has strong timeliness, clear causality and adaptive optimization capability, and is suitable for continuous monitoring and management of a complex ecological system.

The invention belongs to the field of robots, and particularly discloses a mechanical arm man-machine cooperation self-adaptive admittance control method and device, a terminal and a medium, a man-machine interaction model omitting virtual stiffness is constructed, and admittance parameters in the man-machine interaction model comprise virtual inertia and virtual damping; designing a stability observer of the physical man-machine interaction system, monitoring an external force applied by an operator by the stability observer, and performing spectral analysis on a force signal to obtain a system instability index; constructing an admittance parameter adaptive controller through a system instability index, wherein the admittance parameter adaptive controller comprises a virtual inertia adaptive controller and a virtual damping adaptive controller; and the virtual inertia and the virtual damping are adjusted based on the admittance parameter self-adaptive controller, so that the physical man-machine interaction system returns to a stable state. The method realizes self-adaptive adjustment of controller parameters, adapts to a complex environment, and keeps stability of physical man-machine interaction.

The invention relates to the technical field of intelligent network connection automobiles, in particular to an intelligent network connection automobile information interaction method and device based on category personnel judgment, and the method comprises the steps: obtaining a multi-modal data set, designing an improved intelligent interaction model, training the model, carrying out feature analysis, carrying out classification decision making, and generating a personalized interaction scheme. Personnel categories are accurately identified through a multi-modal sensing unit, personalized contents are generated in combination with a dynamic classification module and a context adaptation sub-module, and data security and response speed are guaranteed through a privacy protection module and a real-time enhancement mechanism. According to the invention, the pertinence of information pushing can be improved, the real-time performance of interaction is enhanced, the privacy of the user is effectively protected, and an efficient and safe information interaction solution is provided for the intelligent networked automobile.

The invention discloses a retrieval enhancement system and method based on a multi-modal interaction agent, and relates to the field of artificial intelligence, and the retrieval enhancement system comprises the following steps: obtaining an initial prompt; the initial prompt comprises first data of at least one mode; when a retrieval operation is determined to be performed on the basis of the initial prompt through a multi-modal interaction agent, retrieval is performed on the basis of the initial prompt through a retrieval model to obtain a retrieval result, and the retrieval result comprises second data of at least one modal; determining a target interaction model from a plurality of candidate interaction models through the multi-modal interaction agent based on the modal of the first data and the modal of the second data; and interacting with a user based on the initial prompt and the retrieval result through the target interaction model.

The invention discloses a new energy power station network source coordination performance detection method and system, and relates to the technical field of new energy power grids, and the method comprises the steps: building an interaction model between a new energy power station and a power grid based on operation data, and analyzing the interaction behavior of the energy power station and the power grid through the interaction model; identifying a coordination contradiction point between the random gene of the new energy power station and the deterministic demand of the power grid, and optimizing the coordination contradiction point into a coordination balance point by using a distributed balance control model; and simulating a real-time operation state when the new energy power station accesses the power grid, comparing the real-time operation state with the initial state, and identifying the abnormal coordination performance when the new energy power station accesses the power grid. Through the distributed balance control model driven by the homotopy algorithm, the abstract coordination contradiction point is converted into the specific optimal adjustment set value, a dynamic self-adaptive coordination mechanism between the new energy and the power grid is formed, and the power grid stability and scheduling efficiency after the new energy power station is connected are improved.

The invention discloses a multi-aspect reasoning graph method of an NLP interaction model based on reinforcement learning. The method comprises the following steps: extracting entities and relationships from an input text to construct an initial reasoning graph comprising a plurality of reasoning aspects; a reinforcement learning agent is initialized, a state space of the reinforcement learning agent comprises a graph state and user query, and an action space comprises reasoning operation on a graph; the agent updates a graph or generates a path based on a state selection action, and improves performance through continuous interaction based on a comprehensive reward signal optimization policy; according to the method, the limitation that the prior art focuses on a single reasoning dimension is overcome by constructing the multi-dimensional reasoning graph integrating semantics, logic, context and the like and cooperatively operating the sub-graphs by utilizing the reinforcement learning agent, so that the model can carry out all-dimensional and multi-angle deep analysis on complex queries, and the accuracy of the analysis is improved. The reasoning comprehensiveness and the comprehensive judgment accuracy are greatly improved, and therefore more accurate and complete responses are given in tasks such as questions and answers or dialogues.

The invention provides a self-organizing flight planning method based on behavior parameter dynamic adjustment, and belongs to the technical field of unmanned aerial vehicle flight planning. Each unmanned aerial vehicle obtains and updates own state and environmental threat information through a sensor, and establishes a cluster member level interaction model to interact neighbor motion states; comprehensively considering the interaction between members in the cluster and the interaction between the members and the external environment, respectively calculating an internal interaction effect and an external interaction effect, and further obtaining an overall interaction effect; on the basis of an asynchronous optimization criterion triggered by an event, online optimization adjustment is carried out on a behavior parameter set of the unmanned aerial vehicle in combination with an optimization guard interval, a flight state is predicted through a motion model, an optimal parameter is determined by means of a local performance evaluation function, a final control input driving state is generated and updated, and autonomous flight planning is realized. According to the method, the online cooperative flight requirement of the unmanned aerial vehicle cluster in a dynamic unknown environment is met.

The invention discloses a multi-modal interaction method and system, electronic equipment and a storage medium, and relates to the technical field of image understanding, and the method comprises the steps: obtaining a language instruction input by a user and a target image, and extracting an interaction content region pointed by the language instruction from the target image; inputting the language instruction, the target image and the interaction content area into a multi-modal interaction model for multi-modal information fusion processing to obtain an interaction function identifier and a basic interaction parameter; generating complete interaction parameters according to the basic interaction parameters; and calling an interaction function module corresponding to the interaction function identifier to generate an answer to the language instruction according to the complete interaction parameter, and returning the answer to the user. According to the method, the image-text and interaction content area is identified through the multi-modal interaction model, and the text is complemented through light-weight OCR, so that the time delay can be effectively reduced, and the real-time efficient response requirement of a learning scene is met.

The invention provides an entity enhancement and context-aware paragraph retrieval method for an RAG system for solving the problems of fuzzy query intention and insufficient paragraph context modeling in RAG retrieval. The method comprises the following steps: firstly, identifying and extracting a key entity by using a named entity, carrying out weighted fusion on the key entity and question representation obtained by a pre-training model to form an enhanced query vector, and accurately describing a core semantic intention of the question; secondly, performing semantic modeling on paragraphs in a document library, mining a potential semantic association relationship between the paragraphs, and constructing a context interaction model between the paragraphs based on a graph neural network and a gating loop unit mechanism, so as to obtain paragraph vector representation with complete semantics and clear hierarchy; and finally, calculating the similarity between the enhanced query and the paragraph vector, and completing high-precision paragraph-level retrieval. According to the method, the correlation and the recall rate are remarkably improved, insufficient entity utilization and weak context modeling are relieved, and good expansibility and cross-domain applicability are achieved.

The invention provides a building equipment monitoring method and system based on artificial intelligence, and relates to the technical field of building intelligent management, and the method comprises the steps: firstly obtaining a multi-source monitoring information set of target equipment in a building, including real-time operation parameters, surrounding environment perception and historical operation record information; then scene feature embedding modeling is carried out to obtain an equipment operation state scenarized interaction model; calling a pre-trained artificial intelligence scene evaluation model to carry out time sequence evolution and effect pre-judgment, and generating an equipment operation state evolution trajectory and a regulation and control effect pre-judgment result; determining an optimal regulation and control demand according to the equipment operation state evolution trajectory and the regulation and control effect pre-judgment result, and generating an equipment dynamic regulation and control instruction set; and finally, an equipment dynamic regulation and control instruction set is sent to an equipment execution module, feedback information is received, and evaluation model parameters are iteratively updated, so that intelligentization, precision and dynamic monitoring of building equipment are realized.

The invention discloses an import and export commodity intelligent classification method based on knowledge graph metadata topology, and relates to the technical field of reinforcement learning, and the method comprises the steps: inputting an initial data packet into a dynamic interaction model, carrying out explicit association mining through a semantic enhancement layer, optimizing a rule matching path through a rule evolution layer, and constructing a dynamic commodity knowledge graph; performing topological structure derivation on the dynamic commodity knowledge graph to generate a graph topological analysis report and a metadata list, and performing knowledge reasoning integration on the graph topological analysis report and the metadata list to generate an intelligent navigation engine; calling an intelligent navigation engine to execute multi-path semantic query and rule verification on the dynamic knowledge graph to generate a candidate classification scheme set; and performing multi-target collaborative optimization on the candidate classification scheme set to generate a sorting scheme sequence, performing traceability packaging on the sorting scheme sequence, and outputting an intelligent classification scheme. According to the invention, through the dynamic interaction model and multi-target collaborative optimization, the rule adaptation efficiency in a complex scene is improved.

The invention discloses a vehicle lane changing intention prediction method based on comparative learning under a data missing condition, and the method comprises the steps: building a self-supervised comparative learning framework, employing a twin network structure for an upstream task, and employing a graph attention network module for a downstream task; by constructing positive and negative sample pairs, data representation is learned, so that the positive sample pairs are closer in a feature space, and the negative sample pairs are farther; and respectively processing a complete data sample and a missing data sample by adopting a dual-channel trend attention mechanism. The mechanism can effectively capture the global trend and local change in the time sequence data, and improves the accuracy and reliability of feature extraction. According to the method, the prediction robustness is remarkably improved, the complex operation of traditional data filling is avoided, time sequence dynamic and space interaction can be fused, efficient space-time feature modeling is achieved, and the problems of data missing and space-time interaction modeling confronted by vehicle lane changing intention prediction in an intelligent driving scene are effectively solved.

The invention discloses an ancient building VR education interaction system and method based on gesture control and physical feedback, and relates to the technical field of VR intelligent education. Multi-source data of a target ancient building are collected and processed through a data processing method, and then a corresponding target ancient building three-dimensional model is generated based on the processed multi-source data; establishing a VR education scene through a VR engine, establishing a target ancient building education interaction model, formulating an interaction logic rule between a user gesture and the target ancient building education interaction model, analyzing user interaction data, recording corresponding operation through the VR education scene, and setting a physical feedback signal according to the interaction data of the user; finally, interaction data of the user is recorded in real time, the learning progress, interest points and knowledge mastering conditions of the user are evaluated, the presentation mode of VR education content is dynamically adjusted, personalized learning suggestions and guidance are provided, and powerful support is provided for efficient inheritance and high-quality education of historic building culture.

The invention discloses a highway passenger and freight mixed traffic flow modeling method based on METANET model optimization. The method comprises the following steps: constructing a dynamic critical density correction function based on a freight car proportion; establishing a differentiated lane changing behavior decision-making mechanism, respectively setting lane changing probabilities based on a Logit utility function and a suppression coefficient for cars and trucks, and enhancing the dynamic simulation capability of lane transverse flow distribution; and constructing a ramp interaction model coupled with the truck proportion, and analyzing a traffic capacity attenuation mechanism of the confluence area. According to the method, the macroscopic modeling advantage of the METANET model is kept, and the method has good structural compatibility and generalizability. According to the method, the prediction precision of the flow, the speed and the density in a multi-vehicle mixed traffic scene is superior to that of a traditional model, and the method is suitable for modeling, simulation and control of an intelligent high-speed system.

The invention discloses an equivalence evaluation method for testing the fracture behavior of an irradiation metal material based on a small sample, belongs to the field of mechanical property testing, and deeply researches the size effect problems of non-uniform deformation and crack initiation of the metal material under the irradiation condition through three research means of experiments, theories and simulation. And a powerful basis is provided for performance evaluation of the metal material under the irradiation condition. In the aspect of experiments, micro-stretching and micro-cantilever beam experiments of samples with different sizes under irradiation conditions are carried out, and a correlation mechanism between irradiation material crack initiation and sample sizes is analyzed. On the theoretical aspect, a dislocation channel-grain boundary interaction model is established, and prediction of fracture toughness of irradiation samples of different sizes is achieved. In the aspect of simulation, a finite element simulation system for non-uniform deformation, crack initiation and size effect of the metal material under the irradiation condition is established, and the influence of irradiation and sample size on microstructure evolution and macroscopic fracture behavior of the material is explored.

The invention discloses a smart home interaction method and system based on non-intrusive electroencephalogram / brain magnetic signal identity authentication and a storage medium, and relates to the technical field of smart home. Constructing a smart home integrated interaction model; the method comprises the following steps: acquiring a control instruction signal of a current user in a multi-modal fusion non-invasive mode, converting the control instruction signal into a digital signal, extracting electroencephalogram / electroencephalogram signal features, extracting an electroencephalogram / electroencephalogram signal feature template of an authorized user from an electroencephalogram / electroencephalogram signal database, and comparing the electroencephalogram / electroencephalogram signal features with the electroencephalogram / electroencephalogram signal feature template; if the comparison result is higher than a preset threshold value, marking that the identity authentication of the current user is passed, receiving electroencephalogram / brain magnetic signal characteristics of the current user by a brain control instruction structure, and converting the electroencephalogram / brain magnetic signal characteristics into a smart home interaction instruction; and after receiving the instruction, the smart home integrated interaction model controls the smart home to start and stop, and feeds back an operation result to the user to complete a brain control operation process. According to the invention, safe, convenient and accurate non-invasive brain control of the smart home is realized.

The invention provides a digital human interaction action generation method and device, electronic equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: inputting multi-modal data of interaction between a target user and a digital human into a feature extraction module of an interaction model, and obtaining multi-modal features; wherein the multi-modal features comprise a visual focus feature, a voice feature and a text emotion feature corresponding to the voice feature; the multi-modal features are input into a fusion module of the interaction model, the fusion module adjusts the initial attention score of the fusion module based on the time sequence change features of the visual focus features, and the adjusted attention score is obtained; and the fusion module performs fusion processing on the multi-modal features according to the adjusted attention score to obtain multi-modal fusion features, and generates control parameters for driving at least one body part of the digital human to move according to the multi-modal fusion features.

The invention discloses a multi-modal interactive brain training system, method, device and medium. The system comprises a multi-modal signal acquisition layer, a brain dynamics modeling layer, a cross-modal cooperative training layer, a three-dimensional evaluation layer and a brain function adaptation scene generation layer. The multi-mode signal acquisition layer synchronously acquires surface physiological, behavior and deep brain image signals; the brain dynamics modeling layer preprocesses the signal, constructs a brain region interaction model and positions a core brain region pair and an interaction strength threshold value; the cross-modal cooperative training layer generates and adjusts a training task according to the training task; the three-dimensional evaluation layer fuses related features to generate a comprehensive rehabilitation score; the brain function adaptation scene generation layer adjusts training scene elements based on brain function bias features. According to the invention, through synchronous acquisition of multi-modal signals and dynamic modeling of brain functions, accurate adaptation of training tasks, scenes and brain region functions is realized; three-dimensional evaluation guarantees effect quantification and mechanism explanation, and rehabilitation pertinence, scientificity and user compliance are improved.

The invention discloses an interaction model training method and device, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining a training sample set, the training sample set comprises a plurality of training samples, the training samples at least comprise first training data, second training data, and third training data, the first training data is used for representing a user emotion corresponding to a user state of the user, the second training data is used for representing a role behavior executed by a virtual role corresponding to the user under the user emotion, and the third training data is used for representing a user behavior executed by the user under the user emotion; inputting the first training data and the second training data into a to-be-trained interaction model, and obtaining a predicted user behavior output by the to-be-trained interaction model; and training a to-be-trained interaction model according to the predicted user behavior and the third training data to obtain a trained interaction model. According to the interaction model, the virtual character can provide more personalized interaction experience for the user.

The invention relates to the technical field of data processing, and discloses a multi-station microwave oven intelligent cooking combined control method and system. The method comprises the following steps: acquiring temperature, water content and weight data of each station to establish a multi-station comprehensive state vector, inputting the state vector into a graph neural network to establish a station interaction model, determining a parallel execution scheme by adopting an out-of-order execution strategy based on the interaction model, returning to a stable state when a pre-calculated execution state is not consistent, and executing the multi-station interaction model. And dynamically adjusting power and time slice distribution to generate a cooperative control instruction. According to the multi-station microwave oven, the problem that all stations in the multi-station microwave oven are lack of cooperative control and intelligent scheduling is solved, and the overall efficiency of multi-station cooking and the consistency of food cooking quality are improved.

The invention provides an emotional voice interaction method and device based on a humanoid robot, and relates to the field of robot interaction. The method comprises the following steps: acquiring voice data of a target user through a humanoid robot, and extracting acoustic features and semantic features in the voice data; inputting the acoustic features and the semantic features into a cross-modal fusion emotion classification model, and outputting an emotion recognition result corresponding to the target user; determining an emotion recognition misjudgment risk, and correcting an emotion recognition result based on the emotion recognition misjudgment risk; inputting the corrected emotion recognition result and the semantic feature into an emotion voice understanding interaction model, and outputting an emotion voice interaction result; and controlling the humanoid robot to execute a corresponding multi-modal interaction response based on the emotion voice interaction result. The problem that the voice interaction experience is greatly reduced due to the fact that the voice interaction content output by an existing humanoid robot is difficult to fit the real emotional state of the elderly user in multiple aspects such as text expression and voice emotion is solved.

The invention belongs to the field of artificial intelligence, and particularly relates to a voice interactive intelligent terminal emotion adaptation system for teenager users. According to the system, accurate recognition, dynamic modeling and active guidance of adolescent emotions are realized through five units, namely, multi-modal emotional feature perception, developmental stage psychological modeling, nonlinear emotional evolution prediction, adaptive interaction strategy decision and feedback closed-loop regulation. According to the system, a development psychological theory is fused, acoustic, semantic and non-verbal features are combined, a personalized emotion interaction model is constructed, real-time and low-delay flexible emotion response is completed on the premise that privacy is guaranteed, and the affinity of human-computer interaction and the mental health supporting capacity are effectively improved.

This invention provides an active flow control method and system based on intelligent algorithms. The method includes: determining the number of inlet parameter sets for a typical flight state point, constrained by simulation economy and sampling efficiency; performing numerical simulations according to the number of inlet parameter sets to obtain dataset 1, with inlet parameters as independent variables and flow field characteristics as dependent variables; obtaining dataset 2, with flight state as independent variables and flow field characteristics as dependent variables, through numerical simulation for a certain set of inlet parameters; constructing a proxy model of inlet flow field characteristics for a typical flight state point using deep learning based on dataset 1; constructing a proxy model of inlet flow field characteristics for a wide-speed-domain flight state based on the proxy model of inlet flow field characteristics for the flight state point, using a transfer learning algorithm and dataset 2; constructing an environment-agent interaction model based on a deep reinforcement learning algorithm, using the proxy model of inlet flow field characteristics for a wide-speed-domain flight state as the environment model for deep reinforcement learning; setting optimization termination conditions based on the environment-agent interaction model, and obtaining a control sequence with continuously optimal inlet performance under different flight states through deep reinforcement learning. This invention can stably adapt to flight scenarios with a wide speed range and a large airspace, and achieve real-time optimal control of the air intake flow field under a wide speed range, solving the problem of poor generalization ability of traditional methods under different operating conditions.