486 results about "Interaction model" patented technology

The invention discloses an industrial robot real-time adaptive control method and system based on digital twinning, and relates to the technical field of industrial robots. The digital twin engine module runs a high-fidelity dynamics simulation model and an environment interaction model, performs real-time state estimation, abnormal working condition recognition and twin parameter dynamic updating, is seamlessly integrated with the control execution module, and provides decision support with high robustness and high adaptability for an industrial scene; the adaptive control module performs online rolling optimization on a control strategy based on a deep reinforcement learning algorithm, generates joint space trajectory correction, tail end precision compensation and dynamic load adaptability optimal instructions, and realizes parameter adaptive setting through fuzzy logic or a neural network; and the fault diagnosis module performs multi-scale time sequence analysis by using an LSTM and convolutional neural network fusion model, detects position offset, moment sudden change or temperature overrun and other abnormalities, and triggers emergency shutdown, sound-light alarm and an adaptive recovery strategy.

The invention provides an intelligent inspection path planning method and system based on reinforcement learning, and relates to the technical field of path planning, comprising the steps of constructing a scene understanding model and a dynamic interaction model, and forming a cognitive enhanced digital twin system. Metaheuristic search and social learning mechanisms are fused, and the inspection efficiency, energy consumption and risk are balanced through a multi-target conflict coordinator. The group behavior emergence prediction model achieves dynamic prediction of a collaborative mode, the federated learning framework achieves aggregation of experience knowledge, a group evolution strategy with high adaptability is generated, and closed-loop optimization from task execution to cognitive enhancement is achieved through a robustness evaluation mechanism fed back in real time and a task allocation optimizer based on an attention mechanism. And the inspection efficiency and adaptability are improved.

The invention provides an intelligent rehabilitation training method and system based on artificial intelligence and virtual reality, a user wears an intelligent wearable device to collect multi-modal data such as electroencephalogram, myoelectricity, physiological features and motion signals, the multi-modal data is preprocessed and then input into an artificial intelligence training model, and key features are extracted and fused by using a graph convolutional network and an attention mechanism algorithm. And constructing a digital twinborn model by using the fusion features, performing real-time dynamic mapping and predictive simulation, and generating a customized training scheme by means of a reinforcement learning algorithm in combination with a rehabilitation target and a physical state of the user. A user is trained in the virtual reality interaction model, the system monitors actions and physiological states in real time, the digital twin model synchronously acts, and the scene is dynamically adjusted. After training, the rehabilitation effect is evaluated according to the physiological indexes, the motion data and the twinning optimization analysis result, and an optimization training scheme and a digital twinning model are fed back. Precision, individuation and intelligentization of rehabilitation training are achieved, and the training effect and quality are improved.

The invention discloses an intelligent scheduling and optimization method for an industrial electrical automation system, and the method comprises the following steps: deploying a distributed sensor network to collect electrical parameters, an equipment vibration spectrum and production work order data in real time, and constructing a unified feature vector based on time-space alignment and confidence weighting; a production system-energy management-external power grid three-layer interaction model is established, and a dynamic carbon emission calculation engine and process deadlock detection module is embedded; an improved NSGA-III algorithm is adopted to solve a multi-target Pareto leading edge, and energy consumption, productivity and carbon emission target priorities are adjusted in real time in combination with a dynamic weight mechanism; distributed optimization is executed through an edge-cloud federated architecture, cross-system instruction synchronization is achieved, and closed-loop dynamic feedback is formed. According to the method, the limitation of traditional single system optimization is broken through, the energy consumption is reduced by 15%-30%, the carbon emission intensity is reduced by 12%-18%, the abnormal response speed is increased to 3 seconds, and intelligent decision making and green transformation in a complex industrial scene are supported.

The invention relates to a DVS vibration signal semantic representation method based on prior knowledge enhancement, and relates to the field of signal processing and artificial intelligence. The method comprises the following steps: (1) constructing a distributed vibration signal text enhancement data set; (2) cross-diffusing the standardized DVS vibration signal; (3) multi-band input alignment is carried out; (4) residual signal enhancement; (5) DVS vibration signal feature extraction; (6) aligning and mapping DVS vibration signal semantic features; and (7) fine adjustment of the DVSLLM model. According to the method, the technical problems that in the field of signal processing, sampling frequencies are not uniform, spatiotemporal features are difficult to extract, semantic information is difficult to represent and the like are solved, and a text enhancement data set is constructed by utilizing Deepseek-V3; a fine-grained interaction model from DVS vibration signals to natural language questions and answers is constructed through cross diffusion standardization, two-dimensional discrete transformation, multi-scale convolution, a CBAM attention mechanism, bilingual sense mapping alignment and DVSLLM model fine tuning, and an intelligent method is provided for road roadbed vibration event health monitoring.

The invention provides a micro-grid group-containing AI active distribution network scheduling optimization method, a medium and a system, and belongs to the technical field of power grid scheduling. The method comprises the following steps: firstly, constructing a micro-grid group and main and distribution network interaction model, and determining boundary constraints; predicting key parameters of the micro-grid group by using deep reinforcement learning; constructing an active distribution network power balance equation and topology constraint conditions; solving by adopting mixed integer programming to obtain power flow distribution of the distribution network; constructing a power grid dispatching optimization objective function based on a quantum evolutionary algorithm; processing multi-source data by using an MGPN deep neural network to output an optimal scheduling strategy; monitoring a running state verification effect in real time through a state estimation technology; updating the strategy in real time by applying a rolling optimization mechanism; and establishing an evaluation system to dynamically optimize neural network model parameters, realizing efficient collaborative scheduling of the micro-grid group and the active power distribution network, and solving the technical problem of low distributed energy consumption rate in the collaborative scheduling optimization process of the micro-grid group and the active power distribution network.

The invention discloses a time-space interaction vehicle trajectory prediction method based on speed perception, and the method comprises the steps: obtaining driving trajectory data of a target vehicle and surrounding vehicles in a perception range of the target vehicle, inputting the driving trajectory data into a pre-trained trajectory prediction model, and obtaining the trajectory data of the target vehicle in a prediction time period; the trajectory prediction model comprises an encoder module, a speed sensing interaction modeling module and a decoder module; in the encoder module, a spatial-temporal feature encoder is used for obtaining spatial-temporal feature codes based on the driving tracks of the target vehicle and other vehicles; the scene perception encoder is used for extracting a global spatial dependency relationship between vehicles to obtain a scene perception spatial code; the speed perception interaction modeling module is used for extracting space-time interaction features and scene interaction features of the target vehicle and surrounding vehicles by using a multi-head attention mechanism based on the space-time features and scene perception space codes, and further obtaining global interaction features; and the decoder module is used for obtaining a driving track of the target vehicle in the prediction time period based on the space-time interaction characteristics and the global interaction characteristics. According to the method, the vehicle-scene spatial dependency can be accurately captured, and the trajectory prediction accuracy is improved.

The invention provides a digital human generation method based on a multi-modal large model. The method comprises the following steps: constructing a digital human basic model; generating a structured training set; generating a question and answer model supporting multi-channel interaction; semantic answers of the user questions are output, text emotional tendencies of the semantic answers are extracted, and emotional intensity parameters are output; generating facial muscle movement track data, and performing real-time rendering on the digital human basic model according to the facial muscle movement track data to output a digital human three-dimensional image with emotion expression. According to the embodiment of the invention, cross-modal alignment is carried out on text, image and audio data, and a multi-modal large model containing visual, voice and knowledge models is optimized by using a joint training method, so that more natural and smoother multi-channel interaction experience is realized; in addition, by introducing an emotion recognition model and a face interaction model, the emotion tendency contained in the semantic answer can be captured and reflected more accurately, so that a digital human three-dimensional image with real emotion expression is output.

The invention relates to the technical field of intelligent man-machine interaction, and discloses a customized virtual pet interactive simulation method, which comprises the following steps: S1, perceiving the emotional state of a user, S2, analyzing the behavior and emotion of the user, S3, establishing a virtual pet behavior model, and S4, establishing a virtual pet interaction model. The invention provides a customized virtual pet interactive simulation system, which comprises a sensing module, a decision-making module, an execution module and a feedback module. The method comprises the following steps: S1, selecting a virtual pet behavior, S2, selecting an optimal behavior, S5, carrying out deep reinforcement learning optimization, S6, executing the virtual pet behavior, and S7, feeding back and adjusting a behavior strategy. The invention also provides the customized virtual pet interactive simulation system, which comprises a sensing module, a decision-making module, an execution module and a feedback module. Through long-term emotional state tracking, personalized behavior pattern recognition and long-term reward correction of reinforcement learning, the virtual pet can continuously optimize a behavior strategy, dynamically adapt to long-term emotional changes of a user, and improve the personalized matching degree and long-term stability of interaction.

In various examples, an interactive agent platform that hosts development and / or deployment of interactive agent may include an interpreter that generates interaction modeling API events specifying commands to make agent (e.g., bot) expressions, poses, gestures, or other interactions or movements, which may be translated into corresponding agent animations. The interpreter may generate an interaction modeling API event using a standardized interaction categorization schema, which an action server implementing an animation service may use to identify a corresponding supported animation. The animation service may implement an action state machine and action stack for all events related to a particular interaction modality (e.g., bot gestures), connect with an animation graph that implements a state machine of animation states and transitions between animations, and instruct the animation graph to set a corresponding state variable based on a command to change the state of an agent movement represented by an interaction modeling API event.

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 discloses an Alzheimer's disease long-term prediction and dynamic intervention method based on deep learning. Accurate dynamic intervention from group statistics to individual dynamics is realized through time sequence alignment, multi-scale time sequence feature extraction, dynamic risk assessment and personalized intervention. Through time sequence alignment and multi-scale time sequence feature extraction, a time-sensitive personalized intervention scheme can be generated. And carrying out continuous time modeling by adopting a cubic Hermite interpolation method and a neural control differential equation, and predicting the long-term risk. By establishing a double-track interaction model, a pathological track and a functional track of a user are analyzed, so that time-varying association among multi-modal data can be dynamically captured. A personalized intervention strategy is provided through reinforcement learning, the intervention strategy is dynamically adjusted in combination with risk reduction amplitude, intervention measure compliance and physiological index change, the effect of short-term behavior change and long-term prediction is balanced, and the Alzheimer's disease is further promoted to be converted from passive treatment to active intervention.

The invention relates to a multi-person motion capture real-time digital human driving method based on a skeleton-muscle interaction model, and belongs to the field of artificial intelligence and ubiquitous universe. According to the method, the key points of the human body are detected through YOLO-Pose, the positions of the shielding points are obtained through a double-stage dynamic shielding point compensation method, and the accuracy of the key points is guaranteed. And outputting the three-dimensional coordinates of the key points of the human body by adopting a three-dimensional key point depth extractor based on multi-dimensional exclusive-shared feature reasoning in combination with an MT ransPose model. A real person-skeleton model-digital person real-time mapping method is provided, three-dimensional key points are mapped to a standard human body skeleton model, and a digital person role and the skeleton model are bound through a weight mapping algorithm. Based on a skeleton-muscle interaction model, the digital person accurately reflects a real motion posture by introducing the mechanical action of a skeleton rigid body dynamic model and a muscle force line model, and the process of driving the digital person in real time through multi-person motion capture is achieved.

This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for performing interaction between displays of an automobile. In some implementations, the method may include displaying, on a first screen, a first graphical user interface (GUI) including multiple regions, a first region including multiple graphical representations, each graphical representation representing a respective application through which a user can interact with the respective application. In addition, the method may include detecting a user input on a selected graphical representation of the multiple graphical representations on the first GUI. The method may include in response to the detecting the user input, launching, on a second screen different from the first screen, the application corresponding to the selected graphical representation, the application being displayed on a second GUI of the second screen while displaying the graphical representation of the application on the first screen.

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 VR teaching experience enhancement system and method, and belongs to the technical field of virtual teaching, and the method specifically comprises the steps: collecting the position data and posture data of a trainee in a VR environment, building a multi-user coordination interaction model based on the position data and posture data of the trainee in the VR environment, and carrying out the interaction of the multi-user coordination interaction model. The method comprises the following steps: acquiring training participants, identifying an interaction relationship and an interaction event among the training participants, generating tactile feedback data corresponding to the interaction event based on the interaction event, performing calibration processing on the tactile feedback data, and synchronously sending the calibrated tactile feedback data to VR equipment of the training participants, the calibration processing comprises adjusting the tactile feedback data based on the spatial propagation difference quantity and the tactile feedback time offset value of the trainees; according to the invention, when multiple trainees cooperatively operate the same virtual object or scene, consistent and real-time tactile response and spatial perception can be obtained, and the teaching experience in a multi-person cooperation scene is improved.

The invention relates to a rigid-flexible trans-mass self-adaptive robot force position and rigidity collaborative optimization method and system, and relates to the technical field of robot control, and the method comprises the steps: firstly, carrying out the linearization processing of a robot dynamic model through a semi-implicit integral method, and obtaining a robot dynamic model; and in combination with an extended Kalman filter, stiffness parameters in the contact operation process are estimated in real time, a dynamic stiffness sensing model is constructed, and the system response capability is effectively improved. Then, a rigidity parameter is embedded into a Hertz contact model, the dependence of a traditional model on prior information of a contact surface is broken through, a dynamic interaction model between the robot and an operation object is established, and high-precision real-time sensing of normal force and friction force is achieved. And finally, under a nonlinear model predictive control framework, multi-dimensional physical constraints are constructed based on the contact force, the position and the contact rigidity, an optimal control model is obtained, control input is dynamically and adaptively updated through rolling optimization, and the stability and the control precision of the robot in rigid-flexible heterogeneous contact operation are improved.

A system for serving personalized advertisements based on biometric and identifying data captured by sensors. The system employs pre-processing, feature extraction, and recognition modules to identify individuals. A context-aware processing module adapts recognition strategies based on environmental data and analyzes personal information to confirm the identity of the targeted individual and send targeted advertisements. The system includes display and speaker modules for visual and audio advertisements, a predictive interaction modeling module for generating personalized advertisements, and a cross-platform behavior analysis module for analyzing user behavior across offline and online platforms.

The invention discloses a dietary pattern evaluation method and system based on digital intelligent analysis, and relates to the technical field of dietary pattern evaluation.The method comprises the steps that a mobile terminal is used for synchronously collecting multi-modal data, and the multi-modal data are preprocessed; food pictures are retrieved based on keywords to form a data set, an image recognition model is constructed, the volume and area of food materials are calculated in combination with a 3D reconstruction technology, a food material density database is matched, and automatic estimation of the quality of the food materials is achieved; building a voice interaction model fusing characters and regional voice features, and recognizing food material types and food material quality by using voice data; a dynamic allocation weight is calculated through multi-modal confidence, a graph attention mechanism is utilized to detect and correct data conflicts, and a space-time constraint rule base is combined to align dispersed intake records; and constructing a data visualization chart library. According to the method, the rise of dietary structure analysis from extensive statistics to refined intelligent evaluation is realized, and the problem of error accumulation caused by dependence on a single data source in a traditional method is effectively solved.

In various examples, an interactive agent platform that hosts development and / or deployment of an interactive agent may include an interpreter programmed to iterate though one or more flows until reaching an event matcher, a top level flow may specify instruction(s) to activate any number of flows comprising any number of event matchers, the interpreter may use any suitable data structure to keep track of active flows and corresponding event matchers (e.g., using a tree or other representation of nested flow relationships), and the interpreter may employ an event-driven state machine that listens for various events and triggers corresponding actions specified in matching flows (with event matchers that match an incoming interaction modeling API event). As such, the interpreter may execute a primary processing loop that processes incoming interaction modeling API events and generates outgoing interaction modeling API events that implement the interactive agent.

The invention relates to the technical field of medicine and artificial intelligence, and discloses an elderly care-oriented medical and nursing combined knowledge service system construction method, which comprises the following steps of collecting sentiment expression data of the elderly, applying a nonlinear time sequence analysis and deep learning model, extracting sentiment dynamic characteristics, and obtaining sentiment expression data of the elderly; recognizing an early signal with reduced emotion regulation ability; on the basis of the obtained emotion dynamic features, a memory enhanced attention network is combined with a psychological knowledge graph, an individualized emotion cognitive interaction model of the old people is constructed, a dynamic interaction mechanism between an emotion state and a cognitive mode is revealed, and key intervention nodes are recognized; based on an emotion cognition interaction model and a key node recognition algorithm, the system can accurately position key links of mutual influence of emotion and cognition, and targeted intervention is achieved; and a dual-channel collaborative intervention strategy adjusts an emotional state and reconstructs a cognitive mode through multi-agent reinforcement learning, and breaks through an emotional cognitive vicious circle.

The invention discloses an intelligent data analysis method and system based on semantic interaction, belongs to the technical field of big data processing and analysis, and aims to solve the technical problems that a traditional data analysis method has limitation when processing a large-scale, multi-dimensional and semantic complex data set, the analysis depth is insufficient, and the analysis efficiency is high. According to the technical scheme, the method comprises the steps that multi-modal data collection and data preprocessing are conducted, specifically, data are efficiently collected from a multi-source heterogeneous data source, distributed cleaning is conducted on the collected multi-modal data by removing repeated data, supplementing missing values and replacing wrong data, the cleaned data are labeled and classified, and a corpus is constructed; training the pre-training language model by using a corpus to generate a semantic interaction model with a semantic intelligent analysis capability; and analyzing and processing user input contents based on the trained semantic interaction model, and finally outputting a data result set meeting user requirements.

The invention discloses a detection laboratory total factor digital twinning model construction method and an intelligent operation and maintenance system, and relates to the field of digital twinning, and a total factor digital twinning model comprises a detection laboratory physical object model, a detection laboratory virtual model, a total factor data model, a data interaction model, a learning decision model and an operation and maintenance management model. Real-time mapping is kept between the physical object model and the virtual model of the detection laboratory; the total element data model is used for collecting, inputting, processing and updating multi-source heterogeneous data in the digital twinborn model of the detection laboratory; the data interaction model carries out fusion transmission on real-time data among the models; and meanwhile, the learning decision-making model performs autonomous decision making and diagnosis, and functions are integrated and displayed through the operation and maintenance management model, so that the intelligent operation and maintenance level of the detection laboratory is further improved. The whole detection process of the detection laboratory is digitalized, the communication cost of the detection test process is saved, the manpower and time cost is saved, and the detection efficiency is improved.

The invention belongs to the technical field of intelligent medical treatment, and discloses a chronic disease information management system based on a behavior interaction model. Comprising the following steps: acquiring background information, internal motivation and cognitive evaluation; based on the background information, a health education content library is constructed, and health education content is pushed in combination with cognitive evaluation; fusing the background information and the internal motivation to generate a multi-dimensional treatment scheme matrix; acquiring willingness information of a patient, performing quantitative evaluation on acceptance degrees of different treatment schemes, and screening out an optimal treatment scheme; acquiring and analyzing real-time interaction data, and dynamically formulating an emotion support strategy; patient health data are integrated, and the interaction effect is evaluated; according to the interaction effect, the health education content, the optimal treatment scheme and the emotion support strategy are intelligently optimized in sequence; behavior interaction is taken as the core, and accurate management of the whole life cycle of the chronic disease patient is realized, so that the health management effect of the patient is remarkably improved, and the complication risk is reduced.

The invention discloses an Internet of Things intelligent application method and device based on a large language model, belongs to the technical field of Internet of Things equipment, aims at solving the problems of complexity and inconvenience of user interaction, insufficient compatibility between equipment and poor security and privacy, and comprises the following steps: S1, demand analysis and system design; s2, data collection and preprocessing; s3, language model integration and processing; s4, intelligent decision making and automatic management; by setting the natural language processing module and the large language model, the natural language instruction of the user can be understood and generated through the natural language processing technology, so that the user can carry out equipment control and information query by using simple statements, the complexity of operation is reduced, and meanwhile, by combining the voice recognition technology, the user experience is improved. The user can interact with the Internet of Things system through voice, the model can accurately understand voice input, real-time feedback and operation execution are provided, and user experience and operation convenience are remarkably improved.

The invention discloses a state evaluation and fault early warning method and system based on superconducting current limiter modeling, an electromagnetic heat multi-physical field coupling model of a superconducting current limiter is constructed based on finite element software, and the method comprises the following steps: constructing a three-dimensional geometric structure of a solenoid-shaped superconducting current limiter, and setting a peripheral electromagnetic environment boundary; establishing an electromagnetic field control equation based on a Maxwell equation set and the nonlinear resistivity characteristic of the superconducting material, and coupling a solid heat transfer control equation to form a multi-physical field interaction model; optimizing grid division to balance calculation precision and solving efficiency; body parameters of the superconducting current limiter including the initial critical current Ic0 and the critical temperature Tc and working condition parameters including the environment temperature and the transmission current It are input, the parameters are dynamically adjusted according to the actual operation scene, and the voltage U at the two ends during normal operation is calculated through a model; by collecting voltage measured values Up at the two ends of the superconducting current limiter during actual operation in real time, whether the voltage measured values Up exceed a threshold value set according to the voltage U or not is judged, and an early warning mechanism is triggered.

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.