53 results about "Adaptive interaction" patented technology

The invention provides an intelligent examination and approval method, system and device based on a multi-modal large model and a medium, and belongs to the technical field of artificial intelligence. The method comprises the following steps: analyzing a multi-modal examination and approval material through a visual large model to obtain multi-modal feature information; performing semantic understanding by using the language large model to generate structured semantic data; performing entity matching, relationship verification and logical reasoning based on the knowledge graph to generate a research and judgment report; intelligent decision support and risk early warning are realized; approval instruction conversion, service evaluation and self-adaptive interaction are realized through a multi-mode interaction technology; and continuously optimizing the model and the knowledge base by using the approval process data. According to the invention, by constructing a technical framework of deep fusion of vision, language and knowledge, comprehensive intelligentization of the approval process is realized, and the beneficial effects of improving the approval efficiency, guaranteeing decision fairness, enhancing the complex material processing capability, improving the user experience and realizing continuous evolution of the system are achieved.

The invention discloses a water conservancy flood control scene-oriented question and answer intention recognition and multistage classification model construction method and system and a computer readable storage medium. The method comprises the steps of data collection and knowledge fusion; data preprocessing and intention system construction; constructing training data; training an intention recognition model; an online application mechanism; and model optimization and feedback closed loop. By constructing a standardized data acquisition process, a specialized intention recognition model and a high-adaptability interaction mechanism, accurate understanding and structured expression of the natural language instruction of the user in the flood control scene are achieved, and then the intelligent level of key services such as scheduling and early warning is improved.

The embodiment of the application provides a kind of based on multi-dimension recognition's vehicle emotion interaction method and device, through innovatively constructing emotion fusion identification model, by integrating facial expression, speech emotion, driving behavior and physiological state characteristics, the accurate judgment of driver emotion is realized.Design scene-based adaptive interaction strategy, combined with external environment data and danger level, establish interaction trigger threshold for intelligent matching.Introduce interaction effect evaluation mechanism, through online learning module, continuously optimize interaction strategy model, realize the dynamic adjustment of personalized interaction content.The method effectively solves the deficiency of traditional technology in emotion recognition, interaction strategy and effect evaluation, significantly improves the intelligent level and user experience of vehicle emotion interaction.

This invention discloses a multimodal interactive interface design method for elderly care robots, relating to the field of intelligent elderly care. The method includes: collecting user facial images, voice signals, and touch operation information to form a raw multimodal data stream; processing the raw multimodal data stream to extract standardized user real-time state feature vectors; inputting the user real-time state feature vectors and historical interaction data into a support vector regression model; obtaining the real-time cognitive load level based on the user's real-time state feature vectors in the current session; and analyzing the rate of change of user touch operation accuracy within a time window using historical interaction data, calculating the acceleration value of capability change and the trend of touch operation accuracy, and fusing them to derive the interaction abstraction level. This invention constructs a joint decision matrix sensitive to the acceleration of capability change, dynamically triggering an adaptive interaction strategy when accelerated capability decline is detected, driving the interface engine to adjust interface rendering and multimodal guidance in real time.

The invention discloses a self-adaptive interaction method based on multi-modal fusion perception, and belongs to the technical field of man-machine interaction and artificial intelligence. According to the method, multi-modal data of vision, hearing, physiology and the like of a user and an environment are synchronously collected, depth feature alignment and semantic understanding are carried out by utilizing a fusion neural network, and a depth state vector representing a comprehensive state and context of the user is generated. Based on this, an adaptive decision module integrating a rule engine and deep reinforcement learning dynamically generates a structured interaction instruction including modality, content, time sequence and strength parameters. Finally, through a high-precision synchronous scheduling mechanism, multiple physical actuators are coordinated to output fusion and coherent interaction feedback. The method solves the problems of one-sided perception and rigid response of an existing interaction system, realizes accurate understanding and active and personalized adaptation of a dynamic scene and a user hidden state, and is particularly suitable for complex scenes with high requirements on safety and experience, such as an intelligent cabin and the like.

The invention relates to the technical field of intelligent blind guiding, and discloses an intelligent blind guiding cap system based on multi-modal perception, which comprises a multi-source data acquisition module, a data processing module, a multi-terminal interaction and prompt module and a collaboration and optimization module. Through multi-modal perception fusion, visual information of the obstacle is captured, sound source and temperature and humidity data are also included, and correlation reasoning is carried out, so that the problem of a single-modal perception blind area is solved, the accuracy of obstacle recognition in complex environments such as rainy days is improved, and the safety of the blind guiding process is greatly enhanced; meanwhile, through layered adaptive interaction and integration of bone conduction hearing, micro-vision display, tactile vibration and other multi-sensory prompt modes, users with residual vision and mild hearing impairment are covered, the prompt information receiving rate is increased, and adaptive coverage of different user groups is achieved.

This invention discloses an adaptive interaction method, device, equipment, and medium for intelligent vehicle cockpits. The method includes: collecting multi-source perception data, including visual perception data, voice perception data, physiological perception data, and vehicle state perception data from drivers and passengers; cleaning, time-synchronizing, and feature-level fusion processing of the collected multi-source perception data to obtain a feature vector to be identified; analyzing the feature vector based on a trained emotion recognition model to identify the behavioral and emotional state labels of drivers and passengers, generating a comprehensive risk label; matching a corresponding cockpit interaction strategy from a preset strategy library based on the comprehensive risk label, and adjusting the cockpit state based on the cockpit interaction strategy. This technical solution can achieve the goals of improving driving safety, alleviating negative emotions, and enhancing the driving experience.

This invention relates to the field of rehabilitation robot control technology, specifically an adaptive interactive control method for rehabilitation robots incorporating controllable damping. To simultaneously achieve joint position control within limits and adaptive variable-intensity human-machine interactive training for the rehabilitation robot, a hysteresis-fuzzy-PD (MD-Fuzzy-PD) inner-loop controller is designed by establishing a human upper limb resistance model. This enables the rehabilitation robot to accurately track the target position, ensuring response speed and stability while reducing position overshoot, avoiding dangerous postures, and ensuring the safety of exercise training. For variable-intensity training requirements, an adaptive trajectory generator based on Lyapunov functions is designed to correct the reference trajectory through interactive forces. By estimating model parameters online, the desired trajectory is calculated and corrected in real time, and then the inner-loop controller completes real-time tracking of the desired trajectory, ultimately achieving active and compliant human-machine interactive training.

The application belongs to the technical field of swarm intelligence control, and proposes an agent cluster pursuit and evasion game method based on hierarchical reinforcement learning. The method maps discrete instructions and continuous actions to target assignment and path planning respectively in view of the problem of mixed decision space in the cluster pursuit and evasion scene, and proposes a novel hierarchical reinforcement learning framework. In view of the uncertainty problem caused by the enemy strategy, moving obstacles and insufficient training, a robustness-enhanced adaptive method is proposed. In addition, the method embeds a probability integration network between the instruction network and the action network for quantifying uncertainty, and adjusts the interaction frequency of the two-layer network based on uncertainty. In view of the instability problem of the traditional training method, a fusion training method is proposed. The method independently pre-trains the instruction network and the action network, and cross-trains the two networks to promote the adaptive interaction mechanism.

The invention discloses a multi-mode AI interaction method and device, a medium and a product, and the method comprises the steps: obtaining user portrait data, real-time scene data and user memory data; a fusion feature vector is generated; determining a target style, and combining the target style with the fusion feature vector to obtain a plurality of candidate multi-modal interaction contents; carrying out sorting processing on the plurality of candidate multi-modal interaction contents, and determining target multi-modal interaction contents; outputting the target multi-modal interaction content, and obtaining a user voice stream, a user image stream, a user video stream and a user text stream; performing timestamp alignment processing on the user voice stream, the user image stream, the user video stream and the user text stream to obtain multi-modal data; performing emotion recognition processing on the multi-modal data to determine a current emotion state; and matching and determining an interaction strategy by using the current emotional state, generating an adaptive interaction response and outputting the adaptive interaction response. By implementing the scheme, the overall intelligent level of man-machine interaction and the user experience are enhanced.

The invention relates to the technical field of Internet of Things, and discloses a cloud platform general interaction method and device, computer equipment and a storage medium, a message rule group is configured on a cloud platform according to the category of an intermediate node, and matching between the intermediate node and a terminal device and message rules can be realized only by depending on the transmission direction of message data and a communication protocol. The message data can be subjected to adaptive interaction of the cloud platform, the intermediate node and the terminal equipment according to the matched message rule, codes or structures of the cloud platform, the intermediate node and the terminal equipment do not need to be transformed, zero-code adaptation is achieved, and adaptation time consumption and cost are greatly reduced; and the cloud platform updates the online state of the associated terminal equipment by monitoring the state of the intermediate node, so that the equipment difference is effectively dealt with, and the interaction efficiency and the system adaptability are improved.

The application relates to the technical field of robot control, in particular to a conference investigation robot control method and system based on artificial intelligence. The method comprises the following steps: acquiring audio data and monitoring data of a conference environment; analyzing the monitoring data and the audio data to determine a speaking state and speaking content; determining a speaking distribution heat map according to the speaking state and the speaking content; determining a robot active interaction strategy according to the speaking content and the speaking distribution heat map, and sending the robot active interaction strategy to the robot to enable the robot to execute the active interaction strategy to guide conference discussion. The method improves the accuracy and real-time performance of intention understanding, provides structured input for heat map generation and interaction strategy, realizes real-time visualization of conference discussion distribution, eliminates the defect that a heat map cannot be automatically generated, improves the monitoring capability of participation balance, realizes an adaptive interaction mechanism, eliminates the delay of relying on manual intervention, and ensures efficient and accurate promotion of the conference.

The application discloses a wisdom scene self-adaptive interaction method and system based on a multi-modal large model, relates to the technical fields of artificial intelligence, natural language processing and the Internet of Things, and comprises the following steps: constructing a multi-modal entity understanding pre-training data set; encoding multi-modal data in the pre-training data set according to a pre-constructed multi-modal entity encoder to generate an entity input sequence with controllable length; performing multi-target joint optimization pre-training on a pre-constructed double-tower multi-modal large model according to the pre-training data set to obtain a general pre-training model; performing lightweight scene adaptation on the general pre-training model for a subdivided wisdom scene to obtain a scene adaptation model; inputting the entity input sequence and a current natural language query into the scene adaptation model to generate a thought chain reasoning conclusion; and generating an interaction instruction according to the thought chain reasoning conclusion, so that the wisdom scene self-adaptive interaction with high accuracy, low delay, low cost and feasibility is realized.

The invention provides a self-service certificate handling equipment service method and system based on robot guidance, and belongs to the technical field of intelligent government affairs. The method comprises the following steps: acquiring certificate handling demand information and associated feature data of a user, and combining a preset certificate handling knowledge graph to generate a self-adaptive guide path; a user is guided to target self-service equipment in an adaptive interaction mode, equipment operation and user behavior data are collected in real time, abnormity judgment is carried out, and a dynamic correction strategy is triggered; after the user completes the operation, the whole-process data is synchronized to the management system, the management system calls the reinforcement learning model to extract features, identifies node bottlenecks, generates an optimization scheme and updates a knowledge graph, and meanwhile, the service robot can push a subsequent service package. The system comprises a service robot unit, a self-service certificate handling equipment unit, a management system unit and a data interaction unit, realizes the intelligentization, self-adaption and continuous optimization of the self-service certificate handling service, and improves the certificate handling efficiency and the user experience.

The application discloses a game artificial intelligence character dynamic interaction method and system fusing multi-modal emotion feedback, and the method comprises the following steps: collecting player in-game interaction behavior data and terminal device sensor physiological data in real time; pre-processing and feature fusing are performed on multi-source heterogeneous data; the fused features are input into a pre-trained CNN-LSTM multi-modal emotion recognition model, and a high-confidence player real-time emotion state label is output; based on the emotion label, in combination with a game world view knowledge base composed of scene constraints, character settings and plot rules, a fuzzy logic behavior decision engine is used to dynamically generate a non-player character behavior adjustment parameter set; finally, the AINPC is driven to real-time adjust its confrontation strength, interaction frequency, guidance mode and behavior style, so that emotion-driven personalized and adaptive interaction is realized.

The application discloses a kind of personalized adaptive interaction methods, by collecting user voice, touch trajectory data and portrait information;Dialect enhancement and the text of recognition are carried out to voice data;Touch trajectory feature is extracted and is fused into joint feature vector with portrait;Analysis touch mode;Based on portrait and touch mode, adjust speech rate, UI font size and touch feedback strength using transfer learning;According to text, joint feature vector and the dynamic adjustment of instruction response of adjusted parameter interface;Evaluate feedback effect, trigger adaptive process to realize dynamic learning adjustment.The method improves dialect recognition accuracy by end-side distillation Whisper model combined with multi-modal dialect corpus, accurately identifies touch mode by touch trajectory processing combined with DBSCAN clustering, dynamically adjusts interaction parameters based on transfer learning and meta-learning, continuously optimizes through feedback evaluation mechanism, and realizes lightweight deployment by end-side distillation technology.

The invention discloses an AR (Augmented Reality) system cognitive security interaction method based on multi-modal large language model reasoning and bidirectional individuation, which utilizes a cross attention mechanism guided by an inertial measurement unit signal to explicitly model and eliminate electroencephalogram signal motion artifacts, and compared with the existing method of directly using electroencephalogram signals or simple filtering, the method has the advantages that the method is simple and convenient to implement, and the efficiency is high. The anti-interference capability of personalized attention perception is high, attention recognition is more accurate, the distraction moment of the user can be accurately captured, and the false alarm rate is reduced. Besides, personalized preference configuration information is generated through man-machine alignment and is embedded into the reasoning process of the multi-modal large language model, so that the subjective preference of the user to the risk is read, the problem of alarm fatigue is solved, and user trust is established. According to the method, a real agent closed loop is realized, and the method is a complete agent architecture with perception (physiological denoising)-cognition (LLM reasoning combined with preference)-action (self-adaptive interaction), and can adapt to physiological features and psychological preferences of different users.

The present application belongs to the technical field of bioelectric signal processing and control, and specifically relates to a non-stationary signal codec-free adaptive control method based on a neuromorphic device. The present application directly feeds the collected non-stationary bioelectric signal as a physical excitation into the neuromorphic hardware; by using the transient amplitude-frequency characteristics of the input signal, the dynamic evolution of the synaptic weight is induced through the bottom-layer pulse time-dependent plasticity, and the action pulse is triggered to drive the external physical actuator; the action of the external physical actuator causes natural sensory feedback, promotes the spontaneous remodeling of the power spectral density and phase-amplitude coupling index of the bioelectric signal, and then reversely guides the spontaneous attenuation and convergence of the hardware weight to the optimal steady state. The present application overturns the traditional closed-loop control paradigm of "analog-digital conversion-software algorithm decoding-feature matching", and can realize the adaptive closed-loop driving of complex signals without artificial algorithm code, thereby providing a new physical-level methodology for bionic control and bio-mechatronic adaptive interaction.

This invention relates to an adaptive aircraft swarm control system and method. Each aircraft in the swarm includes: an intelligent master control scheduling module, a tacit consensus module, a communication adaptive interaction module, a multi-source situational awareness module, and a multi-task coupled decision-making module. This invention employs a swarm control system mounted on each aircraft, enabling compatibility with both centralized and distributed collaborative models and achieving closed-loop collaboration of swarm tasks such as perception, decision-making, and communication. Through the offline construction and online updating of multi-source consensus information by the tacit consensus module, the consistency of swarm behavior and task collaboration are maintained even in weak communication environments such as localized, intermittent, and delayed communication. This invention effectively solves the challenges of collaborative decision-making, situational awareness sharing, and task execution in intelligent swarm systems under extreme communication interference conditions.

The invention discloses a situational interactive evaluation method for creativity diagnosis and motivation, which performs creativity evaluation by executing two-stage tasks of supervision fine tuning and near-end strategy optimization, and comprises the following steps: pre-establishing an evaluation index system, initializing a dialogue-level reward calculation mechanism, and establishing an evaluation result; updating language model parameters by utilizing the pre-collected interaction data through a supervision fine tuning mode, and generating an initial dialogue strategy; real user behaviors are simulated through a user simulator, candidate guide strategies are generated, the current round of interaction is added into temporary session history, one or more rounds of user dialogue tracks are obtained through sampling, multi-round perception rewards are calculated, and model parameters are updated through a near-end strategy optimization algorithm; repeating the interaction optimization model until convergence to obtain a self-adaptive interaction strategy; and performing multi-round interaction with the real user based on the trained and optimized language model to realize creativity evaluation of the real user. The invention further discloses a system for implementing the method, and the system has a wide application prospect.

The application relates to the technical field of intelligent education and man-machine interaction, in particular to a hierarchical infant drawing inspiration system and method based on multi-modal behavior perception, which comprises a multi-modal perception evaluation module, a hierarchical decision engine and an adaptive interaction module. Behavior data is collected through a sensor array, and a concentration, emotion and skill evaluation vector is generated by using deep learning; the engine realizes accurate grade division and smooth transition based on a clustering algorithm and reinforcement learning, and matches an inspiration strategy in real time. The application can realize deep perception and adaptive guidance of an infant drawing state, an intelligent interaction closed loop is constructed through AR projection and multi-modal feedback, and the problems of rigid guidance strategy and insufficient individualized teaching ability in the prior art are effectively solved.

The invention belongs to the field of urban resident traffic trip next position prediction, and discloses a traffic trip next position prediction method and device based on multi-adaptive hypergraph collaboration, and the method comprises the steps: constructing an interactive hypergraph and a directed hypergraph based on an individual traffic trip trajectory sequence, constructing a geographic hypergraph based on geographic feature data of a position, and constructing a traffic trip next position prediction result. The interaction hypergraph and the geographic hypergraph are updated to obtain a self-adaptive interaction hypergraph and a self-adaptive geographic hypergraph, and a position overall embedding matrix and an individual overall embedding matrix are obtained based on the hypergraphs; and outputting the first k positions with the highest probability as a prediction result of the next travel position of the individual through a normalization function. The method has high accuracy and strong robustness for position prediction.

The invention belongs to the technical field of power system simulation and information interaction, and particularly relates to an information interaction method for joint simulation of a main network and an active distribution network, and the method comprises the steps: building a multi-rate clock synchronization and prediction compensation mechanism, and achieving the coordination of the simulation step size of the main network and the distribution network and the perspective compensation of boundary data; constructing a hierarchical boundary information model containing static topology, dynamic electrical quantity and aggregation characteristic data, and supporting high-fidelity equivalent representation of dynamic external characteristics of the distributed power supply; executing a self-adaptive interaction strategy based on the running state, and dynamically adjusting the interaction frequency, the data granularity and the model order according to the normal, transient or topological change state; boundary data consistency verification and closed-loop correction are implemented, and numerical value stability is ensured through sensitivity information exchange and iterative correction. According to the invention, the precision, efficiency and convergence of joint simulation are improved.

The invention relates to the technical field of intelligent terminals and acoustic signal processing, and discloses a Bluetooth sound box voice interaction method and system. The method comprises the following steps: acquiring an original mixed acoustic signal to obtain a multi-dimensional interactive input sequence; analyzing the multi-dimensional interaction input sequence to obtain an environment scene label and a user intention category; according to the user intention category, mining to obtain a personalized preference vector; generating a self-adaptive response control instruction set based on the environment scene label, the user intention category and the personalized preference vector; calculating according to the adaptive response control instruction set to obtain a target audio control parameter; and driving an audio output unit to execute playing operation by using the target audio control parameter, and generating a closed-loop feedback record. According to the method, adaptive interaction and preference self-evolution in a complex scene can be realized.

The invention belongs to the technical field of artificial intelligence, and provides an arc model parameter optimization method based on an improved Asian wolf optimization algorithm, and the method comprises the steps: collecting an arc current signal based on a current sensor, and extracting the spectrum capability waveform of the arc current signal; establishing a direct-current arc noise model according to the arc current signal spectrum capability waveform; constructing an objective function based on the root-mean-square error, and determining a to-be-optimized parameter; and executing the improved Asian wolf optimization algorithm, and optimizing the to-be-optimized parameters. According to the method, the Asian wolf optimization algorithm is introduced through the chaos self-scaling learning mechanism, adaptive interaction of population individual position information is achieved through the chaos self-scaling learning mechanism, the optimization algorithm can be effectively prevented from being caught in premature convergence, the convergence speed is increased, and the method has high recognition precision for parameters of the direct-current arc noise model.

The invention relates to the technical field of tire changer sales, in particular to a tire changer sales strategy self-adaptive generation system based on reinforcement learning, which comprises a supply and demand feature sensing module, a conversion fluctuation recognition module, a control module, a decision-making module, a decision-making module, a decision-making module, a decision-making module and a decision-making module, the state operation association module analyzes multi-dimensional attributes to establish mapping, the interaction process arrangement module arranges operations according to a state sequence, and the interaction behavior self-adaptive adjustment module positions deviation according to feedback and selects replacement operations for rearrangement to obtain a self-adaptive interaction strategy generation result. According to the method, the market state is enabled to have a structural property through multi-dimensional disassembly and transaction consistency description in the sales process, abnormal limits are converted to positions, business constraints are associated to enable positioning to have directivity, stable mapping is established between the process state and operation, and an interactive predictable basis is given; and the operation sequence is rearranged according to feedback, so that the sales behavior keeps coherent adjustment capability, and the supply and demand identification definition, the interaction stability and the strategy adaptation performance are enhanced.

This invention provides a metaverse virtual character adaptive interaction system based on multi-task collaboration, comprising: an interaction data acquisition module for acquiring multimodal interaction data generated by the user in the current metaverse scene; an analysis and processing module for analyzing and processing data based on a pre-trained multi-task collaborative analysis model, extracting multi-dimensional features corresponding to the multimodal interaction dataset and fusing them to generate a target interaction feature vector; a parsing module for parsing the user's dominant interaction intent within the current interaction cycle based on the target interaction feature vector and calling an intent recognition model; an interaction control module for determining interaction response parameters based on the dominant interaction intent and controlling the virtual character to execute corresponding interaction behaviors; and a model update module for collecting user feedback data after the virtual character executes interaction behaviors, incrementally learning the multi-task collaborative analysis model, and updating the parameters of the multi-task collaborative analysis model. This enhances the realism and immersion of the user experience.

The invention relates to the technical field of electric vehicle control, and discloses an instrument control panel interaction method and system for an electric vehicle, and the method comprises the steps: collecting riding data in real time according to a default sampling rate through a multi-dimensional sensor; the current driving scene of the electric vehicle is identified through micro-dynamic estimation and one-dimensional aerial view mapping; through dual anti-shake and prediction verification, outputting a prediction label containing a time sequence prediction and quantization trend; dividing the current riding state based on a preset speed threshold value; generating a personalized adaptive interaction mode through intra-domain exploration optimization and habit migration guidance; a user executes operation by using a personalized adaptive interaction mode, and the instrument control panel performs feedback according to an operation instruction. According to the method, data circulation channels of all links are opened, so that collected data, scene evaluation results, personalized parameters and interaction logs form a real-time feedback link, and through logic deep association instead of independent operation, the coordination and accuracy of overall interaction response of the system are improved.

The embodiment of the application provides a multi-role adaptive interaction method and system based on an oral medicine knowledge base, which comprises the following steps: when a query signal is received, a query role is identified, and query content is acquired; a preset query engine matched with the query role is called, a previously constructed knowledge base is accessed according to the currently called query engine and the query content, and a differential diagnosis set containing multiple diseases with a sorting relationship is acquired; the diseases in the differential diagnosis set are subjected to multi-dimensional differential diagnosis reasoning one by one according to the sorting relationship, and the comprehensive confidence of the reasoning result is correspondingly evaluated; when the comprehensive confidence is not less than a preset threshold, the disease corresponding to the comprehensive confidence is taken as a diagnosis disease, and a query report matched with the query role is output. The application can assist doctors in making professional clinical decisions and provide patients with convenient oral common sense popularization services.

The invention provides an intelligent catering interaction method integrating environmental perception and user behavior analysis, and relates to the technical field of intelligent catering interaction.The method comprises the steps that interaction channel selection, interaction content and interaction time sequence sub-strategies are generated by analyzing table group interaction intentions and combining noise, service loads and equipment states, and the table group interaction intentions are analyzed; and interactive operation is executed in channels such as voice, a terminal interface and a service robot according to the strategy. In the interaction process, dominant feedback, implicit feedback and environment state change data are synchronously collected, and a multi-source feedback sample is constructed for incremental updating of a scene recognition and intention reasoning model and regeneration of a multi-channel interaction strategy, so that service channel selection and content arrangement are adaptively optimized, and the user satisfaction and the operation efficiency are improved. The problems that in the prior art, environment perception and user behavior analysis are mutually separated, and self-adaptive interaction decision and closed-loop optimization based on the environment and user joint state are lacked are solved.