66 results about "Knowledge integration" patented technology

A federated distributed computational system enables secure oncological therapy optimization through robotic integration. The system establishes a distributed graph architecture with secure communication channels connecting computational nodes, implementing encryption protocols for cross-institutional data exchange. Each node contains processing capabilities for fluorescence-guided imaging, uncertainty quantification, and expert knowledge integration while maintaining hierarchical knowledge graphs of oncological biomarkers, interventions, and outcomes. The system coordinates domain-specific knowledge through token-space communication and implements an advanced robotic integration system for surgical interventions using spatiotemporal tumor mapping, multi-modal fluorescence imaging, surgical robot coordination, and space-time stabilized mesh management. Key capabilities include wavelength-specific multi-modal fluorescence detection, combined epistemic and aleatoric uncertainty estimation, tensor-based data integration with adaptive dimensionality control, and light cone search for adaptive treatment optimization—all while maintaining strict privacy controls.

Systems and methods for dynamic knowledge integration in LLM systems including receiving multimodal input data comprising text, image, audio, video, and / or code data, extracting information by processing the multimodal input data through a document processor, storing the extracted information in a dynamic knowledge base, receiving a user query at a query processor, identifying knowledge domains related to the user query using domain-specific agents, retrieving real-time information from the dynamic knowledge base responsive to the identified knowledge domains, integrating the real-time information into the processing of an LLM by a dynamic knowledge integrator, and generating a response using the LLM with the real-time information.

The invention belongs to the technical field of artificial intelligence and educational informatization, and relates to a multi-mode knowledge graph enhanced intelligent teaching-assistant question-answering system. According to the method, the knowledge graph construction technology, the multi-modal content analysis technology and the large language model reasoning enhancement technology are comprehensively applied, and the semantic understanding, knowledge integration and reasoning generation capabilities of the intelligent teaching assisting system in an education and teaching scene are improved. The related technology comprises layout analysis of textbook documents, semantic description generation of image content, entity and relation extraction of text content, multi-modal knowledge graph construction and question and answer reasoning and natural language generation combined with the knowledge graph. Through cooperative application of the technologies, semantic interconnection can be carried out on various modal information such as texts, images and tables in the textbook, and a searchable and traceable textbook-level knowledge network is formed.

The invention provides a hybrid AI adaptive optimization system based on agent context engineering. The hybrid AI adaptive optimization system comprises a context knowledge base, a generation module, a feedback analysis module and a knowledge integration module. According to the method, the problems that in an existing context optimization technology based on a large language model (LLM), context Bias is simplified, Context Collapse is caused by overall rewriting, and the learning process is high in delay, high in cost, unstable and the like are solved.

The invention discloses a BGE embedding model fine tuning method for power grid engineering cost knowledge, and relates to the cross technical field of artificial intelligence and electric power engineering cost, and the method comprises the following steps: collecting text data, and constructing a semantic pairing set based on a graph structure of cross-format semantic mapping and quality detection; constructing an initial knowledge corpus according to the semantic pairing set, and performing fine adjustment on a BGE pre-training model; performing vectorization coding on the initial knowledge corpus according to the fine-tuned model, and constructing an efficient vector database by adopting an FAISS index method; searching the question input by the user based on the efficient vector database, performing knowledge enhancement on a search result, and outputting final decision support; through the method based on cross-format semantic graph modeling, BGE embedding model fine adjustment and multi-scale vector index retrieval, the problems that a general embedding model is insufficient in understanding of power grid cost technical terms, the cross-document knowledge integration efficiency is low, and semantic matching is not accurate are solved.

The invention relates to a rule-based reinforcement learning and thinking chain retrieval enhancement generation reasoning method. The method comprises the following steps of: preprocessing data; model training; and performing actual reasoning by adopting the trained model. The method has the beneficial effects that the complex multi-step reasoning capability of a large model is remarkably improved; knowledge integration is carried out, and the efficiency of retrieval enhancement generation (RAG) is optimized; the training cost is reduced; the stability of the strategy is enhanced; dynamic decision support and logic specification constraints are enhanced; the method can perfectly accord with verification requirements for multi-step reasoning ability, and can better adapt to knowledge and language styles in specific fields; the problem that a traditional RAG retrieval result is disjointed with an inference chain is solved, and the capacity of the model for processing complex and multi-step inference tasks is improved.

The invention provides a double-layer adaptive fusion method and system for scientific and technical literature knowledge, and relates to the technical field of language processing, and the method comprises the steps: constructing a double-layer adaptive fusion architecture; receiving a scientific and technical literature text and extracting a text basic feature vector; the general knowledge layer processing module performs general high-dimensional feature vector mapping, and the professional knowledge layer processing module performs professional high-dimensional feature vector mapping; and the adaptive fusion module performs field confidence calculation, configures an adaptive fusion weight parameter, performs weighted fusion on the general-text high-dimensional feature vector and the professional text high-dimensional feature vector, and applies an output module to perform processing of the scientific and technical literature by using the fused feature vector. According to the method and the device, the technical problem of inaccurate knowledge fusion caused by poor adaptability of a general model, limited generalization ability of a field-specific model and lack of adaptability of static knowledge integration in the prior art can be solved, and the accuracy of knowledge fusion is improved by constructing a double-layer adaptive fusion architecture.

The present disclosure provides a method and system for dynamic enhancement of complex skills in a production line having uncertainty. The method comprises: acquiring a multi-view video segment, comprising an assembly task, in a virtual scene; inputting the multi-view video segment into a video parsing model to perform multiple rounds of interactive questions and answers between large models so as to generate a task action sequence and action instructions obtained after parsing; inputting the task action sequence and action instructions obtained after parsing and all nodes of a multi-level and multi-grade knowledge graph into a data enhancement network model for assembly knowledge integration to generate an enhanced action sequence; and performing secondary enhancement on the enhanced action sequence by using reinforcement learning in a simulation environment, so as to obtain a final task action enhancement result. The present disclosure aims to solve multiple problems in existing 3C product assembly technology, especially how to dynamically cope with different assembly tasks on a production line, and improve the accuracy and efficiency of assembly operation.

The present invention relates to the technical field of robots and knowledge engineering, and in particular relates to a hierarchical knowledge representation method for skills in a dynamic task scenario, an apparatus, an electronic device, and a storage medium. The method comprises: on the basis of different semantic knowledge types, using a graph database to construct a knowledge hierarchical understanding framework; and, on the basis of a preset task, performing knowledge extraction on the dynamic task scenario and, on the basis of a triple, performing external knowledge integration and dynamically updating a knowledge base to obtain a dynamic operation skill knowledge base. The application further discloses: designing a multi-level knowledge expression system of operations, planning, tasks, and objects, establishing a dynamic action library, a skill library, and a task library, and forming a robot skill operation knowledge library in a dynamic scenario together with a static entity library and a scenario library, thereby achieving knowledge guidance and data-driven operation task reasoning. Thus, a model is designed according to different scenario characteristics and an operation skill knowledge library is constructed after collecting data, thereby improving the interpretability, operation task planning, and skill migration efficiency of robot operation skill learning.

The invention discloses a water conservancy flood control scene-oriented question and answer intention recognition and multistage classification model construction method and system and a computer readable storage medium. The method comprises the steps of data collection and knowledge fusion; data preprocessing and intention system construction; constructing training data; training an intention recognition model; an online application mechanism; and model optimization and feedback closed loop. By constructing a standardized data acquisition process, a specialized intention recognition model and a high-adaptability interaction mechanism, accurate understanding and structured expression of the natural language instruction of the user in the flood control scene are achieved, and then the intelligent level of key services such as scheduling and early warning is improved.

The application discloses a database interaction method and device based on multi-agent cooperation, equipment and medium, and relates to the technical field of database interaction. The method comprises the following steps: obtaining a query request, performing semantic segmentation, and then vectorization, and obtaining a search vector set. A search source is selected and searched, and an information block is obtained. A candidate knowledge is obtained through knowledge base retrieval. The information block and the candidate knowledge are integrated, and a candidate information set is obtained. A dynamic demand understanding model is constructed according to the query request and the candidate information set, a task state matrix and a tool calling task are obtained. The corresponding auxiliary tool is called and operated, the task state matrix is updated according to the operation result, and the task planning agent is returned to update the tool calling task, until no tool calling task is output, and a task result is obtained. When the database interaction module is called, a chart is generated according to the output result of the database interaction module, and the chart is output together with the task result. Otherwise, the task result is directly output.

The invention discloses a document-level relation extraction method and system based on knowledge enhancement and evidence guidance, and belongs to the technical field of natural language processing and information extraction. According to the invention, three core modules are mainly used for cooperative work: a document graph enhancement module is used for constructing a hierarchical heterogeneous graph and fusing co-reference analysis to enhance semantic representation; the knowledge enhancement module introduces an external knowledge base and adopts a confidence coefficient filtering mechanism to reduce knowledge noise; the evidence guidance reasoning module realizes multi-hop reasoning through axial attention and evidence supervision, and solves the technical problems of decentralized modeling of reasoning capability, large knowledge integration noise, insufficient evidence guidance and limited long-range dependence capture capability in the existing method. Experiments show that the method can effectively capture inter-sentence dependence, suppress knowledge noise and improve multi-hop reasoning stability, and can be widely applied to scenes such as knowledge graph construction, intelligent question and answer and information retrieval.

The application relates to the technical field of artificial intelligence, and discloses a research report generation method, device, equipment and storage medium, the method comprising: in response to an input research topic, planning an agent to plan research steps based on the research topic, obtaining a multi-step research plan with a logical progression relationship, and based on the multi-step research plan, gradually searching in a search engine by a research agent to obtain research-related information corresponding to each research step, and generating a research report corresponding to the research topic according to the research-related information corresponding to each research step. In the application, multi-agents work together to generate a multi-step research plan with a logical progression relationship and gradually search in a search engine to generate a research report, thereby realizing intelligent planning of research report generation and improving research efficiency and knowledge integration capability.

The invention provides a multi-modal video knowledge query system combined with agent task intention, and relates to the technical field of multi-modal fusion, and the system comprises a feature extraction module which is used for receiving video clips and text problems, and carrying out the processing of a video frame sequence through a lightweight three-dimensional convolutional network to generate a video time sequence feature vector; performing semantic analysis on the text question to generate a text semantic feature vector representing question semantics; and the mapping module is used for analyzing the corresponding relationship between the space coordinates of the video key frame and the text semantics according to the relevance between the video time sequence feature vector and the text semantic feature vector, constructing a dynamic space semantic mapping representation, and determining an initial space reference position based on the mapping representation. Through multi-modal feature fusion, dynamic space-time constraint and external knowledge integration, the task intention of the agent is captured, the comprehensive answer fitting the scene is generated and output in the form of voice, and the accuracy, efficiency and interaction convenience of multi-modal video knowledge query are improved.

This invention discloses a cross-disciplinary knowledge integration teaching method based on a story framework, belonging to the field of smart education technology. First, a general story skeleton is constructed, including an initial state, a target state, constraints, and a role system. Second, the system receives the teaching objective input and automatically matches and extracts relevant knowledge nodes from multiple disciplines using knowledge graph technology. Next, a semantic mapping algorithm dynamically fills the extracted knowledge nodes into the conflict resolution path of the story skeleton, generating a logically coherent cross-disciplinary narrative script. Finally, the system drives a virtual character to execute the script and dynamically adjusts the story's difficulty level and branching directions based on learners' real-time interactive feedback. This invention breaks down the barriers of traditional single-discipline teaching, concretizing abstract knowledge into tools for resolving story crises, significantly enhancing learning immersion, knowledge transfer ability, and comprehensive problem-solving skills.

The invention discloses a medicine research and development industry knowledge base system and method based on artificial intelligence, and belongs to the technical field of medicine information processing and artificial intelligence. The system comprises a data acquisition module, a data preprocessing module, a knowledge extraction module, a knowledge integration module, a knowledge reasoning module, a knowledge updating module and an intelligent center layer. The data acquisition module acquires multi-modal medicine research and development data, the preprocessing module performs cleaning, standardization and feature alignment, the knowledge extraction module adopts a deep learning model based on Transformer to extract entity relationships, the knowledge integration module checks conflicts through a chemical rule knowledge base and constructs a knowledge graph, and the knowledge graph is used for establishing a knowledge database. The knowledge reasoning module performs association prediction by using a graph neural network and a time sequence model, the knowledge updating module realizes parameter optimization and incremental updating based on human feedback reinforcement learning, and the intelligent central layer overall plans all the modules to work cooperatively based on a large language model arrangement framework. According to the method, multi-source heterogeneous data can be integrated, domain semantics can be deeply understood, a knowledge structure is dynamically evolved, intelligent decision support is provided, and the efficiency and accuracy of medicine research and development knowledge management and application are remarkably improved.

The invention discloses a big language model fine tuning enhancement method and system based on mixed knowledge adaptation, and the method comprises the steps: firstly carrying out the structural knowledge embedding pre-training of a knowledge graph, obtaining the embedding vector of an entity and a relation, and mapping the embedding vector to a big language model semantic space; key tokens are extracted from the input text, entities are aligned, embedding vectors are associated, and structured knowledge representation is formed; fusing the representation with output features of a corresponding layer of the large language model through a knowledge adaptation layer, and generating a knowledge enhanced text representation; and finally, selecting an adaptive expert module through an entropy regularization routing mechanism by using a hybrid expert architecture, and outputting an expert prediction weighted sum instead of the traditional feedforward network output to finish fine tuning enhancement. According to the method, the problems of knowledge structure loss, insufficient multi-view knowledge integration and the like in the prior art are solved, the accuracy and reliability of the model in knowledge-intensive tasks are improved, and the calculation cost is reduced.

The invention discloses a motor-oriented fault mode knowledge graph construction and updating method and a motor-oriented fault mode knowledge graph construction and updating system. The motor-oriented fault mode knowledge graph construction and updating method comprises the following steps: constructing a motor fault domain ontology model: defining a core concept class hierarchy, an object attribute and a semantic relationship, obtaining structured data and unstructured data, defining a data attribute, and setting a logic constraint and an axiom; performing double-channel knowledge extraction: performing knowledge extraction on the unstructured data by adopting a deep learning model, performing knowledge extraction on the structured data by adopting a mapping method, and generating original triple knowledge; knowledge fusion: integrating knowledge from different data sources through entity alignment, attribute fusion and conflict resolution to construct a high-quality and unambiguous knowledge graph, and storing the high-quality and unambiguous knowledge graph in a graph database; and performing intelligent fault reasoning and dynamic updating based on the knowledge graph. According to the method, multi-source data are fused, long and difficult entities and complex semantic relationships are identified more accurately, and the accuracy and efficiency of troubleshooting are improved through a double weighting algorithm.

The application discloses a kind of multi-agent cooperation methods based on retrieval enhancement's knowledge integration, specifically related to compliance audit question and answer technical field, document analysis agent splits compliance document into clause fragment and generates clause positioning mark, constructs knowledge unit and calculates evidence qualified score, and stores into knowledge unit library;Inquiry analysis agent forms structured inquiry representation, and retrieval agent retrieves accordingly and generates evidence package under the filter rearrangement of evidence qualified score in audit mode;Reasoning agent constructs integrated evidence graph based on evidence package and generates conclusion unit, and outputs candidate reply with reference drop point;Consistency check agent calculates support score and contradiction score and determines auditable conclusion strength, and output control or trigger closed-loop rectification process is carried out to reply.

The application discloses an airplane overall concept scheme intelligent design method based on a large language model, and belongs to the field of airplane overall design. The method fully gives play to the capacity of the large language model in knowledge integration, multidisciplinary collaboration and optimization design. By constructing a knowledge base of overall parameters, engine parameters and aerodynamic layout parameters, and in combination with the powerful text understanding and reasoning capacity of the large language model, the method realizes the rapid generation and optimization of design. Compared with traditional methods and existing tools, the large language model can significantly improve design efficiency, optimize the design process and output high-quality parameters, thereby meeting the needs of modern airplane design for rapid response and innovative design. Advantages of the method are as follows. First, the large language model can efficiently process multidisciplinary knowledge and realize cross-field collaborative design. Second, the parameter estimation and design optimization capacity of the large language model is significantly improved, thereby providing more accurate support for design schemes. The method provides strong technical support for modern airplane design.

The rise of specialized vision foundation models has created a need for methods to consolidate knowledge from multiple models (i.e. the teachers) into a single model (i.e. the student). However, this type of knowledge agglomeration leaves open several critical challenges, including that teacher models typically operate at varying resolutions due to different architectures and training goals, creating feature granularity inconsistencies, that existing models have different distribution moments which can result in biased learning, and that computer vision models are oftentimes trained to produce features at a particular resolution, and therefore do not generalize well to different tasks requiring different resolutions. The present disclosure provides multi-resolution and multi-teacher based training of a computer vision model, which can capture both fine details and broader abstractions from the teacher models, which can prevent biased learning among the teacher models, and which can produce a flexible computer vision model for different feature resolutions.

Systems or methods of the present disclosure may provide a design tool for adjusting designs implemented on programmable logic devices. The present disclosure includes receiving one or more sources, like documentation, design files, constraints, design reports, source code, chat history, or any combination thereof. The present disclosure also includes identifying relevant relationships between related information across the one or more sources, creating attribution metadata to track lineage of information based on the relevant relationships, and continuously maintaining and updating a knowledge integration database using the attribution metadata. Furthermore, the present disclosure includes providing visualization of the knowledge integration database.

The application provides a data and knowledge jointly driven traffic flow prediction method, and belongs to the technical field of traffic flow prediction. The method comprises the following steps: preprocessing traffic flow data of a current road network; configuring parameters of a traffic flow prediction neural network model, and constructing the traffic flow prediction neural network model; training the traffic flow prediction neural network model by using the preprocessed traffic flow data; and predicting future traffic flow signals of the road network by using an optimal traffic flow prediction neural network model obtained through training according to historical road network traffic flow data. The application solves the problems of insufficient knowledge integration and precision improvement bottleneck of a traditional deep learning traffic flow prediction method.

The functional knowledge integration method for innovative design based on deep reinforcement learning includes: 1) constructing a functional knowledge graph by matching discrete functional knowledge units with their input / output; 2) modeling the core task of functional knowledge integration—functional unit chain generation—as a Markov decision process and solving it using the deep Monte Carlo algorithm in reinforcement learning; 3) merging the phased solutions (functional unit chains) generated by the reinforcement learning algorithm into a final design solution through an automatic or semi-automatic iterative framework. Based on the user's structured semantic description of the target product's functions, this invention can output the most functionally complete design solution in near real-time, ensuring solution quality while significantly reducing the time cost required for functional knowledge integration under a large-scale knowledge base.

The invention belongs to the field of information technology and nuclear power engineering management cross technology, and particularly relates to a multi-reactor nuclear power station knowledge management intelligent platform and method based on a block chain technology. Comprising a cloud computing and big data driven knowledge storage integration module which is a function block shared by all block chain nodes on a chain; the block chain enabled decentralized collaborative network comprises a multi-node trust mechanism module and an intelligent contract rule base; the intelligent knowledge management module driven by artificial intelligence comprises an intelligent knowledge pushing module, an intelligent editing and research system and an active pushing and synchronous updating module; an Internet of Things and edge computing integration module; and a one-key copy block chain node regeneration module. The method is used for realizing knowledge integration, resource sharing, risk management and control and efficient cooperation in the global strategy of the nuclear power project.

The invention discloses an automatic driving reinforcement teaching learning method, device and equipment, a medium and a product. The method comprises the following steps: in a simulation platform, constructing a reinforcement learning abstract environment containing a state, an action and a reward function based on an automatic driving scene; obtaining multi-source trajectory data in the reinforcement learning abstract environment, wherein the multi-source trajectory data comprises a preset teaching state transition trajectory, a different-orbit state transition trajectory and a same-orbit state transition trajectory; clustering the multi-source trajectory data to obtain a clustering result, performing probabilistic sampling according to the clustering result, and constructing a mixed experience playback pool; and carrying out automatic driving reinforcement teaching learning based on the mixed experience playback pool. According to the scheme, teaching knowledge used in imitation learning is integrated into a traditional reinforcement learning method, and the sampling and utilization mode of a probabilistic sampling optimization sample is combined, so that the learning ability of the traditional reinforcement learning method is kept, and meanwhile, the automatic driving learning process is more stable.

The technical scheme of the invention discloses a system for integrating test knowledge and managing and applying a test fault knowledge base, which is characterized by comprising a test fault knowledge base subsystem and a test training guide subsystem. According to the invention, through centralized storage and management of test fault related knowledge, a tester can be helped to quickly find a solution when facing a test fault, test pause time is reduced, work efficiency is improved, and meanwhile, operation behaviors of the tester are guided and standardized through test training, and the risk of misoperation is reduced.

The invention discloses an incremental tuning and knowledge injection method and system for few samples / rare diseases, and relates to the field of continuous learning of a large language model (LLM) and medical artificial intelligence. In order to solve the technical problem that catastrophic forgetting is easily generated when an existing model is subjected to incremental tuning in small-sample and high-value fields (such as rare diseases), the invention provides an optimization strategy based on PEFT (Parameter Efficient Fine Transfer) and knowledge integration loss. The method comprises the following steps: initializing a PEFT module and adding the PEFT module to a pre-training LLM; taking few-sample data labeled by experts as new task data; constructing a dual loss function containing new task loss and knowledge distillation loss (measuring the difference between the output of the new model and the output of the basic model); only by optimizing the parameters of the PEFT module, the basic universality is protected from being damaged to the maximum extent while it is guaranteed that the model quickly masters rare disease knowledge. According to the invention, the efficiency and the stability of the medical LLM in a continuous updating scene are remarkably improved.

This application provides a method and system for managing activities related to ancient architecture research and study, relating to the field of digital culture. The method includes: acquiring multi-source data on ancient architecture and basic data of research and study users; performing entity recognition and relationship extraction on the multi-source data to construct a knowledge graph of ancient architecture and form structured knowledge of ancient architecture; constructing a set of rules for the knowledge graph of ancient architecture based on the multi-source data and the knowledge graph of ancient architecture; constructing user profiles based on the basic data of research and study users and the knowledge graph of ancient architecture; the user profiles are used to characterize the user's cognitive level, interests, preferences, and learning abilities; retrieving knowledge subgraphs from the knowledge graph that match the user profiles, and generating research and study activity paths. This application, used in the management of activities related to ancient architecture research and study, solves the technical problem that existing technologies cannot meet the needs of multi-dimensional knowledge integration and application in ancient architecture research and study activities.

The invention relates to the technical field of health science popularization education, in particular to a knowledge graph-based interactive science popularization platform for old-age common-disease health management scenes, which is characterized in that a main body adopts a four-layer three-terminal architecture system, and the four-layer architecture comprises a data layer, a knowledge layer, a scene interaction layer and an application layer. The system has the advantages of breaking through practical problems such as disease complexity, insufficient health education and information overload so as to improve the health quality and self-management ability of the co-sick elderly patients, and in the actual use process, through the use of a four-layer three-terminal architecture system, the form of traditional health science popularization is fundamentally changed, and the development of health science popularization is facilitated. The knowledge graph is utilized to integrate the segmented single disease knowledge into the associated network, so that the spanning from fragmented informing to systematic understanding is realized, the elderly user is helped to clear complex interaction among common diseases, precise and personalized health guidance is provided, and the learning effect and initiative of the elderly user are effectively improved.