57 results about "Knowledge engineering" patented technology

The invention relates to the technical field of artificial intelligence and knowledge engineering, and provides a digital human knowledge graph dynamic iteration system and method based on user feedback. According to the method, the timeliness and automation level of knowledge updating are improved; the configuration efficiency of technical resources is optimized; a data-driven iterative verification closed loop is constructed; according to the knowledge service system, the maintainability and robustness of the system are enhanced, the system has the capabilities of tracking, querying and rollback any change, the risk of system service degradation caused by misoperation or invalid updating is greatly reduced, and the stability of the whole knowledge service system is improved.

The invention provides a dynamic updating method and system of a knowledge graph based on reasoning enhancement. The method belongs to the cross technical field of artificial intelligence, knowledge engineering and dynamic system modeling. The method comprises the following steps: performing multi-dimensional feature extraction on original knowledge data to generate a knowledge feature vector set; constructing an initial knowledge graph structure based on the knowledge feature vector set, and defining an initial association rule between knowledge nodes to form a basic knowledge graph model; building a multi-order causal inference engine according to the basic knowledge graph model, performing deep mining on potential causal relationships among knowledge nodes, and generating a knowledge causal relationship network; and performing confidence evaluation on each causal chain in the knowledge causal relationship network to obtain the knowledge causal relationship network subjected to quality verification. Based on a multi-order causal reasoning engine, the system can mine and verify potential causal relationships among knowledge nodes in real time, and continuous updating and self-optimization of the knowledge graph are ensured.

The invention belongs to the technical field of artificial intelligence and knowledge engineering, and relates to a multi-modal knowledge graph construction and interactive exploration method and system oriented to game cognition enhancement. The method comprises the following steps: acquiring multi-source heterogeneous multi-modal data, converting non-text modal data into a description text, and extracting a knowledge triple; constructing a multi-modal knowledge graph according to the extracted knowledge triad; and based on the constructed multi-modal knowledge graph, game cognition enhanced interactive exploration and multi-modal visual presentation are carried out. According to the method, end-to-end multi-source heterogeneous multi-modal unified integration can be realized, cross-modal concrete support of a cognitive process is realized, multi-modal knowledge traceability verification of a decision basis is realized, real-time perception and synchronization of a dynamic game environment are supported, and the method is suitable for popularization and application. According to the method, newly generated key information can be quickly digested, absorbed and updated to the knowledge graph in a quickly changing game environment, and is immediately retrieved and explored, so that approximate real-time dynamic cognition and decision support is provided for a user.

The invention discloses a big language model illusion detection method and device based on a knowledge graph and a medium, and relates to the technical field of natural language processing and knowledge engineering. The method comprises the steps of generating a to-be-detected text in response to a large language model, and obtaining a domain knowledge graph; performing structured analysis on the to-be-detected text to obtain an entity set and a relation triple corresponding to the to-be-detected text; based on the domain knowledge graph, performing factual illusion detection on the entity set and the relation triple to obtain a detection result and confidence corresponding to the factual illusion detection; and generating an illusion detection result corresponding to the to-be-detected text based on the detection result and the confidence coefficient. Therefore, the detection precision is high, the coverage range is wide, and the interpretability is high.

The invention discloses a dynamic adaptive management system for road traffic safety planning driven by artificial intelligence. According to the system, multi-source data are acquired through a data acquisition and preprocessing layer and are cleaned and standardized; the knowledge engineering layer constructs a policy knowledge graph and a rule engine; the large model service layer realizes natural language generation, semantic understanding and multi-modal reasoning; the intelligent generation layer uses a GAN model to generate multi-modal planning content and dynamically adapts the multi-modal planning content; the implementation process management layer monitors planning implementation, middle-stage evaluation and last-stage summarization in real time; and the interaction and output layer provides visual editing and multi-format output. The system integrates the technologies of deep learning, generative adversarial network and the like, realizes intelligent planning generation and dynamic supervision, has the capabilities of multi-modal data processing, dynamic self-adaption and full-process management, can effectively improve the scientificity, high efficiency and adaptability of road traffic safety planning, and provides powerful support for road traffic safety management.

The invention relates to the cross technical field of artificial intelligence and knowledge engineering, in particular to a local knowledge base question-answering system based on a new energy automobile and a construction method thereof, and the method comprises the following steps: integrating a knowledge graph, a ChatGLM2-6B language model and a LangChain framework to construct a local knowledge base question-answering system; obtaining a ternary collaborative architecture for structured management, retrieval and semantic question and answer of heterogeneous data in the new energy field; and based on the ternary collaborative architecture, correspondingly designing a plurality of functional modules for providing an intelligent question-answering solution for the field of new energy vehicles, and forming the local knowledge base question-answering system for the new energy vehicles. According to the'knowledge graph-pre-trained large model-LangChain 'ternary collaborative architecture provided by the invention, structured management, efficient retrieval and high-precision semantic question and answer of heterogeneous data in the field can be realized, and structural management, efficient retrieval and high-precision semantic question and answer of multi-source heterogeneous data in the new energy automobile field can be realized; and local deployment, large model generation and interpretable retrieval can be combined.

The invention discloses a knowledge graph multi-modal document analysis and image table semantization knowledge recall method, and belongs to the technical field of knowledge engineering and information retrieval. The invention provides an innovative scheme for fusing a visual language model, semantic abstract generation and knowledge graph modeling. The method comprises the following steps: constructing a vertical domain knowledge graph by adopting a BERT-BiLSTM-CRF model; according to the method, multi-modal document analysis is realized through models such as DocLayout-YOLO, TableMaster, UniMERNet and the like; the method comprises the following steps of: segmenting an image into 16 * 16 block sequences by adopting a vit-gpt2-image-adaptation model, and realizing image semantization through 768-dimensional vector space mapping and Transform coding; constructing a document summary tree based on DBSCAN clustering and LLM recursive summary; and designing a hybrid retrieval space fusing semantic vectors and structured vectors, and reordering by adopting a double-attention mechanism. According to the method, the knowledge base document retrieval recall rate is increased to 99%, the question and answer accuracy rate reaches 90% or above, the index construction time is shortened by 60%, and the problem that semantic understanding and recall of non-text elements in complex documents are difficult is effectively solved.

The invention provides a document knowledge retrieval method and system based on a two-way quantity library hybrid architecture, relates to the technical field of crossing of artificial intelligence and knowledge engineering, and solves the technical problems that a traditional RAG knowledge retrieval system is delayed in response to high-frequency repeated problems, high in cost and poor in answer consistency due to indifference processing. The method comprises the steps of obtaining a user query request and historical document data; constructing an FAQ vector library and a document vector library based on the historical document data; calculating the matching similarity between the user query request and the FAQ vector library through a similarity algorithm to obtain an FAQ similarity score; comparing the FAQ similarity score with a preset similarity threshold value; when the FAQ similarity score is greater than or equal to a similarity threshold value, marking a standard answer corresponding to the FAQ similarity score as a query result; when the FAQ similarity score is smaller than the similarity threshold value, the document vector library is retrieved, and a big language model is called for TOP-M related fragments to generate answers to serve as query results. The method and device are used in the knowledge retrieval process.

The application discloses a dynamic enhanced multi-modal hypergraph retrieval enhancement generation method and system, belonging to the technical field of information retrieval and knowledge engineering, comprising: in the offline stage, cross-modal encoding is performed on multi-source heterogeneous data to generate cross-modal vector index and candidate theme / entity set; knowledge drift detection is performed on the cross-modal vector index and the candidate theme / entity set, if it is determined that there is drift, then local subgraph incremental hypergraph update is triggered, and after multi-expert voting alignment verification, it is written into a multi-modal double hypergraph index library; in the online stage, the user request is subjected to semantic analysis, theme words and entity words are extracted; according to the theme words and the entity words, coarse retrieval and fine retrieval are performed based on the multi-modal double hypergraph index library, evidence subgraphs are extracted, multi-modal context is obtained; the user request and the multi-modal context are input into a multi-modal large language model to generate an answer and feedback the user; the timeliness, stability and reliability of retrieval are improved, and the integrity of complex knowledge reasoning is improved.

The application discloses a domain knowledge triple extraction method, system, medium and equipment, and relates to the technical field of knowledge engineering.The domain knowledge triple extraction method and system provided by the application can provide high-quality and efficient data support for triple extraction by analyzing and converting the obtained domain professional text into a structured vector knowledge base which can be efficiently searched, then the domain professional text is subjected to quantitative calculation and fusion screening, the initial entities of domain core high-frequency words which have global high frequency and cross-text universality are mined, the problem of "local optimum and global deviation" caused by traditional single word frequency is avoided, non-core term interference is effectively avoided, and the stability, relevance and efficiency of iterative extraction are improved, and further, the high-frequency word initial entities are subjected to closed-loop iteration through iterative RAG algorithm combined with the structured vector knowledge base, accurate extraction of the large model and iterative correlation entities, the explicit and implicit semantic correlation triples in the text can be mined layer by layer, the strong relevance and structural integrity of the extracted triples are ensured, and the professionalism and accuracy of the model in extracting triples are improved.

The application relates to the technical field of knowledge engineering, and discloses a production and manufacturing digital twin modeling method based on a knowledge graph, which comprises the following steps: performing data fusion and model construction on original multi-source data, obtaining multi-source fusion data, and generating a digital twin architecture; performing ontological design and semantic modeling on the multi-source fusion data, and generating a manufacturing knowledge graph; wherein the manufacturing knowledge graph is represented by triplets, and the triplets comprise entities-relation-entities / attributes; performing entity modeling on the manufacturing knowledge graph, and obtaining a knowledge-driven geometric model; and performing reasoning based on the manufacturing knowledge graph and historical data, and obtaining a knowledge-driven decision model. The method can construct a digital twin model with knowledge-driven prediction and decision-making capabilities, and provides a high-robustness and sustainable-evolution digital twin modeling method for intelligent manufacturing, smart factories and other fields. The application also discloses a production and manufacturing digital twin modeling device based on the knowledge graph and an electronic device.

This invention belongs to the interdisciplinary fields of industrial internet, knowledge engineering, and intelligent mining. It proposes a method and system for knowledge decoupling and dynamic collaborative reasoning throughout the entire mineral processing process. It constructs a static domain ontology covering geology, mining, and beneficiation, integrates multi-source heterogeneous data, responds to mining loading events, matches target ore body segments based on spatial coordinates, creates ore unit instances with attached geological attributes and established traceability associations, and updates their status in real time as the ore flows, associating them with current process equipment to form a dynamic flow knowledge graph. Based on the geological attributes and location information in the graph, it uses spatiotemporal mapping rules to predict the estimated time for the ore to reach downstream equipment, generates process adjustment instructions based on preset reasoning rules, and sends them to the control system during the buffer period. This invention achieves dynamic collaboration and intelligent control throughout the entire process from geological source to beneficiation terminal, effectively improving the accuracy and efficiency of mineral processing.

The invention discloses a query request processing method and system based on a scatter neural network, and relates to the technical field of artificial intelligence and knowledge engineering. According to the method, an original knowledge source of a target domain is obtained, ternary array knowledge scatter points containing a core object, association logic and domain connotation are generated through structured analysis, and ternary array and dense vector double views are adopted for representation and storage; and responding to a query request, performing adaptive multi-path retrieval on the knowledge scatter points based on the semantic type and other characteristics of the query request, and generating a target answer after confidence evaluation and optimization. According to the method, the problems of low analysis efficiency of an original knowledge source in the financial field, poor semantic matching of a single retrieval strategy, insufficient understanding of general and special knowledge and low question and answer accuracy caused by large model illusion can be solved, and the accuracy and efficiency of vertical field query request processing and the dynamic knowledge strengthening capability are improved.

This invention discloses a method and system for constructing a SPEC parameter extraction structure vector model. The method includes the following steps: Step 1: Constructing a multi-constraint international standard knowledge graph; Step 2: Intelligently extracting SPEC document parameters based on the multi-constraint graph; Step 3: Constructing a multi-constraint structure vector model; Step 4: Constructing a sub-project experience database, and outputting the results of the multi-constraint structure vector model. This invention relates to the field of knowledge engineering interdisciplinary technology and can solve the problems of low parameter extraction efficiency, fragmented constraint relationships, poor generalization of vector models, and lack of sub-project experience systems in existing technologies.

The application discloses a document checking method, system, device, medium and product based on a large language model and a rule graph, relates to the field of information processing and knowledge engineering, and comprises the following steps: a large language model is used to analyze a rule document and a business term table, an examination element table and a rule graph are generated, and a document processing pipeline and a logic verification pipeline are executed in sequence; when the document processing pipeline is executed, image recognition and layout analysis are performed on the materials to be examined and user metadata, a visual large model is called in combination with the examination element table to perform structured extraction, and context objects are generated; when the logic verification pipeline is executed, based on the context objects, preconditions are selected, evidence requirements are evaluated, and decision determination is performed in sequence, an examination report is generated based on a final determination state, and routing strategies of automatic passing, manual review or returning are triggered. The application can realize rule analysis automation, examination process standardization, interpretable determination results and full-link traceability.

The application discloses a kind of based on the automatic construction method and system of business ontology of information foraging theory, it is related to knowledge engineering and artificial intelligence field.The method includes: determining the target vector of business ontology and constructing the bidirectional smell word bank containing positive and negative smell words;Multi-source heterogeneous documents are cut into information patches, and the multidimensional smell intensity containing theme correlation component and smell word hit component is calculated;According to smell intensity, a foraging priority queue is constructed from high to low, and patches below the global stop threshold are skipped;The patches extracted are extracted ontology elements in turns, and whether to terminate and migrate is determined according to the comparison of instantaneous yield and average yield of environment;Ontology elements are fused into business ontology according to confidence, and the smell word bank is updated according to output, so that the word bank, smell intensity and ontology extraction form a foraging closed loop.The application concentrates limited computing power on high-value patches, reduces computing power consumption and processing delay under the premise of ensuring accuracy and recall rate.

The invention discloses a method and a system for automatically constructing, tracing and deducing a affair graph based on a large model, and belongs to the crossing field of artificial intelligence and knowledge engineering. The construction method comprises the following steps: respectively constructing a knowledge graph and an event graph of a target application scene based on an ontology category tree and an event category tree; transmitting the knowledge graph and the event graph to a large model to generate a affair graph; wherein the large model identifies equivalent entities in the knowledge graph and the event graph through semantic similarity calculation and performs merging, then dynamic connection between events and entities is established to obtain the affair graph, and the affair graph is composed of four-tuple basic units composed of entities, events, relations and attributes. According to the method, a traditional knowledge triple is expanded into a quadruple structure fusing knowledge and events by means of a multi-graph fusion technology, so that more reliable and interpretable strategy suggestions are provided for decision makers.

This disclosure relates to the field of computer technology, and more particularly to a text processing method and apparatus. The method includes: identifying input text using a knowledge engineering model and a target rule base to obtain a first output element set corresponding to the input text; identifying the input text using a large model to obtain a second output element set corresponding to the input text; obtaining a first overlap degree between the first output element set and the second output element set; if the first overlap degree is greater than a first overlap degree threshold, obtaining a target element set corresponding to the input text, and obtaining output text corresponding to the input text based on the target element set. Using this disclosure can improve the efficiency and accuracy of element extraction.

The invention relates to the technical field of water resource management, in particular to a planned water consumption management method and system based on the Internet. The method comprises the following steps: carrying out data networking convergence and water consumption data labeling through the Internet to obtain a water consumption data labeling flow; utilizing a geographic information system technology to carry out geospatial association on the water consumption data annotation flow to obtain geospatial water consumption data; performing motivation recognition model training according to the water consumption data annotation flow to obtain a water consumption motivation recognition model; performing hydraulic motor identification on the water data annotation flow by using a hydraulic motor identification model to obtain hydraulic motor label data; and constructing a user group portrait library based on the hydrodynamic motor label data to obtain the user group portrait library. According to the invention, through deep fusion of data mining, machine learning and knowledge engineering technologies, a full-chain intelligent water consumption management closed loop from data to knowledge and from perception to decision is formed, and more intelligent, accurate and efficient water consumption management is realized.

The invention belongs to the technical field of deep fusion of an artificial intelligence technology and electric power industry knowledge engineering, and relates to a power generation field multi-mode question and answer method and a related device. Professional entities in questions are accurately recognized through a professional term recognition module, information such as texts, images and waveforms is uniformly represented through a multi-modal information fusion mechanism, a model is trained through an expert thinking chain data set, domain knowledge is internalized, an expert thinking mode is learned, and transparent and verifiable answers are generated in a mode of first reasoning and then conclusion. According to the method, the problems of accuracy, reliability and interpretability of multi-modal questions and answers in the power generation field are effectively solved, related knowledge fragments can be accurately positioned, complex problems can be comprehensively understood, complete reasoning logic can be displayed, a credible and reliable multi-modal knowledge question and answer solution is provided for intelligent operation and maintenance of a power plant, and the power generation efficiency is improved. The method is suitable for an intelligent decision support system of a power plant and has important industrial application value.

The invention belongs to the technical field of artificial intelligence and knowledge engineering, and relates to a dynamic knowledge graph construction method and system based on big data and a terminal. According to the method, N tuple data is extracted to construct a graph structure, static embedding is obtained by combining a TransE model, extended data and the static embedding are coded to obtain a time sequence hidden state, and dynamic embedding is obtained based on the time sequence hidden state and the static embedding. Trimming the N-tuple data by constructing a dynamic knowledge graph to obtain a simplified sequence; and calculating characteristic distillation loss and prediction-level distillation loss of each learning stage through the teacher model and the branch student model to obtain total distillation loss, finally calculating to obtain unified context representation, and decoding the unified context representation to obtain a dynamic knowledge graph reasoning result. According to the method, the dynamism and the context adaptive capacity of knowledge representation can be improved, the intelligent learning and decision-making capacity is achieved, and an accurate reasoning result can be obtained.

The invention provides a dynamic troubleshooting problem processing method and device, electronic equipment and a readable storage medium, and relates to the technical field of artificial intelligence such as knowledge engineering, structured information, intelligent agents, external tool calling and visualization. The method comprises the following steps: obtaining a to-be-checked problem initiated for an abnormal condition; the method comprises the following steps: determining a troubleshooting scheme corresponding to a to-be-troubleshot problem by using structured knowledge pre-constructed according to a KDSL (Knowledge Engineering Field Dedicated Language), the troubleshooting scheme being determined and obtained based on different troubleshooting modes and troubleshooting sequences; and issuing each troubleshooting mode to the matched intelligent agent according to the troubleshooting sequence to carry out troubleshooting step by step until the real reason causing the abnormal condition is determined. According to the method, the coverage range and the solving capability of systematic diagnosis of complex problems without clear intentions or needing multi-step reasoning can be remarkably improved.

The application belongs to the technical field of natural language processing and knowledge engineering, and particularly relates to an HPC trusted data question and answer method and system based on closed-loop feedback, a device and an HPC trusted data knowledge base construction method. The method comprises the following steps: S1, collecting text data in the HPC field and screening out trusted text data; constructing a triple in the HPC field according to the trusted text data; S2, for the triple without conflict, removing the triple with consistent semantics, merging the triple with complementary information, and retaining the triple with refined description for the triple with refined attributes; for the triple with conflict, performing conflict resolution to obtain the triple without conflict; the conflict resolution comprises: retaining the triple with higher credibility; S3, constructing a vector knowledge base of HPC trusted data. The application solves the technical problem that the existing technology lacks adaptive trusted evaluation and conflict resolution mechanism in establishing a knowledge base, resulting in the generation of confused or wrong answers.

The application discloses a government affair knowledge graph ontology construction and optimization method and device, equipment and medium, belongs to the cross technical field of artificial intelligence and knowledge engineering, and the technical problem to be solved by the application is how to provide a unified and standardized knowledge benchmark for ontology construction, realize autonomous perception of ontology change characteristics of a system, accurately match an optimal analysis mode, and guarantee the efficiency and accuracy of ontology construction without manual intervention, and the technical scheme is that: a field knowledge base is constructed; an ontology construction system is started, basic configuration parameters of a target field are automatically loaded, core knowledge elements and unstructured documents of the target field are collected, the unstructured documents are classified, semantically marked and uniformly processed in format, a hierarchical structured field knowledge base is generated, and the field knowledge base is used as a unified knowledge benchmark for ontology construction; a processing data acquisition and analysis process is triggered; and an ontology analysis mode is adaptively selected.

The invention relates to the technical field of power grid emergency decision, in particular to a power grid emergency command decision generation method and system based on knowledge engineering, and the method comprises the steps: firstly carrying out the time alignment and noise suppression of fault types, image streams, PMU measurement and topological data based on historical fault alarm timestamps, and constructing a multi-modal data sequence; then target detection is executed on the image frame and the screen display information, entity alignment and semantic disambiguation are completed in combination with a power grid equipment body and a fault type body, and a state action fragment is obtained; and performing consistency verification and conflict resolution on the state action segments through an emergency disposal rule engine and security constraints to obtain training data. And based on the training data and the processing result label, performing training through a deep learning model. And finally, inputting the real-time state action fragment into a training convergence model, generating a real-time target processing step sequence, and converting the real-time target processing step sequence into a structured emergency command decision suggestion, thereby realizing automatic and normalized generation of the power grid emergency command suggestion.

The invention relates to a multi-source heterogeneous document knowledge base construction method and system based on self-adaptive normalization, and belongs to the field of knowledge engineering.The method comprises the steps that original document data of different modals from multiple heterogeneous data sources is collected; performing preprocessing and modal feature extraction on the original document data to obtain modal feature vectors corresponding to the original document data; dynamically mapping the modal feature vectors of different modalities to a unified shared semantic vector space to generate a unified document vector; local reasoning is carried out on the modal feature vectors based on modal exclusive AI agents; recognizing document sets with similar semantics, conflicts or duplicates; performing online aggregation and duplicate removal operation on the document set; constructing a knowledge graph based on a cross-modal semantic association result; and automatically triggering an active learning process to update the model parameters of the AI agent in real time. According to the application, a knowledge base system with self-adaption, real-time performance and autonomous learning ability is constructed.

The application provides a household environment ontology knowledge base automatic construction method and system, and relates to the technical field of artificial intelligence and knowledge engineering. The method comprises the following steps: constructing a household environment ontology knowledge base template, wherein the template contains classes, attributes and instances of the ontology; establishing communication with a target object, obtaining communication text of the target object, and extracting semantic information of the target object; obtaining an image of the target object, and extracting semantic information of the target object based on the image; comparing the extracted semantic information of the object with the existing classes and attributes in the household environment ontology knowledge base as instances of the ontology; judging whether new classes and attributes need to be established based on the similarity comparison result, updating the semantic information, and perfecting the household environment ontology knowledge base. The application can simplify the construction process of the household environment ontology knowledge base, improve the construction efficiency, reduce the labor cost, reduce the non-standardization of manual construction, and improve the quality of the constructed ontology knowledge base.

The invention discloses an incremental knowledge graph dynamic updating method and system based on influence domain recognition, and belongs to the technical field of artificial intelligence and knowledge engineering. The method comprises the following steps: acquiring an incremental knowledge unit containing a new entity and a relationship; determining an influence domain of the new entity in an existing knowledge graph by taking the new entity as a center and utilizing a multi-strategy mixed neighborhood retrieval algorithm, and constructing a local relation sub-graph; and performing iterative enhancement and integration processing on the local relation sub-graph, and circularly performing context enhancement, intelligent deduplication detection, entity aggregation and relation prediction operation in each round of iteration until the graph quality index meets a preset convergence condition. According to the method, the updating complexity is reduced to a local range through an influence domain recognition mechanism, and the problems that the incremental updating efficiency of the large-scale knowledge graph is low, the data consistency is poor and the technical evolution version is missing are effectively solved by combining iterative convergence and a multi-dimensional conflict detection technology.

The invention belongs to the technical field of aircraft wing rib modeling, and particularly relates to an aircraft wing rib modeling method, electronic equipment and a computer readable storage medium. Typical feature extraction is performed on a wing rib structure, and a relationship between typical features and a wing rib mathematical model is established by using a knowledge engineering array; therefore, the influence that the features need to be manually added or deleted due to the fact that the lengths of the wing rib structural parts of the aircraft wings are different is eliminated, rapid modeling is achieved, the modeling method is more efficient, modularization and structuralization are achieved, modification and updating are convenient, visual parameter input is provided, user friendliness is achieved, the repeated modeling process is eliminated, and digital-analog lightweight is achieved.