46 results about "Collaborative knowledge" patented technology

The invention discloses a multi-agent collaborative knowledge reasoning system based on a large language model, and relates to the technical field of intelligent manufacturing and artificial intelligence. Natural language output of a large language model is converted into rules, facts and ontology fragments which can be directly consumed by an inference engine through knowledge obtaining and compiling, continuous increment updating of cross-domain knowledge is achieved in cooperation with metadata with sources and timestamps, and the limitation that a traditional static knowledge base is difficult to cover dynamic faults is overcome; secondly, a blackboard and agenda mechanism is used as a cooperative carrier, intermediate assertions of intelligent agents such as vibration, circuits and logs are published and subscribed in a structured mode, and a conflict resolution and consistency verification module carries out unified judgment according to specificity, time freshness and source credibility; therefore, delay and uncertain accumulation caused by long-chain natural language dialogues are avoided in a strong real-time scene.

The invention discloses a multi-source feature collaborative knowledge mining and semantic association method, and belongs to the technical field of full-life-cycle knowledge processing of railway track engineering. According to the method, field-related documents are screened, an element range and a processing sequence are limited in combination with a knowledge graph, the documents are customized to generate a term candidate set, term statistical weights are calculated based on a full-life-cycle corpus, dynamic semantic vectors are generated by utilizing a field self-adaptive pre-training model, and composite concept representation is obtained through fusion of an attention mechanism. And linking the knowledge graph to construct a heterogeneous graph, mining association through a graph attention network, analyzing, querying and verifying sequential logic, and then outputting structured knowledge. According to the method, the problems of railway track engineering data islands and cross-stage semantic segmentation can be solved, low-frequency key terms are accurately recognized, the result interpretability is enhanced, applications such as design optimization and construction management and control are directly supported, and the method is adaptive to multiple engineering professions and high in practicability.

The invention relates to the technical field of knowledge tracking, and discloses a graph enhanced double-memory collaborative knowledge tracking model based on an ACT-R cognitive architecture. Comprising a static knowledge structure coding module based on hypergraph projection, a batch-level dynamic learning track construction and coding module, a cross-graph gating fusion mechanism, a sequence modeling module and an expert hybrid prediction module. According to the method, long-term stable structured semantic association between concepts in declarative memory is modeled through a static knowledge structure diagram, a dynamic learning trajectory diagram based on batch reconstruction is designed to accurately capture an evolution rule of a behavior sequence in programmed memory, and on the basis, a cross-diagram gating fusion mechanism and a hybrid expert mechanism are introduced, so that the evolution rule of the behavior sequence in the programmed memory is accurately captured. And self-adaptive fusion and multi-path decision of double-graph features are realized.

The application belongs to the technical field of recommendation system, and provides a knowledge graph recommendation method based on multi-view contrast learning. Four different views are comprehensively considered and constructed from different perspectives, including a collaborative knowledge graph composed of a knowledge graph and a user-item interaction graph, a user-item interaction graph, and a user-user graph and a project-project graph constructed based on the user-item interaction graph. In addition, the intersection and union ratio is applied to reasonably construct the user-user graph and the project-project graph, and a receptive field is designed to avoid introducing more noise. Then, the four views are subjected to contrast learning at the local and global levels, aiming to mine the collaborative information between users and projects, between users, and between projects, and the global structure information in a self-supervised manner, thereby alleviating the problem of sparse supervision signals.

The application provides a construction scheme intelligent generation method and system based on multi-agent cooperation, and relates to the field of building engineering digitization technology. The method comprises the following steps: constructing a project knowledge base containing vector index and knowledge graph index; retrieving similar historical schemes based on project characteristics and learning chapter structure characteristics; generating a construction scheme outline; performing knowledge-enhanced retrieval on the chapter to be generated to obtain structured technical data; using a double-channel generation mechanism to process general chapters and construction method chapters respectively; receiving natural language fine-tuning instructions to complete content correction; converting the generated content into a standard Word document and applying an enterprise template. The system comprises a knowledge base construction module, a template retrieval module, an outline generation module, a knowledge retrieval module, a multi-agent cooperation module, a full-text integration module, and a document output module. The application significantly improves the efficiency and technical accuracy of construction scheme preparation through multi-agent division of labor, knowledge-enhanced retrieval, and double-channel generation, and solves the problems of low efficiency, case residue, and insufficient targeting in traditional scheme preparation.

The application relates to a collaborative knowledge graph recommendation model construction method enhanced by contrast learning. Three contrast learning tasks are designed to supplement the recommendation supervision task, so that the problem that the node representation learned by the graph neural network is inaccurate due to the problems of sparse supervision signal, long tail effect, noise interference and the like can be alleviated. Meanwhile, in order to make the contrast learning more beneficial to the recommendation task, a multilayer perceptron containing two linear layers is introduced between the node representation and the contrast learning to help the contrast learning training. The application promotes the development of the knowledge graph-based recommendation system and has practical significance.

This invention relates to the fields of artificial intelligence and software testing technology, and provides a content compliance review method for a "testing brain" based on KG and RAG collaborative knowledge enhancement. The method includes: acquiring a set of reference documents and obtaining the knowledge graph and high-dimensional vector corresponding to each reference document to construct a knowledge base; receiving a report to be reviewed; on the one hand, comparing the similarity between the retrieval vector of the report to be reviewed and the high-dimensional vector of the knowledge base to retrieve highly relevant reference documents from the knowledge base; on the other hand, selecting highly relevant subgraphs from the knowledge graph based on the entities in the report to be reviewed; fusing the highly relevant reference documents and highly relevant subgraphs to form structured knowledge, and generating structured prompts based on the structured knowledge; and outputting the compliance review results of the report to be reviewed based on the structured prompts and structured knowledge. This invention can significantly improve the efficiency, accuracy, and interpretability of software testing compliance review.

The invention relates to the technical field of network security, and discloses a social robot collaborative group detection method based on a multi-order collaborative knowledge graph. According to the method, user data in a Chinese social platform is collected through a crawler, a multi-order collaborative interaction graph is constructed based on the interaction relation of users of the social platform and then input into a graph encoder module, node feature vectors are obtained and input into a time perception module and a graph perception module respectively, and a time sequence prediction task and a side link prediction task are executed. Meanwhile, the model is constructed based on a time-graph semantic consistency perception module of a self-attention mechanism. And finally, inputting a node feature vector obtained by training under the guidance of double tasks into a group detection module constructed based on a Gaussian mixture model and a K-means clustering method for detection. According to the method, the complex interaction relationship among the users in the social robot group and the abnormal mode in the time sequence activity can be effectively captured, and efficient detection of the social robot collaborative group in the social network platform is realized.

This invention discloses a method, apparatus, and non-volatile storage medium for generating attack paths. The method includes: acquiring attack information, wherein the attack information includes an attack target, an attack object, a vulnerability, and an attack result; constructing a task model based on the attack information; constructing multiple collaborative knowledge graphs based on preset semantic anchors; retrieving the multiple collaborative knowledge graphs according to the task model to construct a task subgraph; querying attack paths in the task subgraph according to the attack target to obtain candidate paths; calculating the scores corresponding to the candidate paths; and selecting candidate paths whose scores meet preset conditions as the target attack path. This invention solves the technical problem that existing AI attack path generation methods rely on static graphs, lack real-time environmental feedback and dynamic replanning capabilities, resulting in generated attack paths that cannot respond to execution deviations, alarm triggers, or asset changes, lack a closed-loop feedback mechanism, and cannot dynamically replan or adaptively repair.

The invention relates to the technical field of knowledge viewpoint classification, in particular to a feature custom weight enhancement-based viewpoint classification method and system. Comprising the following steps: S1, collecting viewpoint text data; s2, preprocessing the collected data, and extracting key feature words; s3, carrying out vector representation on the key feature words by adopting Word2Vec; s4, a TF-IDF superposition enhancement weight algorithm is used for the vectorized key feature words; and S5, constructing a viewpoint classifier by adopting a machine learning algorithm model, and verifying the effect of extracting the key feature words in classification. The machine learning-driven online collaborative knowledge construction viewpoint classification method comprising six links is designed, the Word2Vec is adopted to carry out vector representation on feature words, the SMOTE oversampling technology is adopted to solve the problem of sample size imbalance, four machine learning algorithm models are adopted to construct a viewpoint classifier, and particularly, the viewpoint classifier is used for distinguishing the importance of different features. According to the method, the superposition enhancement weight algorithm is customized based on the TF-IDF, and the accuracy of machine learning viewpoint classification is improved.

The application discloses a method and device for constructing a multi-level power field knowledge base, and relates to the field of artificial intelligence, and aims to improve the field knowledge base constructed based on the existing method, which is not good for improving the reliability of large language model application. The method comprises the following steps: separating text and images from original data to obtain field knowledge original text and field knowledge original images; performing adaptive semantic text block segmentation on the original text to construct a semantic text block knowledge base; performing double-channel collaborative knowledge extraction on the text blocks, and fusing the extraction results to construct a knowledge graph knowledge base; performing adaptive text description generation on the field knowledge original images to construct an image and text description knowledge base; performing vector conversion and mapping alignment on the combination of the field knowledge text blocks, the knowledge graph triples, the field knowledge original images and the corresponding text descriptions to construct a semantic vector knowledge base; and constructing a multi-level field knowledge base based on the above multiple knowledge bases.

The application discloses an industrial intelligent agent system and method fusing digital twin and a four-element core, belongs to the field of artificial intelligence, and comprises a digital twin perception layer, a four-element fusion core layer, a hybrid reasoning engine and an interpretable report generator.The digital twin perception layer is used for acquiring real-time state data of a physical entity; the four-element fusion core layer integrates OWL ontology modeling, graph database storage, large language model interaction and multi-physical field agent model, and generates a four-element collaborative knowledge processing result; the hybrid reasoning engine performs parallel rule reasoning, graph algorithm mining, large language model reasoning and agent model reasoning and fuses to generate a comprehensive reasoning conclusion; and the interpretable report generator generates a multi-modal report containing a reasoning path and physical evidence.The application realizes interpretable tracing of a decision-making process through four-element collaboration, realizes millisecond-level physical quantity prediction through an agent model, realizes continuous evolution of knowledge through a dynamic evolution module, and significantly improves the reliability, real-time performance and adaptability of an industrial intelligent system.

The application discloses a personalized recommendation method based on interactive bipartite graph reconstruction neighborhood, comprising the following steps: counting the interaction information of users to items and the attribute information of items, constructing a user-item bipartite graph, a knowledge graph and a collaborative knowledge graph; randomly sampling a collaborative path for each user on the interactive bipartite graph; calculating the average item popularity of each collaborative path of each user, and selecting all item nodes in the X paths with the lowest average item popularity to replace the original first-order neighbors of the user; inputting the embedding of the reconstructed first-order neighbors of all users into a self-attention layer; generating attention weights based on the relationship between each node and neighbor nodes, and aggregating neighbor node information; and predicting a recommendation score. The beneficial effects are that the recommendation method can effectively reduce the influence of popular items on the recommendation result, improve the diversity of the recommendation while maintaining the accuracy of the recommendation system.

The application relates to the technical field of knowledge graphs, and discloses a reasoning method for semantic association and logical rules based on a knowledge graph, which comprises the following steps: acquiring a first data set across functional departments, and constructing a cross-department knowledge graph; extracting index nodes from the cross-department knowledge graph, identifying semantic conflict indexes, generating an index semantic conflict list, and constructing a cross-department knowledge graph after semantic mapping based on the index semantic conflict list; acquiring a second data set across functional departments, obtaining a fused cross-department knowledge graph and a semantic association degree matrix based on the second data set and the cross-department knowledge graph after semantic mapping; dynamically adjusting the weights of each node and edge of the fused cross-department knowledge graph according to the semantic association degree matrix, and generating a cross-department collaborative knowledge graph; and generating cross-department collaborative decision-making suggestions based on the cross-department collaborative knowledge graph; and the application significantly improves the efficiency and quality of cross-department collaborative decision-making.

A use case knowledge base is collaboratively developed by receiving language input from a user, featurizing it into language elements, extracting predicate sets that are missing a predicate head or a predicate argument, querying users for input regarding the missing predicate information, and updating the knowledge base with predicate sets and other information provided by the users.

To promote knowledge accumulation by increasing the incentive of a knowledge provider.SOLUTION: This knowledge storage support system collects knowledge from a knowledge provider, and determines whether the received knowledge is useful knowledge based on similarity between the received knowledge and the stored useful knowledge. The knowledge-based collaborative system calculates, for each knowledge provider, a royalty to the knowledge provider based on the number of pieces of useful knowledge provided by the knowledge provider.SELECTED DRAWING: Figure 1

The invention discloses a heterogeneous federated learning method and system based on personalized collaborative generation, belongs to the technical field of crossing of federated learning and generative models, and aims to solve the core problems of coexistence of data and model heterogeneity, dependence on a common data set and poor undersampling learning effect in existing federated learning. According to the method, efficient and privacy-protected personalized training is realized through a two-stage collaborative framework, each client trains a conditional variation auto-encoder to capture local data distribution, and a priori distribution offset mechanism of privacy enhancement is adopted; in addition, a uniform feature representation space is constructed by selecting a lens space similarity graph through a reference encoder, cross-model knowledge migration and under-sampling type pertinence enhancement are realized by combining collaborative knowledge updating, matching of auxiliary generators driven by class recognition capability and self-adaptive synthetic sample generation, and finally, a local model is optimized by adopting mixed loss. The method does not need to depend on a public data set, takes performance, privacy and deployment flexibility into consideration, and is suitable for privacy sensitive fields such as edge device cooperative training, medical treatment and finance.

The invention discloses an AI intelligent agent system and a collaborative knowledge construction method. The method comprises the steps that communication data are collected in real time and preprocessed; constructing an intelligent agent role library; dialogue situation analysis and intelligent agent role switching are carried out; designing an intelligent reasoning driving decision-making method, and carrying out interaction mode decision-making and execution; building a domain knowledge base based on knowledge extraction of domain knowledge enhancement RAG and a graph; performing knowledge synthesis and visual output; the AI agent system comprises a data acquisition module, a situation analysis engine, a core processing unit, an interactive output module and a user feedback interface. According to the method, real-time analysis, knowledge extraction, conflict identification and process assistance of communication in the team collaborative knowledge construction process can be realized, and the efficiency and quality of team collaborative knowledge construction are remarkably improved.

The invention discloses a collaborative knowledge tracking method based on difficulty perception, and belongs to the technical field of knowledge tracking. The method comprises the steps that difficulty parameters of all questions in historical answering data of students are acquired, and standardization processing is carried out on the difficulty parameters; based on historical answers and difficulty information of the students, difficulty perception behavior characteristics are constructed; the similarity between the target student and other students is calculated, and students similar to the target student in difficulty perception behavior characteristics are screened out; collaborative information screening is carried out according to the answer data of the similar students and the difficulty information of the target questions; and predicting the learning state of the target student based on the screened collaborative information. The method is clear in process and easy to implement, can be directly deployed in an existing online learning system, and improves the overall performance of knowledge state prediction on the premise of not increasing extra hardware cost.

The invention provides a sewage treatment parameter prediction method based on plant group collaborative knowledge migration, which comprises the following steps: considering parameters in three aspects of water quality state, environment state and operation state of a target plant and a source domain plant, establishing a corresponding similarity model, screening out a final source domain plant according to a similarity value, and predicting the sewage treatment parameter according to the final source domain plant. Training a parameter prediction model by using the screened source domain factory data as a pre-training model; afterwards, the pre-training model is migrated to a target plant, and transfer learning training is carried out on the pre-training model through a small amount of historical data of the target plant, so that the suitability of the parameter prediction model and the actual state of the target plant can be effectively ensured, and the final prediction precision of the prediction model is ensured.

The invention discloses an edge analysis early warning method and device for power grid equipment installation data, and relates to the technical field of power grid equipment installation data processing, and the method comprises the steps: collecting multi-source heterogeneous original data, analyzing the data type, and distributing the data to a corresponding preprocessing channel for adaptive preprocessing; and obtaining the current real-time computing power load of each node to perform grading lightweight processing, loading the data analysis model and the early warning rule base according to the type of lightweight data, and performing real-time analysis and risk early warning. Different types of data can be subjected to differentiated self-adaptive cleaning, dynamic lightweight adaptation is performed according to the computing power load, the original features of the data are reserved to the maximum extent, and the real-time performance and accuracy of risk early warning are ensured. The system can be well adapted to multiple link installation construction sites of various power grid devices, and can timely find low-quality data to ensure the stability and reliability of data analysis. The cloud-edge collaborative knowledge update enables the edge computing nodes to be globally and continuously evolved, and the defect of model solidification is overcome.

The invention provides a stability monitoring method and system for bridge swivel construction, belongs to the field of bridge construction monitoring, and is used for solving the problems of long adaptation period, poor real-time working condition response and inaccurate risk early warning of a single bridge swivel project monitoring model in related technologies. The scheme comprises four core support systems of data acquisition, local calculation, cloud collaboration and communication transmission, a global collaborative knowledge model is constructed through multi-project parameter weighted aggregation, model parameters are optimized through a self-organizing evolutionary optimization algorithm, and dynamic weight and Bayesian parameter collaborative calculation is performed, so that efficient processing of monitoring data and dynamic adaptation of the model are realized. The model adaptation period can be shortened, the monitoring real-time performance and the risk pre-judgment precision are improved, and the bridge swivel construction stability is guaranteed.

The application discloses an AI intelligent agent system and a collaborative knowledge construction method, which comprises the following steps: collecting communication data in real time and preprocessing; constructing an intelligent agent role library; analyzing a dialogue context and switching an intelligent agent role; designing an intelligent reasoning driven decision method, making an interactive mode decision and execution; based on field knowledge, enhancing the knowledge extraction and graph construction field knowledge base of RAG; knowledge synthesis and visual output; the AI intelligent agent system comprises a data acquisition module, a context analysis engine, a core processing unit, an interactive output module and a user feedback interface. The application can realize real-time analysis of communication, knowledge refinement, conflict identification and process assistance in the team collaborative knowledge construction process, and significantly improves the efficiency and quality of team collaborative knowledge construction.

The invention discloses an enterprise information collaborative management method and system based on multi-source data fusion, and relates to the technical field of collaborative management, and the method comprises the steps: firstly carrying out the full-modal serialization and context reconstruction of a heterogeneous data stream containing orders and work orders, and converting a discrete form into a serialized context with semantic association; then, extracting a business rule as system-level constraint injection, and guiding the large language model to mine a structural relation of cross-domain data under a rule framework; and then, performing logic verification and deterministic alignment on a reasoning result by using a dual-gating threshold, and eliminating semantic ambiguity. Based on this, super node fusion and attribute aggregation are performed on the initial graph, and a collaborative knowledge graph mapping global business logic is constructed. And finally, through graph traversal and sub-graph mode matching, analyzing long link dependence and generating a cooperation instruction. In this way, the entity alignment precision in a complex environment can be effectively improved, and intelligence and automation of enterprise information collaborative management are achieved.

The application provides a power distribution room state evaluation and early warning method based on digital twinning and edge intelligence, first, a three-dimensional high-fidelity digital twinning model embedded with physical information constraints is constructed to ensure that the evolution process conforms to the physical law. Secondly, through cloud edge collaborative knowledge distillation, the cloud large model is compressed into a lightweight graph neural network-attention fusion model and deployed on the edge side to realize real-time feature extraction of multi-source data. Thirdly, a diffusion-adversarial hybrid anomaly generator is designed, and the residual generator is trained under the condition of no fault label to realize high sensitivity detection of early latent anomalies. Finally, combined with the causal inference engine, the abnormal area is automatically located and the fault path is inverted, and the visual operation and maintenance guidance is realized through the augmented reality terminal. The method significantly improves the early fault identification accuracy and decision-making interpretability.

The invention provides a multi-expert collaborative knowledge tracking method and system for cognitive strategy perception, and relates to the technical field of knowledge tracking, and the method comprises the steps: building a memory consolidation expert module through combining a knowledge obtaining process with a forgetting gate and absorptivity parameters, building an attention regulation expert module through combining attention distribution of knowledge points with a time attention mechanism, and building a memory consolidation expert module; creating a structure adaptation expert module based on a correlation evolution process between knowledge points; generating a global memory matrix by combining an attention mechanism based on the long-term memory of the historical cognitive state of the student and the current interaction embedded information, and determining a corresponding expert weight; performing weighted fusion on knowledge state parameters generated by the memory consolidation expert module, the attention regulation and control expert module and the structure adaptation expert module on the basis of expert weights, splicing the obtained fused knowledge state parameters and feature embedding vectors of test questions to be predicted, and inputting the spliced information to a preset feedforward neural network, and obtaining the answer accuracy corresponding to the test question to be predicted.

A multi-UAV collaborative decision-making method based on key pattern mining and dynamic knowledge guidance is proposed. This method constructs a closed-loop collaborative evolution framework for key pattern mining and policy learning, uses Allen interval algebra to define temporal relationships between events, stores interaction trajectories using a two-pointer cross-linked list data structure, and combines time-constrained anti-monotonic pruning and predecessor dominance pruning strategies to extract high-frequency key patterns that satisfy minimum support and temporal deviation thresholds. Finally, a unit collaborative knowledge matrix is ​​obtained by fusing co-occurrence frequency and temporal density through Hadamard product. This invention achieves a dynamic mapping of temporal collaborative knowledge from historical data to online decision-making. Simultaneously, a time-constrained frequent event permutation mining algorithm and an exponential moving average update mechanism ensure that the extracted key patterns possess both temporal causal authenticity and environmental adaptability.

The application discloses a course recommendation method based on fine-grained interaction and a knowledge graph, which comprises collecting interaction behaviors of a user on an education platform, obtaining learning records of the user; constructing a knowledge graph G; and obtaining a knowledge unit network of a course according to the knowledge graph, analyzing the learning records of the user, and respectively obtaining a collaborative knowledge unit network set of the user and the course; extracting the general preference and the detailed preference of the user for the course, and generating an individualized course recommendation list based on the two preferences; the application is based on fine-grained interaction and a knowledge graph, provides additional information for a recommendation algorithm by means of rich semantic information of the knowledge graph, supplements collaborative information for the course by using a collaborative course set, and supplements interaction information of the user and a video into interaction information of the user and the course, so that the application not only can distinguish the difference between users of different videos that have interacted with the same course, but also can improve the recommendation performance.

This invention discloses a cloud-edge collaborative knowledge graph defense method for cyber-physical systems. The method includes: addressing the difficulty in effectively integrating real-time physical state, traffic data, and non-real-time threat intelligence, as well as the limitations of cloud-edge resources, by constructing a domain ontology model under a cloud-edge collaborative architecture; on the edge side, analyzing industrial protocols and traffic based on a fingerprint database distributed from the cloud, dynamically constructing a local knowledge graph containing network behavior and physical state characteristics, performing hierarchical lifecycle management based on asset importance, and utilizing a lightweight model to achieve anomaly detection and selective reporting; on the cloud side, integrating multi-source security intelligence and edge-side graph physical topology using a large domain model to construct a global knowledge graph, and performing consistency judgment on anomalies based on physical constraints; finally, generating defense and handling suggestions based on graph retrieval enhancements. This method balances real-time performance with global correlation analysis capabilities, effectively improving the cyber-physical system's ability to perceive and defend against complex cross-domain attacks.

A knowledge base is developed by receiving language input from a source, vectorizing it, extracting an incomplete predicate set, querying another source for input regarding the missing part of the predicate set, and storing a complete predicate set.