109 results about "Cognition" patented technology

The invention discloses an intelligent personalized learning path recommendation system, and relates to the technical field of learning systems, and the system comprises a multi-source data collection module which is used for synchronizing behavior data of students in a cross-platform learning scene in real time; the cognitive feature analysis engine comprises a style recognition sub-engine and a demand prediction sub-engine to predict the potential learning demand intensity of students for unmastered knowledge points and generate a priority list comprising knowledge gaps; the personalized path generator generates a three-dimensional path plan; the proportion of guided questioning, example demonstration and autonomous exploration is automatically configured according to knowledge difficulty; the dynamic self-adaptive adjustment unit is used for designing a reward function including short-term progress speed and long-term ability growth potential by taking real-time performance of students as a state space and taking path adjustment action as a decision space based on a reinforcement learning framework; and a double-loop feedback mechanism is realized. According to the method, the dimension limitation of traditional learning analysis is broken through, the difficulty of stiffness of a static course template is broken through, and meanwhile, the semantic gap of subject cognition is broken through.

The invention provides a large language model long-term memory method based on human cognition inspiration, which comprises the following steps of: calculating semantic similarity distribution of historical interaction text vectors according to a sliding window, and calculating local information entropy of the window; determining an event boundary based on the local information entropy difference of the adjacent windows; taking each discrete event as the memory of the model, and performing partition management on the memory; when the event memory partition is full, the memory event with the low retention rate is transferred to a long-term memory area; when the interactive content relates to historical information, retrieving related historical events in the event memory partition by using a contextualized memory retrieval method; and the large language model generates content for the user in combination with the current context and the retrieved related historical events. According to the method, memory coding and storage, multi-level dynamic memory management and event-level situational memory retrieval methods based on the event cutting theory are adopted, and therefore the problem that an existing large language model long-term memory method lacks dynamic memory and situational memory is solved.

The invention provides a human-computer interaction virtual-real simulation method and system of an intestinal nutrition nursing teaching system, and relates to the technical field of virtual interaction teaching. By integrating a force feedback glove, a bioelectric sensor and a pressure detector, multi-mode interaction data acquisition including intubation angle deviation, maximum force application pressure value and step interval time is realized; the operation feedback dimension and immersion are improved; the system is combined with a scene construction and intelligent guide module, when the detection operation goodness of fit is lower than a preset threshold value or the process completion degree is insufficient, force feedback vector correction and cognitive prompt are triggered, and standard attitude and step memory are guided; and the comprehensive evaluation module summarizes key indexes to calculate a total operation score, performs defect positioning and training suggestion matching on low-score behaviors, generates a structured visual learning report, constructs a cognition-operation-feedback closed loop, and solves the problems of single interactive feedback, insufficient teaching structuralization and lack of feedback mechanisms.

Disclosed in the present invention is a general-purpose intelligent agent. The general-purpose intelligent agent comprises: an input module, which is configured to acquire a preprocessed input signal; a consciousness module, which is configured to perform perception and cognitive operations in a transparent and interpretable abstract thinking form; a self-awareness module, which is configured for perception and cognition of an intelligent agent body; a subconsciousness module, which is configured to use a data-driven model to implement perception and cognitive functions at a subconscious level; an information exchange module, which is configured to perform mutual exchange between perception, cognition and other information generated by the consciousness module, the self-awareness module and the subconsciousness module, thereby enabling integration and utilization; and an output module, which is configured to output a processing result on demand. In a machine intelligent agent of the present invention, a machine uses a general-purpose language as an underlying language for thinking and interaction, a thinking process and result are completely transparent, and thus autonomous decision-making, autonomous learning and continuous evolution are realized under fully controllable conditions. Further disclosed is a method for constructing a general-purpose intelligent agent and a general-purpose language. Compared with the prior art in which a natural language is used, the machine intelligent agent based on the general-purpose language has wide versatility in application.

The innovation is the Landscape Syntax Algorithm, a new analytical framework to transcend the age-old limitations of space syntax. It integrates the highly versatile idea of landscape. Space syntax is largely objective and deals with the arrangement of space, along with little or no consideration for the more subjective parts of human aspects and experiences. Thus, the Landscape Syntax Algorithm fills that gap by providing a model that marries objective spatial measures with the more subjective cognitive and experiential aspects of landscape. This is carried out by infusing perceptual cognition and history / contextual layers within spatial analysis. Hence, there is a thorough reading of the relation between human experience and the built world. It opens up the opportunity to unify the most objective spatial configuration and subjective perceptual cognition to provide a powerful resource for the architect, urban planner, or researcher interested in analyzing and designing spaces that connect to the human experience in a more profound and mature sense. This invention enables quantification and analysis of landscape as moving and interactive phenomena towards a much more human-oriented contextual design of space.

Systems and methods for guiding or steering thought processes on a persistent cognitive machine (PCM) that uses a continuous, differentiable, thought manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with thought manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. A PCM with cognitive manifold performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. Methods for guiding or steering thought processes on the thought manifold are disclosed that involve mathematical manipulations of the geometric space of the thought manifold inspired by gravitational lensing.

A system and method for a digital thought architecture, otherwise called a persistent cognitive machine (PCM), that uses a continuous, differentiable, thought manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with thought manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. Not only does the PCM with thought manifold maintain persistent cognitive processes regardless of external interaction, overcoming limitations of existing AI systems that operate within a prompt-response paradigm where they await input, generate output, and return to a waiting state, it also performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. In some embodiments, the thought manifold may be implemented as a neuromorphic platform.

The invention discloses a DIKWP-driven individualized brain-map interactive feedback system, which is used for neural rehabilitation and brain-computer interface training. The system obtains brain activity data of a patient through electroencephalogram acquisition equipment, constructs a personal brain-semantic map in combination with cognitive evaluation, and establishes a mapping relation between semantic units and brain region responses. In the training process, the DIKWP semantic analysis module performs multi-layer analysis on indexes such as reaction time, accuracy and intention achievement, generates multi-mode instant feedback such as visual sense, auditory sense or tactile sense, and performs directional reinforcement on a weak semantic domain. The system has a dynamic target optimization capability, and the difficulty can be automatically adjusted according to training performance; when attention distraction, emotion abnormity or semantic deviation is detected, a safety intervention mechanism is automatically triggered, and training effectiveness and safety are guaranteed. According to the method, closed-loop individualized rehabilitation interaction is realized, the adaptation degree and efficiency of brain-computer interface training are remarkably improved, and the method is suitable for various rehabilitation scenes such as languages, movement and cognition and has a good industrial application prospect.

The invention provides a construction method of an industrial brain system for an industrial chain, and the method comprises the steps: constructing the industrial brain system based on an autonomous cognitive thinking map function module, an autonomous interactive decision function module and a dynamic behavior active regulation and control function module, the robot is used for autonomously executing perception, cognition, decision making and regulation tasks on various situations of the ductile seepage phase change of an industrial chain and supply chain network; the autonomous cognitive thinking map function module is used for sensing, measuring, cognizing and storing various situations of the ductile seepage phase change of the industrial chain and supply chain network in real time; the autonomous interactive decision function module is used for tough situation identification of total elements, accurate event positioning and comprehensive situation research and judgment; and the dynamic behavior regulation and control module is used for regulating and controlling the vulnerability and risk propagation dynamics behaviors of the industrial chain and supply chain network according to the generated decision scheme. Therefore, accurate identification, measurement, catastrophe prediction and active behavior regulation and control can be carried out on various situations of the tough seepage phase change of the complex giant chain type network.

The invention discloses a brain heuristic multi-expert multi-mode emotion recognition method and system, equipment and a medium, and belongs to the technical field of artificial intelligence and biomedical signal processing. The method comprises the following steps: by simulating a brain function partitioning mechanism, dividing an electroencephalogram signal into a plurality of brain regions according to neuroanatomy prior, and designing a special expert network for each region; a global-local double-current encoder is adopted to cooperatively extract spatial-temporal characteristics of each brain region signal, and meanwhile, a multi-scale large-kernel convolution module is utilized to extract peripheral physiological signal characteristics; and finally, dynamically fusing multi-expert features through an adaptive routing network to realize sentiment classification. Expert load balancing and bifurcation regularization joint loss are introduced into the model in training, and effective cooperation and feature diversity of experts are ensured. According to the method, excellent recognition precision is obtained in practice, it is verified through interpretability analysis that the decision-making process conforms to neuroscience cognition, and a high-precision and high-reliability solution is provided for application of brain-computer interfaces, mental health monitoring and the like.

The invention relates to a superconducting power knowledge system construction method and system based on a lightweight large model. According to the method, multi-source data is utilized for unified representation, deep semantic information is obtained through a lightweight large model, knowledge extraction is achieved, and a basic knowledge graph is constructed; further forming a knowledge graph which can be dynamically updated through knowledge fusion; and in combination with real-time data, adaptive multi-hop reasoning is executed, and a diagnosis and decision result with a causal chain is generated. According to the method, the semantic understanding and reasoning ability of a lightweight large model is taken as a core, the structural expression advantage of a knowledge graph is combined, the limitation of updating lagging and fixed rule reasoning rigidness of a traditional static knowledge base is broken through, and precise cognition and causal chain inference of a complex system state are achieved. The method has universality and mobility, and is suitable for knowledge modeling and intelligent diagnosis of various electric power scenes and other complex industrial systems. The method is verified by taking a superconducting power system as an example, and the feasibility and effectiveness of the construction path are proved.

The invention belongs to the technical field of education, and discloses a method for retrieving answers to questions from an educational knowledge graph, which comprises the following steps: acquiring a first educational question set # imgabs0 #, and analyzing cognitive representation and language style in the first educational question set; unifying language styles and cognitive representations in the first education question set through an instruction of a large language model; extracting subject subjects and combining questions to obtain complete and simplified questions; and performing multi-hop answer reasoning to deduce the answer of the recombined question. The method is improved in the aspects of multi-hop, educational cognition expression and different types of language styles, can be applied to different models of educational cognition expression problems, and has very high universality. According to the education cognition expression question answering method supported by the large language model, different cognition expression modes of learners in the real world are considered, and the effect is better in practical application compared with an existing model.

The embodiment of the invention provides a motion planning method, a training method and a training system for a body intelligence model. The method comprises the following steps: acquiring a body intelligence initial model; wherein the body-equipped intelligent initial model comprises an initial natural language understanding layer, an initial in-vitro perception layer, an initial body cognition layer, an initial motion planning layer and a fusion layer; obtaining a training set of the model; wherein the training set of the model comprises at least one training sample; the training sample comprises a natural language sub-sample, an in-vitro perception sub-sample, an ontology cognition sub-sample and a motion planning sub-sample; wherein the natural language sub-sample, the in-vitro perception sub-sample, the ontology cognition sub-sample and the motion planning sub-sample in each training sample are in one-to-one correspondence; and according to the training set of the model, training the initial body intelligence model to obtain the body intelligence model. The method is used for achieving the effect of improving the accuracy of motion control of the body intelligent model obtained based on training.

The invention discloses a personalized knowledge tracking method based on a cognitive dynamic graph and multi-expert mixing, and belongs to the technical field of intelligent education, and the method comprises the following steps: constructing a cognitive dynamic structure graph based on learning interaction data of students, the cognitive dynamic structure graph comprising a cognitive dependence knowledge point graph and a question-knowledge point association graph; information transmission is carried out on the cognitive dynamic structure diagram based on a graph convolutional network, and cognitive enhanced interaction feature representation is obtained; constructing a heterogeneous expert pool and a self-adaptive routing mechanism to differentiate cognition of the students based on the interaction feature representation of cognition enhancement, and generating a comprehensive learning state evaluation result; and on the basis of the comprehensive learning state evaluation result, predicting the performance of the student on the next question, and realizing personalized knowledge tracking of the student. According to the invention, through dynamic knowledge dependence modeling and a multi-expert mixing mechanism, accurate tracking of student knowledge states and efficient planning of personalized learning paths are realized.

The invention discloses an old people cognition screening method and device, equipment and a storage medium, and relates to the technical field of data processing, and the old people cognition screening method comprises the steps: determining a cognition screening applet related to old people cognition screening in a user side, obtaining cognition self-evaluation question data corresponding to a test type in a management platform, according to each evaluation page, obtaining a selection parameter input by the user for the displayed evaluation page, and determining the reaction time of the selection parameter input by the user; the selection parameters and the reaction time corresponding to each test type are sent to a management platform, the management platform inputs all the selection parameters and the reaction time to a machine learning model, and an old people cognitive self-evaluation result is obtained; and receiving an old people cognitive self-evaluation result fed back by the management platform, and outputting and displaying the old people cognitive self-evaluation result. According to the invention, the efficiency and accuracy of cognitive assessment of old people are improved.

To provide a forecasting system, a forecasting method, and a forecasting program for grasping a cognition state on the basis of utterance of a forecasting object person.SOLUTION: A support device 20 includes a control part 21 for performing machine learning for utterance data on a learning object person. The control part 21 generates a plurality of utterance blocks in which an utterance section of the utterance data on the learning object person is divided into time intervals, and calculates a spectrogram for each utterance block. Furthermore, the control part 21 calculates a feature amount of a power spectrum distribution shape for each spectrogram. The control part 21 then learns a data set that associates the feature amount with a cognition state label based on dementia diagnosis information as teacher information, and generates a forecasting model. When the utterance data on the forecasting object person is acquired, the control part forecasts the cognition state label from the feature amount of the utterance data on the forecasting object person using the forecasting model.SELECTED DRAWING: Figure 1

Disclosed is a method for assessing a cognition and movement disease or disorder in a subject. In the method, a qualimetric activity parameter for cognition and / or fine motoric activity measurements is determined from a dataset of measurements obtained from the subject using a mobile device. The qualimetric activity parameter is compared to a reference and the disease or disorder is thereby assessed. A method identifying whether a subject will benefit from a therapy for a cognition and movement disease or disorder is also disclosed. The method can be carried out with a mobile device having a processor, a sensor and a database as well as software that carries out the method. Also disclosed is a system having a mobile device with a sensor and a remote device having a processor and a database and software that carries out the method for assessing a cognition and movement disease or disorder.

The invention discloses a language and cognition combined language rehabilitation training system and method. The system comprises an information input unit, an evaluation unit, a training unit and a data analysis unit. Personal information of a patient is input into the system through the information input unit, and the evaluation unit is used for carrying out language and cognition double evaluation on the patient, so that a personalized training scheme for the patient is formed according to an evaluation result of the patient, and the personalized training scheme is used for carrying out language and cognition combined rehabilitation training on the patient. In the rehabilitation training process of the patient, the training data of the patient are collected in real time through the data analysis unit and are analyzed, so that the personalized training scheme is updated in real time, and the accuracy and effectiveness of rehabilitation training are ensured.

The invention discloses a cognitive thinking big model construction method based on neural symbols, and relates to the technical field of artificial intelligence. Comprising the following steps: S1, constructing a thinking cellular machine; s2, constructing a cognitive reasoning function domain; s3, constructing a cognitive interaction motif; s4, constructing a cognitive thinking large model based on the thinking cellular machine, the cognitive reasoning function domain and the cognitive interaction motif; and S5, performing risk early warning on the industrial chain supply chain according to the constructed cognitive thinking big model, and obtaining a risk diffusion path of the industrial chain supply chain. According to the method, situation cognition of an industrial chain-oriented cognitive thinking large model in a complex uncertain multi-modal environment can be enhanced, situation evolution laws, event causal interpretable reasoning and anti-fact intervention processing can be accurately understood, and full-modal understanding and cross-task generalization ability of the model are improved, so that the accuracy of industrial chain risk early warning is improved, and the risk early warning efficiency is improved. The interdisciplinary research is promoted, and the artificial intelligence application field is expanded.

The invention discloses a virtual reality psychological disease cognition experience method and system, and relates to the field of virtual reality psychological disease cognition experience.In actual use, cognition experience is achieved through the virtual reality technology, and the best VR scene and intervention strategy are automatically recommended according to information data of a patient through the big data analysis technology; according to the invention, automatic personalized treatment design is carried out according to the specific condition and demand of each psychological disease patient, and specific problems of the psychological disease patients are more accurately solved, so that effective treatment is provided for each psychological disease patient, and the problem that drug dependence may be caused to the psychological disease patients due to long-term medication is avoided.

The invention discloses an AI adaptive learning path dynamic generation method and system based on a multi-modal cognitive trajectory. The method comprises the following steps: non-inductively collecting multi-modal data such as visual, auditory and interactive data; performing feature fusion by using a gating multi-mode unit to generate a student state vector; constructing a three-dimensional cognitive trajectory model for representing cognition, emotion and fatigue; dynamically deciding a learning path by adopting a hierarchical reinforcement learning algorithm and taking a track state as input; predicting a knowledge fault risk in real time by using a dynamic Bayesian network; and when the risk exceeds the threshold, actively generating a personalized completion path based on knowledge graph traceability. According to the method, deep perception of the learning state, advanced prediction of the learning risk and accurate dynamic planning of the learning path are realized, and the learning efficiency and experience are remarkably improved.

The invention discloses a magnetic attraction intelligent connection type autonomous operation and maintenance experiment node system, and the system comprises a sensing and modeling layer which is used for constructing a thinking digital twinning environment which is synchronous with a physics laboratory in real time, is centimeter-level in precision, can be interacted with the physics laboratory, and is rich in semantic information; the cognition and decision-making layer is used for upgrading simple and rule-based reactive behaviors into complex, logic-based and prospective active decisions; the collaboration and network layer is used for connecting all the distributed cognitive experiment nodes into an organic super organism capable of emerging'swarm intelligence '; and the interaction and operation and maintenance layer is used for seamlessly and immersively transmitting remote experts to a physical site by introducing generative artificial intelligence and own intelligence, so that the remote experts become a high-level commander and a lifelong learning partner of the whole cognitive experiment node system. By means of the magnetic attraction intelligent linkage type autonomous operation and maintenance experiment node system, the problems that current experiment equipment is lack of cognition on the physical environment, blank in complex logical reasoning, stagnant in adaptive capacity to dynamic tasks and the like can be solved, and the intelligent and systematic operation capacity of the experiment equipment is remarkably improved.

Systems and methods for latent slice budgeting on a persistent cognitive machine (PCM) that uses a continuous, differentiable, cognitive manifold in geometric space to allow a computer to engage in human-like thought processes. The PCM with cognitive manifold represents a fundamental advancement in artificial intelligence beyond current probabilistic AI system such as large language models (LLMs) and similar reasoning models. A PCM with cognitive manifold performs cognition on a thought manifold in a continuous, differentiable, thought manifold in geometric space as opposed to probabilistic prediction in a discontinuous, anisotropic, and topologically fractured vector space. Methods for latent slice budgeting on the cognitive manifold are disclosed that foliation of the cognitive manifold into time slices and budgeting change between the time slices.

A system and method for implementing experiential manifold cognition that extends persistent cognitive machines beyond discrete thought caching to continuous geometric representation of experience. The system maintains an experiential manifold comprising a differentiable manifold with Riemannian metric tensor encoding semantic relationships, compression pressure field governing memory consolidation, and potential field encoding goals and attention. Input data is projected onto the manifold through adaptive geometric diffusion preserving semantic structure. The system executes geometric transformations including metric evolution, geodesic computation, and curvature estimation. During non-interactive periods, autonomous evolution occurs through trajectory recombination and selective pruning. A user interface enables visualization and direct manipulation of manifold geometry, translating navigation into geodesic traversal and edits into metric modifications. The system maintains persistence across sessions and enables controlled federation between multiple manifolds through consent-bounded synchronization. Applications include persistent narrative worlds, collaborative cognitive spaces, and experiential intelligence systems that learn through geometric evolution.

The invention discloses an interactive task generation method and device and a storage medium, and relates to the field of man-machine interaction, and the method comprises the steps: obtaining context information, task knowledge and a task target; constructing a long-term preference map and a heterogeneous task knowledge base; finely adjusting the large language model; obtaining interaction state information; short-term emotional state memory is constructed, and a preference result is analyzed; generating a query vector; generating a retrieval result; generating a memory enhanced template; generating a current interaction task; collecting behavior data when the current interaction task is executed; analyzing the behavior data, and constructing a multi-dimensional reward; and updating the long-term preference map and the short-term emotional state memory. By constructing a long-term preference map and a short-term emotion recognition mechanism, the modeling ability for the individual state of a user and the environment context is improved, and the space consistency, semantic rationality and personalized adaptive recommendation of a task generation process are realized; and the comprehensive requirements on cognition authenticity, execution accessibility and user experience continuity in a multi-modal interaction scene are met.

The invention discloses a large language model agent collaborative decision-making method for a complex dynamic game scene, and the method comprises the steps: achieving the environment perception, experience accumulation and knowledge calling functions, and supporting the cognitive modeling and strategy generation of an agent; based on cognitive information, intelligent agent role division and labor division are achieved through an action characterization device and a role selector, and the intelligent agents are guided to perform their own functions in the collaboration process. Cognitive information and role information are input into a large language model, hierarchical analysis is performed on a game situation depending on natural language understanding and thinking chain reasoning ability, key game nodes are identified, opponent strategies are predicted, and foresight collaborative decisions are generated in combination with teammate intentions. And through a semantic matching and action mapping mechanism, converting a natural language decision generated by reasoning into a structured executable instruction, and performing rationality verification. The intelligent agent executes actions and interacts with the environment, the system updates short-term memory based on feedback and periodically integrates the short-term memory into long-term memory, and a closed-loop process of'cognition-role allocation-reasoning-execution-updating 'is formed. According to the method disclosed by the invention, a distributed collaborative decision-making architecture based on a large language model is constructed, so that the intelligent agent has stronger autonomous perception, reasoning and collaboration capabilities, and the collaboration efficiency, game adaptability and strategy generalization capabilities of the intelligent agent in a complex dynamic game environment are remarkably improved.

The invention discloses an intelligent contract logic vulnerability detection method and system based on a thinking enhancement large model, and the method comprises the steps: converting a complete intelligent contract project source code into a structured context which is easy to understand and analyze of the large model, and achieving the preprocessing of the intelligent contract project source code; a thinking knowledge base is extracted through a real world security audit report and is used for generating subsequent vulnerability detection thinking; multiple types of agents are designed for collaborative detection, a focus context mechanism is supplemented, multiple processes researched by a security officer are simulated, and vulnerability detection is carried out in an iteration mode.

The invention relates to an intelligent deep questioning method and system, and belongs to the technical field of natural language processing and intelligent evaluation. The method comprises the following steps: acquiring a candidate response, converting the candidate response into a standardized text, analyzing the text in combination with multi-dimensional monitoring data, positioning competency missing elements, generating a missing identification set, and marking a sorting question-chasing point; constructing a dynamic self-adaptive score matrix in which competency is linked with a questioning point, fusing monitoring data to calibrate scores and confidence, and generating a questioning technology intervention scheme; a virtual interviewer role library is preset, roles are dynamically matched, and the intervention logic and the missing identification set are combined to generate specialized questioning content; and when the core element capability element characterization is insufficient or the confidence coefficient does not reach the standard, generating a target element cognition questioning problem, and after element extraction and fusion, outputting a multi-dimensional competency score and a confidence coefficient report. According to the invention, the upgrading of the questioning from mechanical questioning to intelligent technical intervention is realized, the questioning targeting and the evaluation accuracy are improved, and reliable support is provided for accurate talent selection.

The invention discloses an interpretable teaching cognition interaction method and system based on a knowledge graph, and a medium, and relates to the field of education management information systems, and the method specifically comprises the steps: collecting answer data of a learner, calculating a knowledge mastering state vector, mapping the knowledge mastering state vector to a knowledge graph node, and carrying out the feature decomposition; obtaining a cognitive feature matrix and a knowledge node cognitive difficulty coefficient; constructing a cognitive path graph based on the cognitive difficulty coefficient, and calculating the migration probability of adjacent nodes to generate a cognitive migration path; and constructing a multi-layer knowledge network on the path, calculating node weights and knowledge circulation coefficients, generating a teaching knowledge point sequence, and encoding the sequence to generate stepped teaching content. According to the method, personalized content recommendation and scientific allocation of teaching resources can be provided for an education platform, and intelligent optimization and management transparency of the teaching process are realized.

The invention discloses a personalized homework intelligent generating and pushing method based on multi-modal learning data, and belongs to the technical field of education. The method aims at overcoming the defects that in the prior art, the emotion state of a learner is ignored, multi-modal data fusion is shallow, and homework generation is static. The method comprises the following steps: acquiring multi-modal data, acquiring behavior data, physiological data and expression data in real time, evaluating cognitive and emotional states, respectively outputting knowledge point mastery degrees and emotional states through sub-models, and correlating and calibrating; dynamic homework generation: a decision engine generates and pushes a personalized homework package through question bank combination or real-time generation according to a dual-state matching regulation rule; feedback optimization and privacy protection are conducted, and desensitization processing is conducted on the physiological data at the same time on the basis of an operation feedback iteration model and rule. According to the method, double regulation and control of cognition and emotion are realized, the double-state evaluation accuracy is high, the homework completion rate of the learner is effectively improved, and the method is suitable for K12 and vocational education scenes.