27 results about "Semantic Web" patented technology

The invention discloses a microblog emotion analysis method based on standard dictionaries and semantic rules. The microblog emotion analysis method comprises the following steps: collecting microblog data and manually labeling and marking the emotion value of each microblog; proposing corresponding standard micrblog emotion dictionaries, and establishing an emotion dictionary database; based on the standard emotion dictionaries, adding the semantic rules for assistance, and performing parameter adjustment and optimization on parameters of the semantic rules; based on a real dataset experiment, acquiring the final classification accuracy and precision. The technical scheme provided by the invention is adopted to well analyze the emotion tendency of each microblog user by introducing the standard emotion dictionaries, microblog expression dictionaries and the semantic rules, therefore, higher classification accuracy and precision are achieved.

The invention relates to a knowledge graph data intelligent management method and system based on a semantic web technology, and the method comprises the steps: obtaining text data from a high-frequency data flow in real time, and generating a first semantic set through segmentation processing and semantic extraction; performing noise filtering and sorting on the multi-source data to generate a second semantic set; constructing semantic representation compatible with the knowledge graph; utilizing a graph embedding algorithm to generate graph updating data through source weight optimization; based on a historical conflict mode and a credibility weighting model, intelligent resolution of semantic conflicts is completed; and generating dynamic situation awareness data through real-time incremental loading and multi-dimensional association analysis. According to the method, through time sequence priority dynamic weighting, multi-source noise accurate filtering and cross-modal credibility evaluation, the problems of response lag, redundancy accumulation and insufficient conflict resolution during high-frequency dynamic data processing of a traditional method can be solved, and therefore real-time updating and consistency maintenance of the knowledge graph are achieved.

The invention relates to the technical field of data management, in particular to a data weaving semantic integration method based on a semantic network and a knowledge graph, which comprises the following steps: acquiring multi-source heterogeneous data and preprocessing to obtain standardized data, the multi-source heterogeneous data comprises structured data, semi-structured data and unstructured data from different business scenes; performing rule injection on the standardized data to generate semantic web ontology data; extracting entities and attribute values thereof in the standardized data to generate structured knowledge graph data of the instance layer; and establishing a semantic association mapping network of the semantic network ontology data and the structured knowledge graph data, and generating a semantic integration result of data weaving. According to the method, the basic differences of the multi-source data in the aspects of formats, codes and the like are eliminated, a unified semantic standard is provided, and conflicts caused by non-unified semantics are reduced.

The invention relates to the technical field of artificial intelligence, and discloses a smart city monitoring management method based on artificial intelligence, comprising the following steps: step A: data acquisition and preprocessing: acquiring data related to city operation from a plurality of heterogeneous data sources; step B, cross-domain data fusion: carrying out feature extraction and fusion on the preprocessed data; c, performing intelligent analysis and prediction, and applying a machine learning algorithm; and step D, decision support and response: transmitting an analysis result and prediction and early warning information to urban managers and related departments through the system. By introducing an artificial intelligence technology, a deep learning model, a transfer learning technology and a semantic web technology or ontology method, the problem of cross-domain data fusion is effectively solved. The methods can process and analyze heterogeneous data from different data sources and convert the data into a unified and comparable format, so that seamless joint and integration of cross-domain data are realized.

This invention relates to the field of aero-engine digitization, and discloses a systematic multi-dimensional digital representation method and system for aero-engines. The method involves decomposing the component structure of an aero-engine hierarchically to form an engine product decomposition structure. Based on the product hierarchy and inclusion relationships of this decomposition structure, a multi-dimensional representation framework for the aero-engine is constructed. Feature factors for each dimension are obtained by extracting associated features from the models or data derived from each dimension. Using these extracted feature factors as variable ontologies, semantic web technology is employed to form a skeleton variable map with these feature factors as its framework. Data is dynamically input into the skeleton variable map to form an aero-engine representation space based on this map. Machine learning algorithms are used to perform representation traversal calculations and analyses on the aero-engine representation space to obtain the representation traversal calculation and analysis results. This method solves the representation challenges of existing representation technologies for complex systems like aero-engines.

The present application relates to a large-scale noise semantic graph entity type error detection method, belonging to the computer technical field. The method comprises the following steps: S1: reasoning and perfecting the noise semantic graph based on the semantic net standard, completing the entity type not explicitly declared in the semantic graph through reasoning, and obtaining the finest type of all entities; S2: entity type error detection based on node semantic embedding and anomaly detection; S3: distribution statistics of semantic graph type-attribute; S4: entity type error detection based on fact triple linkage, and finally obtaining the semantic graph entity type error result.

The application discloses a kind of offshore task planning and deduction simulation analysis method, and the knowledge data of war knowledge base is set war ontology knowledge base, and the model based on event ontology is designed in combination with ontology modeling language, the class of sea battlefield event ontology and the hierarchical structure setting of class are determined, and the sea battlefield rule file model is established to describe sea battlefield combat event, and the sea battlefield combat rule of the sea battlefield rule file model is obtained based on war semantic net rule;Sea battlefield combat rule is inferred according to BN reasoning engine module to obtain the execution event of sea battlefield combat rule;And the execution event is visualized by man-machine interactive system, and the expression of battlefield combat rule based on offshore task planning and deduction simulation is realized.

The application discloses a kind of cement-steel slag solidified soil sustainable evaluation method based on ontology, including setting cement-steel slag solidified soil basic data, according to the evaluation index of cement-steel slag solidified soil of basic data setting;According to the multiple classes corresponding to the attribute of the multiple classes of the ontology model defined by evaluation index definition;The evaluation index evaluation reasoning rule of cement-steel slag solidified soil is formulated using semantic web rule, and the semantic web query rule is defined according to the evaluation index evaluation reasoning rule, according to the parameter corresponding to basic data, the multiple classes are assigned, according to the multiple classes after assignment and the attribute corresponding to the multiple classes and the evaluation index evaluation reasoning rule of cement-steel slag solidified soil, obtain the influence of the basic data to be evaluated on the sustainability of solidified soil.By ontology model and semantic web rule language combination, the inference result is obtained by quantifying evaluation index, the optimal design and optimization direction are obtained from macroscopic point of view, which is conducive to improving the work efficiency of designer.

This invention claims protection for an intelligent fault diagnosis method for rotating machinery based on semantics and capsule networks. The algorithm is implemented using the Keras deep learning framework and semantic web technology, and includes the following steps: Step 1: Preprocessing the original acceleration signal to input into a pre-constructed convolutional layer for automatic feature learning; Step 2: Introducing an Inception module into the capsule network to extract feature representations at multiple scales, preserving the spatial pose information of the features to the greatest extent; Step 3: Constructing and introducing a low-level capsule layer based on weight sharing to share the affine transformation matrix, obtaining predicted feature vectors, and then weighted summing them before inputting them into a high-level capsule layer; Step 4: Introducing a protocol-based dynamic routing algorithm into the high-level capsule layer for iterative weight updates; Step 5: Using rule-based reasoning based on Prolog+Lisp, leveraging existing knowledge in the rotating machinery knowledge domain ontology and the results of IWSCN predictions, to infer the cause of the fault, improving the level of diagnostic intelligence.

The application discloses a cross-endpoint associated path retrieval method and system driven by RDF class relation, and belongs to the technical field of semantic web data association. The application carries out preprocessing on data in a SPARQL endpoint, extracts RDF class relation from an ontology and entity relation; the extracted RDF class relation is stored in a graph database in the form of graph data; when a user carries out relation query between entities, inputs a retrieval word and selects a data source; the entity URI of the retrieval word is determined, the entity URI is parsed to determine the class to which the entity belongs, and the associated path of the class is queried in the graph database; the associated path information between the classes that are queried is dynamically encapsulated into a SPARQL federated query statement; the SPARQL federated query statement is executed, and the associated path result of the query is dynamically visualized and displayed. The application can retrieve the associated path between entities across SPARQL endpoints, supports multiple data source endpoints and any associated direction, and improves the efficiency and quality of cross-endpoint associated path retrieval.

This invention relates to a heterogeneous ontology matching method and system based on BERT and graph contrastive learning, belonging to the field of semantic web and deep learning integration. The invention constructs a corpus by extracting triple information from the ontology using a semantic feature extraction module. This corpus is then input into a BERT model for parameter fine-tuning, generating semantic feature vectors for entities. A graph contrastive learning module performs graph sampling based on the topological structure of the ontology graph, generating two views. Training is performed by selecting positive and negative samples and setting a loss function to generate a comprehensive entity feature vector. Finally, a similarity calculation module calculates the final similarity score for different entity pairs. This invention effectively utilizes the topological structure of the ontology graph to extract structural features, overcoming the problem that traditional structural features cannot fully express the complex structural relationships between entities, thus improving matching accuracy.

The invention provides an equipment fault prediction method and equipment based on a power grid equipment semantic network. According to the implementation scheme, under the condition that the operation state of target power grid equipment is abnormal, attribute information of a corresponding entity node in a first power grid equipment semantic net is updated based on the operation state of the target power grid equipment; under the condition that attribute information of a first entity node in the first power grid equipment semantic network is updated, based on a rule edge connected with the first entity node, in the first power grid equipment semantic network, changing a connection relationship between the rule edge and a second entity node associated with the first entity node to obtain a second power grid equipment semantic network; determining an influence subgraph of the target power grid equipment from the second power grid equipment semantic network; and performing fault analysis on the influence subgraph of the target power grid equipment to obtain a fault influence range of the target power grid equipment. According to the invention, the accuracy of the fault influence range of the power grid equipment can be improved.

The invention discloses a cooperative override trip prevention decision-making system for a power supply network, and relates to the technical field of power system protection and control, and the system comprises a data collection module which is connected with a multi-level protection device, a monitoring terminal and an environment sensor in the power supply network, and is used for obtaining electrical quantity data, non-electrical quantity data and environment parameters in real time. According to the cooperative override trip prevention decision-making system for the power supply network, cross-protocol analysis and space-time fusion of multi-source heterogeneous data are realized through a multi-dimensional space-time alignment engine, a dynamic semantic gateway and a wavelet packet decomposition technology are combined, a power frequency quantity, a transient quantity and an environmental parameter are uniformly mapped to a fault characteristic spectrum, and the fault characteristic spectrum is analyzed and analyzed. The problem of incomplete fault feature extraction caused by data islands in the prior art is solved, key fault features can be accurately screened, the Pareto optimal action sequence can be generated, the misjudgment rate of override trip is reduced, meanwhile, the unnecessary power failure duration is shortened, and the fault isolation accuracy and the power supply reliability are improved.

The invention provides a geographic semantic web spatio-temporal knowledge extraction method, which belongs to the technical field of data processing, and specifically comprises the following steps: acquiring multi-source geographic semantic web data, and performing data type judgment and data field automatic analysis on the multi-source geographic semantic web data; constructing a geographic semantic network to extract an ontology, and performing self-adaptive matching on an ontology field and a data field obtained by analysis; the method comprises the following steps: constructing a GeoSemanticWeb2Knowledge extraction framework, operating the GeoSemanticWeb2Knowledge extraction framework, and carrying out adaptive knowledge extraction on multi-source geographic semantic network data; constructing a spatial screening constraint condition, and performing spatial screening on the spatio-temporal knowledge triad; constructing a topic screening mechanism based on semantic similarity matching, and carrying out topic screening on the spatio-temporal knowledge triad according to the topic screening mechanism; and carrying out space-time knowledge dynamic reasoning and updating based on evolution mode driving. Through the scheme of the invention, the extraction efficiency, accuracy and interpretability are improved.

The invention provides a complex multivariate combination model comprehensive element intelligent extraction and recombination publishing method, and relates to the field of system comprehensive modeling simulation. The complex multivariate combination model comprehensive element intelligent extraction and recombination publishing method is realized through the following technical steps: step 1, preparing and preprocessing multi-source model data, analyzing a *. Mo file of a target system through a Modelica compiler, and generating an AST syntax tree containing component declarations and equation sets; and importing STEP format geometric data of the CAD model, and carrying out grid repair and feature edge extraction by using Paraview. According to the method, a lightweight digital fingerprint algorithm oriented to multi-source heterogeneous data is developed, while encryption strength is kept, feature extraction time of a gigabit-level CAD model is shortened to be within 30 seconds, an interpretable intelligent confirmation framework is constructed, a model element feature map is constructed, a technical barrier is broken through, a model element association rule base based on a semantic network is developed, and a multi-source heterogeneous data encryption algorithm is developed. And automatic binding and intelligent extraction of the geometric parameters and the multi-physical field equation are realized.

The application provides a geospatial semantic web spatio-temporal knowledge extraction method, and belongs to the technical field of data processing, and specifically comprises the following steps: acquiring multi-source geospatial semantic web data, and performing data type judgment and automatic data field analysis on the data; constructing a geospatial semantic web extraction ontology, and adaptively matching the ontology field with the analyzed data field; constructing a GeoSemanticWeb2Knowledge extraction framework and running the framework to adaptively extract knowledge from the multi-source geospatial semantic web data; constructing a spatial filtering constraint condition to perform spatial filtering on the spatio-temporal knowledge triple; constructing a topic filtering mechanism based on semantic similarity matching to perform topic filtering on the spatio-temporal knowledge triple; and performing spatio-temporal knowledge dynamic reasoning and updating based on an evolution mode. Through the scheme, the extraction efficiency, accuracy and interpretability are improved.

This invention aims to propose a proactive data collection method based on semantic expansion. Initial keywords describing the topic are set. The keywords are then used to identify corresponding initial entities in the semantic web. These initial entities are then expanded using upward and downward expansion methods to obtain several new entities. A classification model is then constructed and used to predict the probability of each new entity being recommended as a relevant entity. The relevance weight of each new entity is calculated and ranked from high to low. The new entities with the highest scores are selected as relevant entities. This process is repeated to obtain more relevant entities describing the topic and their scores. This method can effectively semantically expand the initial keywords.

The invention provides a cognitive path cross-space tracking and visualization method based on a DIKWP * DIKWP semantic network interaction structure, which is characterized in that a semantic interaction network is constructed between a source model and a target model on the basis of a data-information-knowledge-intelligence-intention five-layer model, and hierarchical mapping and alignment of cognitive contents are realized. According to the method, AI reasoning activities are synchronously tracked in concept and semantic spaces, paths from input to output are recorded as cross-layer sequences, and abnormal behaviors such as skip reasoning, semantic fold-back and intention distortion are detected. When the model faces an unclear, uncertain and inconsistent situation, the deviation type and degree can be marked and explained. A matched visualization module visually displays a cognitive path through a multi-dimensional atlas, wherein a thermodynamic diagram shows attention, a broken line marks a process, abnormal nodes are highlighted, and target consistency is analyzed and evaluated by intention. The method can be applied to white-box evaluation, multi-model comparison, semantic consistency detection and AI ethical monitoring, the interpretability, transparency and safety controllability of an AI system are improved, and the method has important application value.

The application relates to the technical field of data governance, in particular to a data weaving semantic integration method based on a semantic network and a knowledge graph, which comprises the following steps: obtaining multi-source heterogeneous data and preprocessing the multi-source heterogeneous data to obtain standardized data, wherein the multi-source heterogeneous data comprises structured data, semi-structured data and unstructured data from different business scenes; performing rule injection on the standardized data to generate semantic network ontology data; extracting entities and attribute values in the standardized data to generate structured knowledge graph data at an instance layer; and establishing a semantic association mapping network of the semantic network ontology data and the structured knowledge graph data to generate a semantic integration result of data weaving. The application eliminates the basic differences of multi-source data in aspects such as formats and encodings, provides a unified semantic standard, and reduces conflicts caused by non-uniform semantics.

Described herein relates to a system and method that supports the creation and execution of collaborative intelligent agents to process machine-readable data into dynamic and / or related outputs. As such, the collaborative intelligent agent system and / or methods thereof may include a compiler to generate an executable expression tree, an executor to manage intelligent agent execution using the expression tree, and / or a processor to manage intelligent agent collaboration during execution. Additionally, using machine-readable inputs, the collaborative intelligent agent system and / or methods thereof may automatically execute the collaborative intelligent agents to dynamically induce outputs, without requiring user interaction. As such, the collaborative intelligent agent system and / or methods thereof may also be configured to realize the second pillar of the Semantic Web and / or may improve upon HTML or machine-readable code only, providing a mechanism to automatically produce dynamic outputs based on input data.

The invention discloses a relation graph constraint-based composite agent communication method, which relates to the technical field of artificial intelligence, and comprises the following steps of: constructing a relation graph through an OWL language and a semantic web specification RDF; constructing and registering a composite agent group of the main control agent and the sub-agents based on the relation graph; after receiving an external task request, the main control agent completes sub-task decomposition and distribution through the sub-agents; a communication request is initiated between the sub-agents, two-way identity verification is completed through the main control agent, verification is performed based on the relation graph, and after verification is passed, the sub-agents execute sub-tasks and feed back results; and if the sub-agents fail, information is reported to the main control agent, and the main control agent allocates tasks again after identity verification. According to the method provided by the invention, the global unique identity identifier is configured for the agent node in the relation graph, so that cross-organization and cross-numeric-domain identity unified management and control are realized, and the problems of identity fragmentation and data inconsistency in the prior art are solved.

The present invention belongs to the field in which a semantic web and deep learning are combined. The present invention relates to a heterogeneous ontology matching method and system based on BERT and graph contrastive learning. In the present invention, a semantic feature extraction module extracts internal triple information of an ontology to construct a corpus; the corpus is input into a BERT model for parameter fine-tuning, and the fine-tuned BERT model is used to generate a semantic feature vector of an entity; and then, a graph contrastive learning module executes graph sampling on the basis of a topological structure of an ontology graph, so as to generate two views. Training is implemented by selecting positive samples and negative samples and setting a loss function, so as to generate a comprehensive entity feature vector; and finally, a similarity calculation module is used to calculate final similarity scores of different entity pairs. The present invention can effectively use a topological structure of an ontology graph to extract structural features, so as to overcome the problem of traditional structural features being incapable of fully expressing complex structural relationships between entities, thereby improving the accuracy of matching.

This invention discloses a method for constructing, querying, and maintaining a time-bucket-based dual-temporal RDF block list index, belonging to the field of semantic web temporal data management technology. The invention first performs dictionary encoding, timestamp standardization conversion, and differential encoding compression on the dual-temporal RDF quintuples; then, it dynamically determines the time bucket granularity through a sliding window to achieve balanced partitioning of temporal data and eliminate empty buckets; it constructs a two-layer auxiliary index of existing bitmaps and changing bitmaps to achieve fast query pruning and block acceleration; based on the bitmap, it constructs a three-layer temporal block list core index adapted to SPO / POS / OSP modes; it uses a localization strategy to complete index addition, deletion, modification, and maintenance, and during queries, it achieves precise retrieval through time bucket pruning, bitmap filtering, and block list. This invention supports queries in all scenarios including no temporality, single temporality, and dual temporality, with dual-temporal path query time consistently below 5ms. It has advantages such as efficient index construction, low maintenance cost, strong data adaptability, and standardized temporal expression, making it suitable for efficient storage and query management of large-scale dual-temporal RDF data.

The invention relates to the technical field of semantic fusion, in particular to a term intelligent gateway system and method based on dynamic embedding, and the system comprises a term mining module, a dynamic embedding module, a dynamic increment fine tuning module and a semantic gateway module. The method has the advantages that the problem of intention recognition failure caused by term lag of a traditional NLP system is effectively solved, and the cold start period is shortened; the service demand response speed is reduced from the hour level to the minute level, and the combined service development efficiency is improved; the manual operation and maintenance cost is reduced, the model iteration period is compressed from the day level to the hour level, and zero-intervention evolution of the model is achieved; the semantic understanding accuracy (especially in scenes such as package recommendation) is improved, and the long-tail problem solving rate is improved.

The invention discloses an enterprise order management method and device based on an internet platform and a medium, and relates to the technical field of order management, and the method comprises the steps: receiving a natural language order demand text inputted by a user through an order management platform; performing semantic analysis on the natural language order demand text, extracting entities and intentions, and generating an initial demand semantic network based on the industrial knowledge graph; based on the initial demand semantic network, generating and presenting a clarified question sentence to the user; matching the updated demand semantic network with a resource knowledge base in real time, and calculating and generating a plurality of visual performance paths; and receiving a selection instruction of selecting the visual performance path by the user, and generating a structured enterprise order based on the selection instruction and the updated demand semantic network. According to the invention, through deep combination of natural language semantic analysis and the industrial knowledge graph, the identification precision and the structuring efficiency of enterprise order demands are significantly improved.

Systems and methods enable an entity to certify a web page address as being linked to the entity. The web page address includes semantic web mark-up identified attributes for the entity. A system may extract the attributes from the web page for the entity and use the attributes to generate an information card for the entity. The certification process ensures that the attributes are accurate, so that information cards generated for the entity are of high quality and reliable. Implementations may also simplify maintenance and quality assurances processes for an entity repository.

The invention provides a system model conversion method and system based on a semantic network, and belongs to the field of digital engineering.The method comprises the steps that S1, system model elements are determined according to SysML modeling language and system modeling specifications; s2, using an ontology definition language OWL2 of a semantic web to define ontology elements; s3, defining conversion rules of system model elements and ontology elements; and S4, converting the system model elements into the OWL2 model according to the conversion rule. According to the method, display definition is carried out on SysML model elements through an OWL2 ontology definition language, interoperation between the SysML model and other professional models can be enhanced in the digital research and development process based on MBSE, and therefore efficient transmission and communication of data between the system model and the professional models are achieved, and the method is beneficial to building of the system model based on the SysML system model and the professional models. A single data true phase source throughout the whole product life cycle provides data support for forward research and development of complex products.