153 results about "Affiliation network" patented technology

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 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 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 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 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 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 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.

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 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.

The invention provides a project group comprehensive evaluation method and device for a power grid transformation project, and a medium. The method comprises the steps of obtaining related text data, geographic information system data, project historical data and power grid topological structure data; performing feature extraction and analysis on the related text data to construct a semantic feature association network; performing connection analysis on the geographic information system data and the power grid topological structure data to construct a geographic topological feature association network; performing time sequence feature analysis on the project historical data to construct a time sequence feature association network; constructing a multi-dimensional coupling network based on the semantic feature association network, the geographic topological feature association network and the time sequence feature association network; identifying a core project group from the multi-dimensional coupling network; establishing a project group comprehensive evaluation model based on the core project group; performing comprehensive evaluation on the to-be-evaluated project group through the project group comprehensive evaluation model to obtain a target project group; and evaluating the comprehensive benefit of the target project group in the power grid transformation. Therefore, the project group evaluation comprehensiveness is improved.

The invention relates to the technical field of material purchasing management, and particularly discloses a material purchasing process optimization method and system based on deep learning, and the method comprises the steps: firstly constructing a unified data set containing time sequence features and static features through multi-source data collection; secondly, time sequence features are decomposed into trend, period and fluctuation components through the multi-scale decomposition technology, the feature contribution degree is dynamically adjusted in combination with static features, and accurate demand prediction is achieved; establishing a multi-dimensional evaluation matrix to quantify the out-of-stock influence, and dividing the purchase emergency degree into three levels through a decision tree algorithm in combination with a supplier capability evaluation system; constructing a task association network, calculating priority scores through feature propagation and deep fusion, and forming an optimized task sequence; and finally, based on historical approval data, recommending an optimal approval path through multi-dimensional similarity matching, and realizing continuous updating of approval features. According to the invention, intelligent optimization of the whole purchasing process is realized.

The invention relates to a digital non-abandoned rural culture display and interaction method and device based on a virtual reality technology, and a medium, and the method comprises the steps: obtaining multi-modal data, carrying out the time-space alignment and feature extraction, and obtaining an action track feature and a time-space correlation feature; generating a fusion feature matrix and constructing a virtual display scene; integrating a dynamic narrative engine in the virtual display scene, and constructing a non-abandoned knowledge graph; interactive behavior information and physiological feedback information are obtained in real time, semantic retrieval and path reasoning are carried out, and a response strategy set is obtained; executing the response strategy set; in conclusion, by obtaining the multi-modal data, carrying out space-time alignment and feature extraction, constructing the virtual scene and the knowledge graph and responding to the user information in real time, an organic association network of non-perpetual cultural elements can be constructed, user interaction behaviors can be responded in real time, technical support is provided for display, interaction and inheritance of non-perpetual cultural, and user experience is improved. And the intelligence and the reliability are improved.

The invention provides a traffic energy source load prediction and collaborative optimization method and system based on data fusion, and relates to the technical field of traffic energy management, and the method comprises the steps: firstly, accessing multi-source traffic energy data to generate a traffic energy data association pool; generating a dynamic source-load association network based on the traffic energy data association pool; mapping the traffic scene features to a dynamic source-load association network to generate a multi-dimensional fusion deduction input set; performing source load change trend deduction on the multi-dimensional fusion deduction input set through a scene-adaptive multi-dimensional fusion deduction model to obtain a traffic energy source load prediction result; and a collaborative optimization scheme is formed based on the traffic energy source load prediction result and the scheduling demand and is fed back to the network optimization scene adaptation weight, so that the operation efficiency and reliability of the traffic energy system are effectively improved, and the energy waste and the operation cost are reduced.

The invention discloses a dynamic cross-domain access authority management method and system based on a zero-trust architecture, and the method comprises the steps: continuously obtaining user behavior data and terminal equipment information of a terminal, carrying out the multi-identity authentication processing of a user access behavior, generating an access trusted identity, and building a three-dimensional association network of a user, equipment and an environment. The method comprises the steps of generating an access permission rule matched with a current risk through context connection of user access behaviors and calculation of a dynamic trust score, mapping the access permission rule to an equivalent permission of a target domain corresponding to the user access behaviors, executing and tracking cross-domain access of the user access behaviors to generate a cross-domain access link of the user access behaviors, and sending the cross-domain access link to the user access behaviors. And performing access context re-verification processing on the user access behavior according to a preset period, and calculating the deviation degree of the re-verified cross-domain access link so as to dynamically adjust the user access authority. The method has the advantages that a unified access mechanism is established, safety control is achieved, and the dual requirements of equal-guarantee compliance and business innovation are met.

The invention discloses a network security monitoring method, which comprises the following steps of: acquiring full-life-cycle data and attributes of network processes in real time, constructing a process chain table and an associated network, and sorting a relationship between the processes; secondly, matching a network event with a process timeline, dynamically dividing a time window according to a process life cycle, calculating a process time characteristic and a network activity characteristic, comparing a historical normal mode, quantifying a difference by utilizing an algorithm, and identifying an abnormal process; then, inputting the comparison process into a support vector machine to establish a prediction model, and predicting an abnormal process in real time; and finally, abnormal process information is fed back to the security equipment, and abnormal files are positioned and isolation / deletion operation is executed in combination with network behavior data association analysis. According to the method, the abnormal process can be accurately identified, misjudgment is reduced, the sensitivity requirements of different service scenes are met, the abnormal file is positioned by means of network behaviors, and the accuracy and timeliness of network security protection are effectively improved.

The invention provides a maritime business standard operation program intelligent construction method and system based on multi-source knowledge fusion, and relates to the technical field of maritime business intelligent construction. Multi-source knowledge and multi-modal data of maritime business are collected firstly and then processed through a Transform technology to obtain a business knowledge graph and scene interaction data; a business process model is established based on the two, a business association network is constructed through a graph neural network to generate an operation program conforming to international and domestic dual standards, and then a standard operation program is formed after test optimization of an application test terminal integrating AR and a voice module, so that actual maritime affair requirements can be accurately met; and standardized and intelligent development of maritime affairs is facilitated.

The invention relates to the technical field of blasting engineering digital monitoring, and discloses a point cloud fused blasting site digital management method and system. The method comprises the steps of collecting multi-time-sequence point cloud data of a blasting site, extracting surface geometric information of an entity unit and generating a structure contour of the entity unit; performing space-time association on the entity units of adjacent time sequences, constructing a time dimension association network, and screening out stable units with constant geometric attributes and evolved dynamic units according to the time dimension association network; calculating a global statistical invariance interval for the stable unit, identifying a key time sequence node for the dynamic unit, and calculating an evolution stability boundary in stages; and when real-time point cloud data is received, qualified information is selected and combined to form a structured digital skeleton according to conformity judgment of a structure contour and a corresponding unit boundary. According to the method, automatic classification and differentiation stability modeling of entity behavior modes are realized, and the capability of continuously and finely evaluating the state of a blasting site is improved.

The invention discloses a power supply enterprise marketing business data management method and system, and relates to the technical field of power systems and automation thereof. Multiple types of marketing data are acquired from multiple systems and terminals, and the acquisition frequency is adjusted according to data types; processing format errors, abnormal values and missing values by using a rule engine and machine learning; establishing an association network based on the knowledge graph, combining similar entities, processing conflict data according to the credibility of a data source, and associating a unified identifier; calculating a comprehensive score through a five-dimensional index, and dividing data quality grades; and protecting data according to sensitivity grading, controlling access authority, recording an audit log to generate a report associated service KPI analysis, and optimizing a governance strategy to form a closed loop. The method solves the problems of power supply enterprise marketing data multi-source adaptation, quality control and cross-domain fusion, improves the data quality and safety, provides reliable data support, and reduces the customer complaint rate.

The invention relates to the technical field of social network application, in particular to a social media viewpoint evolution simulation method and device based on coupling dynamics, and the method comprises the steps: extracting event topic interaction network data based on social network public information, carrying out the statistics of user historical interaction behaviors, and determining an information transmission network and an internal association network according to the data, the two forms a multi-layer association network; determining a transmission state of forwarding and a text viewpoint baseline for calculating a transmission state and a viewpoint value of a user in the social network data set; and inputting the propagation state and the viewpoint value into a coupling dynamics simulation model, carrying out iterative calculation until the viewpoint value converges so as to obtain a final propagation state and a final viewpoint value of the user, and generating forwarding situation distribution and user viewpoint distribution. Therefore, the problems that errors are generated, public opinion monitoring and early warning and public opinion guide strategy construction are affected and the like due to the fact that a viewpoint evolution model adopts a single-layer propagation structure and coupling modeling is not carried out on propagation and an internal correlation structure in the related technology are solved.

The invention discloses a multi-objective collaborative optimization control system and method for a photovoltaic inverter, and relates to the technical field of inverter control. According to the method, multi-source state data of an inverter cluster and a power station environment are acquired, a cluster mirror image three-dimensional model is established according to the multi-source state data, state particles and compensation particles are set for each inverter, and according to historical operation records of the inverters, the state particles and the compensation particles are associated with a plurality of feature parameter ranges, so that the cluster mirror image three-dimensional model is established. State particles and compensation particles of different inverters are mutually connected and matched to obtain a state-compensation association network, real-time multi-source state data of an inverter cluster and a power station environment are obtained and input into the cluster mirror image three-dimensional model and the state-compensation association network, and then a multi-target collaborative decision is output. And simulating and executing the cluster mirror image three-dimensional model in the cluster mirror image three-dimensional model, and correcting the multi-target collaborative decision according to a simulation result.

The invention belongs to the technical field of e-commerce, and particularly discloses an enterprise e-commerce process customization and substituted operation service system. The system comprises a user intention real-time analysis module used for outputting a user intention quantization vector through a deep behavior pattern recognition algorithm; the strategy knowledge graph construction module is used for constructing and dynamically updating a multi-dimensional association network containing commodities, user tags and marketing actions; the dynamic strategy coupling engine is used for inputting the intention vector into a knowledge graph and generating a matched composite marketing strategy instruction set through graph neural network reasoning; the strategy instruction atomization execution unit is used for decomposing the instruction set and scheduling the instruction set into atomic operation instructions; and the full-link effect tracking and feedback module is used for collecting effect data and feeding back the effect data to the knowledge graph to optimize the weight. According to the system, end-to-end intelligent automatic closed loop from user intention recognition to marketing strategy generation and execution is realized, and the timeliness, accuracy and self-adaptive capability of marketing response are improved.

The invention provides a power business data tracing method, system and device and a medium, and the method comprises the steps: responding to a business operation request, analyzing the request, and obtaining state change information; updating a historical evolution chain of the corresponding entity through a transverse pointer, and updating a preset multi-dimensional entity association network through a longitudinal pointer to obtain a target association network; in response to a tracing request of target power business data, obtaining historical state transition of the entity through tracing of the updated historical evolution chain; and reconstructing the entity association relationship at the target historical moment based on the target association network, thereby realizing the tracing of the target power business data. The longitudinal pointers are used for updating the multi-dimensional entity association network, the transverse pointers synchronously record the entity historical evolution chain to enable the time dimension and the space dimension to form a unified whole, the change tracks of the entities are accurately associated through the transverse pointers and the longitudinal pointers, and the precision of the tracing result of the power business data is improved.

This invention relates to the field of software detection technology, specifically disclosing a knowledge graph-based intelligent detection method and system for software backdoors. The method involves intercepting system kernel events and reading the object handle table to generate a time-series interaction log. Based on this log, a time-series knowledge graph is constructed, forming an interconnected network composed of process nodes, token nodes, and relationships such as handle holding, token replication, and memory writes. Newly added process nodes with process creation timestamps are further extracted as target process nodes, and the nominal parent process node is located based on its parent process identifier. Subsequently, a lineage consistency check is performed around the target process node, and cross-chain constraint analysis is conducted using the nominal parent process node, anonymous process nodes, token nodes, and memory write relationships. When contradictions arise in handle permissions, token inheritance, and write timing, and the lineage forgery index exceeds a preset threshold, the target process node is determined to be a parent process deceiving a backdoor process, and a threat interception command is output.

The invention discloses an information association method and device, a storage medium, electronic equipment and a program product, and relates to the field of financial science and technology, and the method comprises the steps: carrying out the anonymous processing of metadata of a first type of entities and a second type of entities; analyzing the anonymous metadata by using a graph neural network, and determining a target implicit relationship network between the first type of entities and the second type of entities according to an analysis result, the target implicit relationship network being used for representing an association relationship between the first type of entities and the second type of entities; generating an entity service path on the basis of the target implicit relation network according to accounts corresponding to the first type of entities and the second type of entities; and updating the target implicit relationship network according to the entity service path to obtain a target association network corresponding to the first type entity and the second type entity. The technical problem that in the prior art, due to the fact that a financial institution is difficult to effectively recognize and utilize the incidence relation between different entities, the personalization of service contents generated for the different entities is low is solved.

The invention relates to the technical field of network security protection, and discloses a network information security protection method based on edge computing, comprising the following steps: S1, obtaining the number of network targets to which each edge node applies for connection in a target area in the current time period; s2, pairing each edge node with each network target to construct a first detection group, and constructing a second detection group according to the application abnormal value of the network target in each edge node in the first detection group; and S3, obtaining a comprehensive abnormal value of each network target in the second detection group, and selecting an abnormal reference according to the comprehensive abnormal value of each network target. The method comprises the following steps: constructing a first detection group and a second detection group to carry out hierarchical detection, identifying a plurality of abnormal network targets, identifying associated network targets controlled by the same threat person through similarity matching of multiple feature dimensions, evaluating threat degrees and danger levels of the abnormal network targets, and finally executing a graded progressive differential protection strategy.

The invention discloses a resource application limiting method and device and electronic equipment, and relates to the field of financial science and tech, and the method comprises the steps: obtaining an associated network diagram corresponding to a target user in response to a resource application request sent by the target user; inputting the association network diagram into a risk identification model to obtain a risk coefficient of the target user; and obtaining a resource application condition corresponding to the resource application request, and displaying target prompt information and sending out a limiting signal under the condition that the risk coefficient meets the resource application condition corresponding to the resource application request. According to the invention, the technical problem of low limitation accuracy of resource application in related technologies is solved.

The invention provides an AI-based image semantic understanding and teaching content association method, which comprises the following steps: acquiring blackboard-writing content through a camera, mapping the blackboard-writing content into a blank template, and generating structured blackboard-writing data; based on a preset knowledge base, performing pairwise association on knowledge points corresponding to each piece of text information in the blackboard-writing data to generate a blackboard-writing data preliminary association network containing a plurality of association relationships; synchronously collecting and identifying teaching audio information, and extracting key knowledge points from the audio information according to a time sequence; carrying out mapping matching on the extracted key knowledge point sequence and the preliminary association network, finding out association paths capable of communicating the key knowledge point sequence through a mapping matching strategy, and calculating the confidence coefficient of each association path; and selecting the path with the maximum confidence from all the association paths as a final knowledge point association relationship, and inputting the final knowledge point association relationship into an education library.

This invention discloses a digital design method for construction projects based on BIM and data collaboration, belonging to the field of digital design technology for construction projects. The method includes acquiring an initial design model set of the target construction project and a cross-disciplinary design parameter set containing constraints from multiple disciplines such as structure, MEP, and architecture. The initial design model set is then meshed in three dimensions to generate a structured design space containing geometric voxels and attribute metadata. Within this space, a parameter semantic association network is constructed, forming a parameter association network model representing parameter dependencies and conflicts. Based on this model, multi-disciplinary constraint consistency evolution calculations are performed to generate a collaborative design optimization space that satisfies all constraints. A computer-aided design optimization engine is used for global optimization to obtain the final collaborative design scheme, which is then fed back to the BIM design platform. This invention integrates geometric and attribute data, clarifies cross-disciplinary parameter relationships, and realizes multi-disciplinary digital collaborative design optimization of construction projects.

This application provides a method and system for dynamic knowledge updating of a large-scale model for operation and maintenance (O&M) technical services. It relates to the field of O&M technology, and models the knowledge generation triggering factors, iteration impact range, and knowledge association strength in multi-source O&M knowledge update sources to obtain a knowledge full-link evolution set including knowledge generation trigger records, iteration impact assessment results, and cross-knowledge association networks. Then, dynamic coupling rules are generated based on the real-time scenario characteristics of O&M tasks and this knowledge full-link evolution set. These rules are used to filter and integrate the knowledge full-link evolution set to obtain a scenario-coupled knowledge set. This set is embedded into the knowledge architecture of the large-scale O&M technical service model, and storage node parameters and retrieval logic are adjusted to obtain the basic updated model. Finally, the basic updated model is dynamically adapted in multiple dimensions, and the knowledge call priority sequence and storage node parameters are adjusted in conjunction with changes in scenario characteristics to generate an adapted updated model, thereby improving the adaptability of the large-scale O&M technical service model.