220 results about "Affiliation network" patented technology

The invention relates to an AI Agent-driven credit risk early warning strategy automatic evaluation method and device, control equipment and a computer readable storage medium, and the method comprises the steps: obtaining structured financial data, unstructured text data and dynamic time sequence data of an enterprise through multi-source data, carrying out the standardization processing, and outputting a standardized risk data set; based on the standardized risk data set, static financial features, dynamic derivative features and associated network features are extracted, and a high-discrimination feature set is generated through feature screening and dimensionality reduction optimization; a multi-model integration strategy is adopted, the high-discrimination feature set is input into a neural network, a Stacking integration model and a graph neural network, and enterprise risk scores and grades are output; and automatically matching an early warning rule based on the enterprise risk score and the grade, and carrying out real-time monitoring and early warning on enterprise credit according to the early warning rule.

The invention discloses a multi-modal fusion lithium iron phosphate battery thermal runaway early warning method and system, and the method comprises the steps: collecting multi-source heterogeneous data, such as temperature, voltage, gas concentration and shell strain pressure, in real time through deploying a heterogeneous sensor network, and carrying out the noise reduction and time sequence feature extraction through employing a sub-linear time low-rank approximation algorithm of a Hankel matrix; constructing a cross-modal feature association network by applying a secondary time algorithm of a maximum weight sparse subgraph problem, inputting a fused feature vector into a Bayesian network health degree evaluation model for probabilistic reasoning calculation to obtain a battery health degree score and a thermal runaway risk level, generating a graded early warning signal through multi-level early warning threshold comparison, and performing early warning on the battery health degree score and the thermal runaway risk level. And corresponding prevention and control suggestions are matched. The method solves the technical problems that single physical quantity monitoring is difficult to comprehensively reflect the complex change in the battery and the response delay of a centralized processing architecture causes the early warning lag, and achieves the timely capture and accurate early warning of the early weak characteristics of thermal runaway.

The invention discloses an import and export risk real-time early warning method and system based on multi-modal data fusion, and relates to the technical field of data analysis, and the method comprises the steps: obtaining multi-modal data in real time, and carrying out the preprocessing; designing a dynamic weight distribution algorithm, and endowing different types of data with differentiated weights to realize dynamic fusion according to quantitative indexes of timeliness, authority and target transaction association degree; fusion data features are extracted through a streaming computation engine, real-time risk calculation is carried out based on an Apache Flink cluster, and an association network is constructed in combination with a six-dimensional knowledge graph; on the basis of the extracted features and the association network, a CEP rule engine quickly identifies and calculates potential risk events and accurately locates risk points by relying on a predefined multi-class composite risk mode; and setting a grading early warning mechanism, enabling the identified risk mode to correspond to a corresponding early warning grade, generating a grading early warning signal, and synchronously prompting a dynamic disposal suggestion. According to the method, the risk identification accuracy can be improved, and the early warning response delay is shortened.

The invention discloses a knowledge base knowledge association fusion method based on a knowledge graph, and the method comprises the steps: integrating structured, semi-structured and non-structured data through a cross-modal alignment technology, and constructing a multi-source heterogeneous data association network of a unified semantic space; newly added external data are fused to a multi-source heterogeneous data association network in real time by using a dynamic attention mechanism, and entity conflicts are eliminated by combining rule reasoning and a machine learning model; hidden association among entities in the multi-source heterogeneous data association network is mined based on the graph neural network, and a knowledge graph logic chain is complemented; based on the knowledge graph, intelligent question and answer and risk assessment decision scenes are supported through a hybrid retrieval architecture and an inference engine; and automatically updating and associating the knowledge base of the network extension knowledge graph by adopting an incremental learning technology. Natural language questions and answers are supported, accurate answers are generated through knowledge reasoning, and user experience is remarkably enhanced.

The invention discloses an AI-based computer basic course personalized learning path recommendation method and system, and belongs to the technical field of AI-based data processing. According to the system, behavior data, cognitive data and course interaction data of a learner are acquired through a multi-dimensional data acquisition module, a computer basic course knowledge point association network is established in combination with a dynamic knowledge graph construction module, and a personalized learning path is generated by using an improved deep reinforcement learning algorithm. And the path is dynamically adjusted through the real-time feedback module. The core of the method is that a learner portrait is fused with space-time correlation features of a knowledge graph, a cognitive evaluation model is updated in real time through a Bayesian network, the problems that in a traditional recommendation method, paths are solidified, and the dynamic learning state of an individual is ignored are solved, more accurate personalized learning guidance is achieved, and the learning efficiency and effect of a computer basic course are improved.

The invention relates to the technical field of intelligent questioning and answering, in particular to an intelligent questioning and answering system implementation method and system.The intelligent questioning and answering system implementation method comprises the following steps of document collection and preprocessing, document dicing, document layout analysis and table layout analysis; the method has the beneficial effects that a semantic association network and a multi-modal index system are formed through offline document collection, preprocessing, slicing, layout analysis, data extraction and knowledge graph construction; in the online part, the capabilities of Embedding vectorization, multi-index joint retrieval, tensor reordering, AI database integration and large language model generation are combined, accurate semantic understanding and rapid knowledge matching of user questions are realized, high-quality answers are generated, and interactive feedback optimization is supported.

The invention discloses a learning content determination method and device based on an intelligent education platform and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: extracting a basic knowledge point cluster and a key knowledge point cluster from a student teaching material, and generating a target question bank containing different difficulties and question types; generating a knowledge point association network according to the association relationship and strength of the knowledge points corresponding to the questions in the target question bank; and in combination with the learning track of the student in the learning map, generating the target association strength between the target knowledge points, updating the knowledge point association network according to the target association strength, obtaining a student exclusive target association network, and updating the target question bank to determine the target learning content of the user. According to the scheme, the knowledge points are extracted through the textbook, the target question bank of the multivariate question types is generated, the problem of single question type in the prior art is solved, the question bank is dynamically updated in combination with the learning track and the association network, students can focus on core knowledge points, and the learning efficiency is improved.

The invention provides a digital intelligent base service achievement management method and system, and relates to the technical field of digital intelligent base service management.The method comprises the steps that firstly, a basic feature set containing attributes, sources and process features of service achievements in a digital intelligent base is collected, then associated features of the basic feature set are mined, and a service achievement associated network is formed; then, a multi-level management index containing a transverse attribute dimension and a longitudinal flow node dimension is constructed based on the service achievement association network, and a management strategy covering storage, updating and sharing features is generated in combination with index features and service achievement real-time state features; and finally, performing dynamic management and control on the business achievements in the digital intelligent base according to the management strategy, thereby deeply mining the relationship between the business achievements, realizing multi-dimensional fine management, dynamically adapting to business changes, and improving the management efficiency.

The invention discloses a pump station unit state comprehensive evaluation method, and belongs to the technical field of pump station unit detection. The method comprises the following steps: acquiring multi-source monitoring data and generating a standardized monitoring data set; time-varying mutual information between indexes is calculated, a dynamic threshold value is determined in combination with current working condition parameters and a water level difference correction term, and a dynamic association network is constructed; performing physical mechanism characteristic decoupling on the data, including stripping a vibration signal working condition drift component based on a reference curve to obtain a vibration residual error, and calculating an equivalent standard working condition temperature based on a heat balance principle; respectively calculating a first weight based on data statistics and a second weight based on network topology, and adaptively generating a comprehensive coupling weight according to a consistency coefficient of the first weight and the second weight; and finally, judging a health state level by using a cloud model. Through deep fusion of a physical mechanism and data driving, the problems that fault features are difficult to extract and the model robustness is poor under variable working conditions are solved, and accurate evaluation of the unit state is achieved.

The invention discloses an LCD display screen production whole-process collaborative management method and system based on the Internet of Things, particularly relates to the technical field of production process collaborative management, and is used for solving the problems of circular waiting and resource stiffness caused by lack of global resource allocation dependency relationship analysis in a complex production scene in an existing collaborative management method. Equipment state data and material position data of each process are acquired in real time, a resource allocation relation graph with production equipment as resource nodes and production tasks as task nodes is constructed, a resource access sequence of each production task is analyzed to identify a circular waiting path, and a process association network and a production flow network are combined to evaluate a blockage propagation risk. And finally, on the basis of the relief urgency degree, the production tasks are selected to carry out resource reallocation so as to realize the relief of the circular waiting path, and the overall efficiency of the production line and the resource utilization rate are improved.

The invention relates to the field of data processing, and discloses a real-time data processing system and method, and the method comprises the steps: carrying out the real-time capturing of a continuous data flow from a multi-source collection end, and generating an initial data sequence with an emergency weight; carrying out cross-source interleaving processing on the initial data sequence, and forming a composite feature set with a time sequence hierarchy characteristic by combining an offset track of a historical data period, buffer areas of adjacent data channels and a conflict frequency of multi-source input; on the basis of the composite feature set, utilizing a partition aggregation deduction algorithm to extract a dynamic occupation path of the data event in a processing cycle, and marking potential abnormal candidate segments; performing re-grading labeling on the abnormal candidate segments, and constructing a local association network with a weight gradient; and according to the local association network, detecting and identifying the data processing units with resource mismatch in the target period, and deducing a corrected data processing sequence. The method has the advantage of improving the real-time performance of data processing.

The invention relates to the technical field of virtual simulation teaching. The e-commerce virtual simulation teaching resource construction method and system based on the ability map are provided, and the method comprises the following steps: on the basis of e-commerce industry technical post requirements, disassembling post capabilities, and generating a structured ability map comprising a core ability unit, a skill point layer and a knowledge point layer; performing classification design processing on the virtual simulation scene resources according to a skill point layer in the structured ability map, and generating a virtual resource library comprising production type scene resources, interactive type scene resources and creative type scene resources; based on the mapping relation between the nodes of the structured ability graph and the virtual resource library, performing label labeling processing on the virtual simulation task to generate a task-knowledge point association network, the technical effects of improving the matching precision of resources and post requirements, optimizing the classification systematicness of virtual simulation resources and enhancing the dynamic relevance of learning paths and knowledge points are achieved.

The invention discloses a dynamic hierarchical encryption system for multi-tenant e-commerce data, and relates to the technical field of multi-tenant data security, the system comprises an encryption management center, the encryption management center is in communication connection with the following modules: a data sensing and grading module, which is used for collecting multi-source context data of an e-commerce platform, and sending the multi-source context data to the encryption management center; performing basic sensitivity level division on the context data; and the multi-tenant knowledge graph construction module is used for constructing a multi-tenant knowledge graph based on the tenant-data-authority association network in combination with the multi-source context data. According to the method, dynamic self-adaptive adjustment of encryption strength is realized through cooperation of the fruit fly algorithm and the knowledge graph, the system dynamically optimizes combination of key length and the encryption algorithm based on data grading labels and real-time context data, and the fruit fly algorithm searches an optimal solution through iteration, so that the system has high encryption efficiency while ensuring compliance. And encryption delay is controlled within a real-time requirement range, so that the user experience in a multi-tenant scene is remarkably improved.

The invention provides a communication module state switching method and system based on event triggering, and relates to the technical field of communication.The method comprises the steps that firstly, multi-source event source information in operation of a communication module is collected, and event influence hierarchy division is conducted; a target association network is generated by combining a current operation state and a historical state switching database of the communication module; generating a dynamic path including a hardware parameter adjustment sequence and the like based on the target association network and the historical stability record; pre-judging the stability of the dynamic path; generating a state switching execution instruction according to the pre-judgment result and generating switching process data; and finally, updating the historical state switching database and the target association network based on the switching process data to form closed-loop optimization, thereby realizing dynamic optimization of communication module state switching, and improving adaptability and stability of switching.

The invention provides an intelligent question answering method and system based on a traditional Chinese medicine classical meta-term engine. The method comprises the following steps: identifying and extracting core traditional Chinese medicine terms and a user query intention in a user question; the core traditional Chinese medicine terms are input into a pre-constructed traditional Chinese medicine classical meta-term engine to be processed, normalized mapping and semantic association extension of the terms are completed, and the engine is constructed based on a classification-term-word list-semantic CTVS association framework. Comprising a traditional Chinese medicine classical book term ancient and modern double-classification system C layer, a meta-term extraction and standardization T layer, a dynamic word list V layer and a semantic association network S layer. Carrying out graph pattern matching and reasoning in the S layer, traversing and integrating a plurality of deep association paths by taking classical element terms and corresponding modern clinical terms as double center nodes, and retrieving answer information associated with the query intention; and carrying out integration sorting and structured assembly on the answer information to generate a structured answer. Intelligent questions and answers can be performed on traditional Chinese medicine related questions of the user.

The invention relates to the technical field of submission suggestions, and discloses a recommended periodical submission decision-making method, which comprises the following steps of: obtaining a metadata set of a paper to be submitted, and executing logic completeness verification; performing multi-level semantic feature analysis and weighted fusion processing on the metadata set, and calculating and generating a periodical comprehensive matching degree quantitative evaluation value based on a collaborative analysis mechanism of a publishing domain knowledge rule base and a periodical academic association network; constructing a candidate periodical dynamic sorting framework taking the evaluation value as a core weight; in response to a selection operation instruction of a user on the candidate periodicals, obtaining a target periodical, and executing deep academic feature analysis on the target periodical; and in response to a deep academic feature analysis result executed on the target periodical, generating a structured recommended periodical analysis report including a verifiable decision basis, the analysis report including periodical quality evaluation system indexes. According to the method, the submission decision suggestions can be comprehensively provided for the copyright in a multi-dimensional manner, and the copyright is assisted to make an accurate submission decision.

The invention discloses a medical institution medical insurance cost accurate monitoring and intervention method, and relates to the technical field of medical informationization, and the method comprises the following steps: collecting multi-source medical insurance data in real time, carrying out the standardized cleaning, and generating a standardized data flow; the standardized data flow is converted into a multi-dimensional feature vector, and time dimension deviation is eliminated through a dynamic baseline; based on the generated multi-dimensional feature vector, calculating a dynamic association weight of each feature and medical insurance cost change in real time; in combination with the feature vectors and the dynamic weights, analyzing a time sequence association relationship between the features, and constructing a multi-dimensional association network to capture a combined abnormal behavior pattern; integrating the feature vector, the dynamic weight and the association network result to generate a real-time anomaly score; triggering a grading response mechanism according to the real-time abnormal score, and executing an automatic intervention measure from observation recording to forced interception; and on the basis of intervention records and historical data, periodically updating a feature baseline and a weight calculation rule to form self-optimization closed-loop control.

The invention provides a multi-dimensional knowledge extraction construction method and system applied to operation and maintenance technology services, and relates to the field of operation and maintenance technology services, and the method comprises the steps: firstly obtaining an operation and maintenance service full record generated in an operation and maintenance technology service process, and then carrying out the association network construction processing of the operation and maintenance service full record, and obtaining a target association network structure. And based on the structure, identifying the core record cluster, extracting complementary operation and maintenance information, and fusing to form an operation and maintenance knowledge module set. And then performing dynamic knowledge system construction processing on the operation and maintenance knowledge module set to form a target operation and maintenance knowledge system with a self-adjustment capability. And finally, based on the target operation and maintenance knowledge system, aiming at the newly received operation and maintenance service request, generating operation and maintenance service response content containing the resource optimization suggestion, thereby effectively improving the operation and maintenance service quality and efficiency.

The invention provides a raw electrode roasting process parameter collaborative optimization control method based on reinforcement learning, and belongs to the technical field of raw electrode roasting. The method comprises the following steps: collecting multi-source state data in a raw electrode roasting process, and carrying out feature extraction; and a reinforcement learning model based on the depth deterministic strategy gradient is constructed, and the operation efficiency of the roasting process is evaluated. And constructing a dynamic association network of the multi-source data. A multi-objective optimization model is established, a non-dominated sorting genetic algorithm is adopted for solving, a parameter optimization solution set is obtained, and optimal control parameters of the current working condition are selected through an analytic hierarchy process. And converting the optimal control parameter into an execution instruction through the industrial controller. According to the method, through combination of multi-source data fusion and dynamic association network construction, reinforcement learning and multi-objective optimization, a roasting complex process is accurately adapted, collaborative optimization of quality, energy consumption and equipment life is realized, control accuracy and reliability are improved, and stable and efficient production is guaranteed.

The invention provides an environmental protection planning dynamic generation method and system based on man-machine interaction and iterative feedback, and the method comprises the steps: firstly collecting an initial environmental protection planning element set of a target region, constructing an initial association network, and calculating the edge association strength; receiving interactive operation data through the human-computer interaction interface, and updating the associated network to obtain an updated network; collecting a feedback data set in a preset interaction period and performing semantic annotation; inputting the feedback data with the semantic label into the element evolution model, driving the node expansion of the association network and the reconstruction of the edge association relationship, generating an evolved network, and identifying element conflicts; and calling a planning scheme generation model to execute multi-target constraint optimization according to the evolved network and conflict analysis report, generating a dynamic environmental protection planning scheme, feeding back the dynamic environmental protection planning scheme to a human-computer interaction interface, and outputting a scheme evolution trajectory diagram. According to the method, dynamic generation and optimization of environmental protection planning are realized, and the scientificity and feasibility of planning are improved.

The invention discloses a smart laboratory scene knowledge retrieval method based on an AI large model, and particularly relates to the technical field of laboratory knowledge management.The method comprises the following steps that multi-modal data in an experiment is obtained, semantic vectors of all modals are generated through preprocessing, and the semantic vectors are stored in a database; aiming at each modal semantic vector, performing cosine similarity alignment and fusion to form a unified semantic vector, and constructing a laboratory knowledge graph and a cross-modal large model; creating a knowledge association network in combination with the cross-modal large model and the laboratory knowledge graph; and outputting a knowledge retrieval result adaptive to the current experiment scene based on the knowledge association network, and recording user feedback. According to the scheme, the problems that a traditional retrieval method is insufficient in heterogeneous data processing capacity, insufficient in context understanding and the like are solved, the accuracy, the intelligent level and the scene adaptability of knowledge retrieval are remarkably improved, intelligent applications such as experimental scheme recommendation and exception handling are effectively supported, and the refined knowledge management requirement of an intelligent laboratory is met.

The invention discloses a shipboard aircraft maintenance process simulation method and system based on virtual reality, and relates to the technical field of analogue simulation. According to the method, the environment sensing data packets of the shipboard aircraft and the maintenance environment are collected through the multi-modal sensor array, the shipboard aircraft maintenance simulation space is constructed based on the environment sensing data packets, and the regional maintenance step association network under different maintenance events is established according to the maintenance event records; mapping the regional maintenance step associated networks to the surface of a shipboard aircraft maintenance simulation space, and matching the regional maintenance step associated networks with one another to obtain a maintenance step associated network; and a user performs communication interaction with the shipboard aircraft maintenance simulation space through the VR equipment, collects a user interaction process through the VR equipment, inputs a user interaction action into the maintenance step association network, and further outputs a corresponding special reference scheme to judge whether the user interaction process is compliant or not.

The invention provides a multi-modal large model-based content generation method and system, and belongs to the technical field of digital content creation and dissemination, and the method comprises the steps: firstly building a demand association network comprising a user demand node, a content element node and a scene form node, and marking the association strength; constructing a multi-modal element coupling pool comprising a text description unit, a visual display unit and a semantic association unit on the basis, enabling the multi-modal element coupling pool to form mapping with demand association network nodes, calling a multi-modal large model to carry out situational mapping processing on the multi-modal element coupling pool, and generating an initial content framework set; and performing element collaborative optimization on the initial content framework set to obtain an optimized content framework conforming to content element node constraints, generating a target content set according to the optimized content framework, and pushing the target content set to a content distribution node to complete propagation, thereby efficiently generating and accurately propagating the multi-modal content.

The invention relates to the technical field of financial credit data evaluation, and discloses a user credit evaluation method based on multi-source credit data. The method comprises the steps of collecting multi-source heterogeneous credit investigation data in real time through a preset API interface group, and performing fusion after cleaning and standardization to form a user credit investigation data cube; extracting static, behavior sequence, association network and time sequence evolution four-dimensional features based on the cube; processing corresponding features by using a gradient boosting tree, a graph neural network and a time sequence convolutional network sub-model by using a multi-modal integrated learning framework, and generating a basic credit score through adaptive weighted fusion; the score is dynamically calibrated in combination with the real-time data flow and the macroeconomic factor, and high-risk user judgment and early warning are carried out based on dynamically adjusted behavior permission parameters by utilizing a real-time risk early warning engine; and finally, model retraining is triggered based on historical and recent default rate differences. According to the method, comprehensive, accurate and dynamic credit assessment is realized, and the assessment accuracy and timeliness are remarkably improved.

An authentication server of an identity management system may establish an authentication policy for a tenant of a multi-tenant system and receive device access signals from one or more network identifiers. In some examples, the authentication server may receive an indication from machine learning (ML) models to update the authentication policy of a tenant based on a set of authentication rules of one or more second tenants that are for one or more applications common between the tenant and the one or more second tenants. In some other examples, the ML model may monitor a set of device access signals received at the authentication server to obtain a set of assurance scores for associated network identifiers. The authentication server may then update the authentication policy for a tenant, generate a set of network zones, or both based on the ML model outputs.

The invention relates to the field of park power management, and discloses a park power intelligent management method and system, and the key points of the technical scheme are that S1, a full-dimensional collection network is constructed, and data collection is carried out; s2, carrying out preprocessing and tagging processing on the collected data, and constructing a data association network; s3, based on the data association network, screening key data objects, integrating historical power data, environmental data and associated data, and training an intelligent prediction model group by adopting a machine learning algorithm; s4, performing real-time monitoring on a data object by using the intelligent prediction model group, and identifying power operation abnormity through dynamic threshold setting, real-time data comparison and abnormity type judgment; s5, performing graded early warning according to the abnormal type and severity; s6, performing intelligent fault diagnosis on the abnormal data object, generating a disposal scheme and tracking a disposal process; and S7, optimizing the data association network, the prediction model and the early warning response flow according to the application result of the intelligent prediction model group.

The invention provides a deep learning-based intelligent monitoring system and method for reservoir bank collapse risk, and relates to the technical field of bank monitoring, and the method comprises the steps: obtaining and preprocessing all monitoring point data of a reservoir bank monitoring network, and constructing a total monitoring point set; screening key base points and quantifying the inherent risk characterization quantity of the key base points; a dynamic association network of the common monitoring points and the key base points is established, and the final clustering association degree of the common monitoring points relative to the key base points is obtained; calculating a radiation risk value of each key base point to the associated common monitoring points in combination with the inherent risk characterization quantity and the final clustering association degree; fusing the radiation risk values of all the key base points to obtain a comprehensive risk value of the common monitoring point; constructing a directed weighted graph by taking the key base point as a source point, and dividing risk communities by adopting a graph neural network community discovery algorithm; and based on the community comprehensive risk value statistical distribution and the highest risk level of the contained key base points, assigning a unified risk level to each monitoring point and outputting the risk level.

The application provides a content generation method and system based on a multi-modal large model, belonging to the technical field of digital content creation and dissemination. First, a demand association network containing user demand nodes, content element nodes and scene form nodes is established, and the association strength is labeled. Based on this, a multi-modal element coupling pool containing text description units, visual display units and semantic association units is constructed, which is mapped with the demand association network nodes. A multi-modal large model is called to perform situational mapping processing on the multi-modal element coupling pool, generating an initial content framework set. The initial content framework set is optimized in terms of element coordination, obtaining an optimized content framework that meets the constraints of the content element nodes. According to the optimized content framework, a target content set is generated and pushed to the content distribution node for dissemination, thereby efficiently generating and accurately disseminating multi-modal content.

A user equipment (UE) operating in an “Onboarding Mode” may search for a network broadcasting Onboarding Capability Information (OCI), then register using onboarding credentials and receive SNPN credentials from the network. The UE may then exit onboarding mode, enter Manual Network Selection or Automatic Network Selection mode, and connect to the SNPN. A UE may also receive from a network a list of PLMNs and SNPNs that are equivalent then, when registering, indicate to the network that a requested slice is not associated with the UE's HPLMN, but is associated with an SNPN. The network may indicate to the UE how the slices of the network map to the slices of the SNPN, and may indicate whether a slice that is offered by the network only partially maps to a slice of the SNPN or HPLMN.

The invention discloses a self-adaptive education system based on knowledge gene evolution, and belongs to the technical field of knowledge gene evolution. The system comprises a dynamic knowledge graph engine, a defect response type training sequence generator, a multi-modal memory intensifier and a hypercycle coordination module, wherein the dynamic knowledge graph engine decomposes subject knowledge into heritable units and constructs a dynamic association network of which the weight is updated in real time along with a learning data flow; a defect response type training sequence generator generates a target variable type training sequence according to the cognitive defect node coordinates; the multi-modal memory intensifier generates multi-sensory nerve coding pulses according to training feedback; and the hypercycle coordination module is connected in series with the modules to form a self-adaptive closed loop of knowledge modeling, defect clearing, memory curing and knowledge iteration. The system can generate a cognitive defect thermodynamic diagram, realizes accurate positioning of cognitive vulnerabilities, provides clear targets for teaching intervention, and improves the pertinence and effectiveness of adaptive education.