141 results about "Knowledge integration" patented technology

A federated distributed computational system enables secure collaboration across multiple institutions for biological data analysis. The system consists of interconnected computational nodes managed by a centralized or decentralized federation manager, depending on the deployment model. Each node contains specialized components that work together to process biological data while preserving privacy. These components include a local computational engine that handles data processing, a privacy preservation module that protects sensitive information, a knowledge integration component that manages biological data relationships by connecting various data sources, and a communication interface that enables secure information exchange between nodes. The federation manager coordinates all computational activities across the network while ensuring data privacy is maintained throughout the process. This architecture allows research institutions to collaborate on complex biological analysis tasks without compromising their sensitive data, enabling breakthrough discoveries through shared computational resources and expertise while maintaining the security, compliance, and confidentiality required in biological research.

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.

A federated distributed computational system enables secure collaboration across multiple institutions for multi-species biological data analysis. The system consists of interconnected computational nodes managed by a central federation manager. Each node contains specialized components that work together to process multi-species biological data while preserving privacy. These components include a local computational engine that handles data processing, a physics-information integration subsystem that combines physical state calculations with information-theoretic optimization, a privacy preservation module that protects sensitive information, a knowledge integration component that manages biological data relationships, and a communication interface that enables secure information exchange between nodes. The federation manager coordinates all computational activities and manages resource allocations across the network while ensuring data privacy is maintained throughout the process. This architecture allows research institutions to collaboratively analyze complex, multi-species biological systems through integrated physics-based modeling and information-theoretic approaches while maintaining security and confidentiality.

A federated distributed computational system enables secure oncological therapy optimization through multi-expert integration and advanced uncertainty quantification. The system implements a multi-expert integration framework that coordinates domain-specific knowledge through token-space communication for precision oncological treatment, while maintaining secure cross-institutional data exchange. The architecture coordinates multi-scale spatiotemporal synchronization across computational nodes, with each node containing local processing capabilities for fluorescence-guided imaging, uncertainty quantification, and expert knowledge integration. Through a distributed graph architecture, the system enables advanced fluorescence imaging with wavelength-specific targeting, multi-level uncertainty estimation combining epistemic and aleatoric approaches, and multi-scale tensor-based integration with adaptive dimensionality control. The system implements light cone search and planning for adaptive treatment strategy optimization, enabling medical institutions and research organizations to collaborate on complex oncological therapy projects while maintaining strict data privacy controls.

The invention discloses a closed-loop fault diagnosis method based on the combination of an AI intelligent agent and power equipment simulation, which is applied to the field of power system fault diagnosis, and comprises the following steps: on the basis of a preset knowledge graph basic data set and power system multi-source data, performing data cleaning, feature extraction and knowledge integration; constructing a unified power equipment fault diagnosis knowledge graph, and performing reasoning on the knowledge graph and time sequence characteristics in combination with large model fine tuning or a mixed reasoning engine of a graph neural network to generate M candidate fault hypotheses; calculating the similarity between simulation and actual measurement waveforms through a DTW algorithm and a frequency spectrum comparison method, and screening high-consistency hypotheses; based on the logic verification rule base, performing causal graph reasoning, constraint checking and anti-factual thinking on the high-consistency hypotheses, and eliminating non-logic hypotheses; feeding back the abnormality found in the verification link to the AI agent, dynamically adjusting the reasoning strategy through reinforcement learning, and generating a convergent diagnosis result; and outputting a target diagnosis conclusion based on the converged diagnosis result.

A federated distributed computational system enables secure collaboration across institutions for unified biological and multiomics data analysis. It comprises interconnected computational nodes managed by a central federation manager. Each node includes specialized components: a local computational engine for biological data processing, a privacy-preservation system, a knowledge integration component leveraging dynamic knowledge graphs, and a secure communication interface. The federation manager coordinates computational activities while ensuring security, privacy, legality, and contractual adherence. This architecture allows institutions, citizen scientists, and patients to collaborate on complex biological analyses without compromising sensitive data. By enabling shared computational resources and expertise, the system facilitates breakthrough discoveries while maintaining confidentiality. Additionally, it supports pro-rata or contractually defined participation in resultant benefits or knowledge, ensuring equitable collaboration.

The invention discloses a database interaction method, device and equipment based on multi-agent cooperation and a medium, and relates to the technical field of database interaction. The method comprises the steps of obtaining a query request, performing semantic partitioning and vectorization, and obtaining a retrieval vector set; and selecting a search source and searching to obtain an information block. And obtaining candidate knowledge through knowledge base retrieval. And integrating the information blocks and the candidate knowledge to obtain a candidate information set. And constructing a dynamic demand understanding model according to the query request and the candidate information set, and obtaining a task state matrix and a tool calling task. And calling a corresponding auxiliary tool and operating, updating the task state matrix according to an operation result and returning the task state matrix to the task planning agent to update the tool calling task until the tool calling task is no longer output, and obtaining a task result. And when the database interaction module is called, generating a chart according to an output result of the database interaction module, and outputting the chart and a task result together. Otherwise, directly outputting a task result.

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 discloses a question and answer system based on a semantic vectorization knowledge graph and approximate nearest neighbor clustering, and the system comprises a data uptake and preprocessing module which is used for the input and preliminary processing of an unstructured text; the knowledge graph construction module is used for constructing a dynamic knowledge graph according to the primarily processed data; the knowledge graph enhancement module is used for expanding representation of entities in the knowledge graph by adopting an information enhancer and converting each entity node and relation node in the knowledge graph into a high-dimensional semantic vector by using an embedded model; during work, the general knowledge graph can convert structured and unstructured data into semantic vectors, the semantic vectors are stored locally in the form of the knowledge graph, and cross-domain knowledge accurate retrieval is supported in combination with a fine-grained tree pruning technology. The knowledge integration model is based on an approximate nearest neighbor clustering method, so that integrated output of a plurality of large language models can be realized, and the hit rate of answers with relatively high credibility is effectively improved.

The invention relates to the technical field of information processing, and discloses an urban multi-department heterogeneous data knowledge graph construction method and system, a terminal and a storage medium, and the method comprises the steps: determining entity objects, description attributes and association relationships of an urban multi-department heterogeneous data ontology model; according to the entity object, the description attribute and the incidence relation, using a rule engine to extract entity records, attribute information and relation information from the city multi-department heterogeneous data; organizing the entity objects, the entity records, the attribute information and the relation information in combination with a storage structure of a graph database to obtain an initial knowledge graph; and calculating a space-time semantic similarity according to the initial knowledge graph, and fusing different entity records with co-reference problems according to the space-time semantic similarity to obtain a target knowledge graph. According to the method, semantic association, knowledge integration and entity co-reference resolution of cross-department data are realized by constructing the knowledge graph, and intelligent decision support from a global perspective is provided for urban governance.

The invention discloses an OVER-NAV vision-language combined navigation system and method, and belongs to the technical field of intelligent navigation.The system comprises a navigation server, a user handheld terminal and a navigation terminal.The navigation server comprises a vision module, a language obtaining module, a vision map module, a semantic map module and a multi-modal feature cross-modal interaction module; the core of the system is that a multi-modal feature cross-modal interaction module comprises a topology-aware heterogeneous modal representation unified framework, a differential geometry inspired dynamic attention guidance mechanism and a heterogeneous knowledge integration and collaborative optimization framework, and deep fusion of three modals of visual information, a language instruction and a semantic map is realized; according to the method, the navigation accuracy is remarkably improved, the natural language instruction understanding accuracy reaches 92%, the high recognition accuracy is still kept in illumination changing and noisy environments, and the method is particularly suitable for complex shopping mall environments, outdoor-indoor seamless transition navigation and other scenes.

The invention discloses a federal map learning method and system based on feature space construction and sharing. The method and system are used for solving the problems of feature space isomerism, harmful knowledge integration and insufficient personalized performance in federal map learning in a cross-domain Internet of Things environment. The method comprises the following steps: constructing a globally consistent feature space, and realizing node feature alignment through random walk feature generation and standardization; designing a client hybrid feature encoder (CHFE), and combining global features (MLP encoding) and local features (GCN encoding) to generate hybrid representation; proposing an independent adaptive aggregation strategy (IAA), and dynamically calculating an aggregation weight based on the domain similarity, the model similarity and the gradient similarity; a personalized regularization mechanism (PPT) is introduced, and global collaboration and local optimization are balanced. The method significantly improves the convergence speed and generalization ability of the model under heterogeneous data, reduces the communication overhead, and is suitable for privacy sensitive scenes such as medical treatment and industry.

The invention relates to a hierarchical retrieval method and device based on multi-modal questions and answers, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of receiving multi-modal input data, wherein the multi-modal input data comprises image data and corresponding to-be-answered question data; performing encoding processing on the document data and the multi-modal input data in the preset knowledge base to obtain a feature vector of the document data in the preset knowledge base and an image feature vector of the multi-modal input data; according to feature vectors of document data in a preset knowledge base, performing at least one time of text retrieval in the preset knowledge base for the image feature vectors to obtain a text retrieval result; and integrating the text retrieval results into an input sequence, inputting the input sequence into the multi-mode question and answer model, and generating a corresponding answer text of the to-be-answered question data. By adopting the method, the retrieval effect and the knowledge integration efficiency can be improved, and the performance and the flexibility of the multi-modal question-answering system are enhanced.

The invention provides a logical reasoning-driven knowledge graph enhanced large model generation method, and belongs to the technical field of knowledge graph enhanced large model generation, and the method comprises the steps: 1, preparing a data set; step 2, extracting and screening a triple; step 3, triple conversion and knowledge graph construction; 4, obtaining an original query question; 5, extracting user question keywords; step 6, graph query engine construction and query execution; and step 7, integrating and generating knowledge. Compared with a traditional manual construction method, the method has the advantages that the manual construction cost is remarkably reduced, and the construction efficiency of the knowledge graph is also improved.

The invention discloses an intelligent multidisciplinary clinical consultation system and method based on a large language model, and relates to the technical field of medical artificial intelligence. According to the structured consultation suggestion set, the association degree value of the possible disease causes and the consultation departments is calculated in combination with the medical knowledge graph, the departments participating in the consultation are automatically matched, and the consultation sub-targets are determined, so that the problem of lack of interdisciplinary knowledge integration and dynamic coordination ability in the prior art is solved, and the situation that diagnosis and treatment only depend on a single subject is avoided; meanwhile, a multi-disciplinary consultation set is formed by counting the disease cause matching number, calculating the treatment emergency value and the priority index, determining the consultation sequence of consultation departments, obtaining consultation content according to matching of consultation sub-targets and clinical guidelines, and determining the application treatment scheme in combination with patient replies and historical treatment records; according to the process, multidisciplinary knowledge is integrated, comprehensive diagnosis and treatment suggestions are provided for the patient, and the defects of the prior art on a multidisciplinary cooperation overall solution are overcome.

The invention discloses a case analysis method and system based on a large language model, and belongs to the technical field of case analysis, and the method comprises the following steps: S1, patient information input, S2, examination item recommendation and determination, S3, preliminary diagnosis generation, S4, case screening and diagnosis and treatment suggestion generation, S5, diagnosis and treatment process monitoring and adjustment, and S6, case report generation and viewing. By means of the powerful knowledge integration and reasoning ability of a large language model, in combination with massive historical case data and professional medical database information, multi-dimensional diagnosis thought reference is provided for doctors, the misdiagnosis and missed diagnosis risks caused by personal experience limitation are reduced, the health indexes of patients can be monitored, and the diagnosis accuracy is improved. Personalized adjustment is performed on the diagnosis and treatment plan according to the disease change and the diagnosis and treatment condition of the patient; the medical database can dynamically expand and correct contents; diagnosis and treatment plans and suggestions can be given according to diagnosis and treatment passes of previously cured patients with similar conditions.

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 discloses a method for constructing a cultural relic knowledge organization, expression and characterization model for a Song charm theme. The method comprises the following steps: S1, constructing a knowledge classification system according to Song charm Shaoxing cultural relic types; s2, modeling knowledge entities and association thereof by using a semantic network; and S3, performing semantic representation of entities and relationships by using the multi-modal data. According to the method, systematic classification and semantic association of cultural relic knowledge are realized, and the structured level of cultural relic data is improved; the accuracy of knowledge reasoning and recommendation is improved, and intelligent service capability is provided for related fields of cultural relics; cross-medium and multi-dimensional knowledge integration and expression are supported, and technical support is provided for research and propagation of cultural heritage; meanwhile, the method is high in universality and can be popularized to other cultural heritage protection scenes, and wider value application is achieved.

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 provides an outline content generation method and system combined with natural language processing, and the method comprises the steps: firstly carrying out the medical semantic analysis of a medical question text inputted by a user, obtaining a question feature set, calling a medical literature database interface for retrieval based on the question feature set, and obtaining a matched medical literature knowledge set; extracting medical knowledge units with independent semantics from the literature knowledge set to generate a structured knowledge unit set, performing association matching on the structured knowledge unit set and the question feature set, distributing weights according to question type identifiers and information demand strength parameters to generate a weighted knowledge integration result, and performing knowledge integration on the weighted knowledge integration result; and finally, generating a medical question answering text according to a weighted knowledge integration result, and feeding back the medical question answering text to a user interaction interface for display, so that accurate, comprehensive and personalized medical question answering can be provided for the user, and the question answering quality and the user experience of a medical academic community are improved.

The invention relates to the technical field of artificial influence weather, and discloses an artificial influence weather knowledge graph construction method and system based on a large model. The method comprises the steps that multi-source meteorological data are collected and preprocessed to generate a standardized data set; extracting a meteorological feature set by using the pre-trained large model; detecting a data dynamic change frequency, and starting a dynamic strategy to switch and mark an abnormal data segment when the data dynamic change frequency exceeds a threshold value; in combination with a similarity matching result of the historical knowledge graph and the current features, decomposing the feature set of the non-abnormal data segments to generate knowledge feature subsets; correcting the knowledge feature subset based on the coupling relationship between the meteorological kinetic parameters and the environmental parameters; and reversely backtracking the key influence factors along the weather influence propagation map, and constructing the knowledge map. According to the method, multi-source data are integrated through standardized processing, abnormal data are dynamically identified, historical knowledge and physical mechanism are combined to correct features, key factors are finally backtracked to complete graph construction, and the method is suitable for knowledge integration and analysis in the field of artificial influence weather.

The invention belongs to the technical field of intelligent electric charge questions and answers, and particularly relates to a hierarchical knowledge network construction and retrieval method for intelligent electric charge questions and answers. The invention provides an iterative adaptive enhanced RAG method, based on a hierarchical knowledge network, information retrieved by a first round of problems is used as a knowledge carrier, newly retrieved information is continuously updated into initialized information in subsequent multi-round iterations, information is adaptively collected from the perspective of knowledge increase, and the information retrieval efficiency is improved. New knowledge and collected knowledge are flexibly integrated, and the problem that information interaction among different retrieval steps is insufficient is solved; in addition, a self-adaptive exploration stopping strategy is formulated, uncertain active retrieval is replaced, time deviation of active retrieval prediction is effectively avoided, and continuous knowledge increase is ensured.

The invention relates to the technical field of medical information processing, and discloses an intelligent prescription auxiliary issuing system and method based on generative artificial intelligence and a storage medium, and the system comprises a multi-modal input module, a model generation module, a knowledge integration module, a prescription generation module, an auditing optimization module and a prescription output module. The method corresponds to the system, and the storage medium corresponds to the method. According to the application, the limitation of function fragmentation is avoided, diagnosis and treatment instructions, personalized habits of doctors, dynamic medical knowledge and risk control requirements are cooperatively and comprehensively planned through the modules, a medication safety base line is kept through risk grading verification, optimization suggestions are generated according to diagnosis and treatment habits of the doctors, meanwhile, the accuracy and efficiency of prescription making are improved, and the application prospect is wide. The comprehensive requirements for safety, personality and high efficiency of prescription assistance in clinical scenes are fully met, powerful support is provided for diagnosis and treatment work of doctors, and medication safety and treatment effects of patients are indirectly guaranteed.

The invention relates to an unmanned aerial vehicle cluster task planning system of a task space unified view. The unmanned aerial vehicle cluster task planning system comprises an LLM-based high-level task allocation decision module, an SAC-based low-level path planning control module, an RAG knowledge integration-based multi-modal representation learning module and a closed-loop self-adaption and continuous improvement module. An advanced task allocation decision module performs advanced reasoning and thinking chain task decomposition by using LLM, and dynamically optimizes an agent reward function; the low-level path planning control module optimizes continuous path planning of the unmanned aerial vehicle based on SAC reinforcement learning; the multi-modal representation learning module fuses the heterogeneous perception data and the historical experience of RAG retrieval, and constructs a unified potential state representation aided decision; and each module is tightly coupled with a closed-loop self-adaptive mechanism, and self-adaptive adjustment reward signals are fed back in real time. The system effectively solves the problems of path crossing, non-uniform resource allocation and the like, improves generalization ability and decision-making precision, and realizes faster convergence and better performance in a complex scene.

The invention relates to the technical field of government affair data analysis, and discloses a government affair SaaS architecture and method based on cloud edge collaboration, and the government affair data processing method based on cloud edge collaboration comprises the steps: obtaining government affair scene feature data, and generating scene semantic representation; the scene semantic similarity is calculated, and the knowledge migration potential is evaluated; analyzing semantic features of a target scene, and screening clients participating in training based on scene similarity; processing the client model, and dynamically adjusting the aggregation weight according to the scene similarity and the model contribution degree; global model knowledge is extracted, and a target scene local model is optimized; through organic combination of federated learning technologies of scene semantic understanding and scene perception, the limitation that data privacy protection and scene specialization model training cannot be realized at the same time in the traditional technology is overcome, and the technical problems of cross-scene knowledge integration and scene specialization service in government affair data analysis are effectively solved.

The invention discloses a dialogue type AI intelligent outbound service automatic control method combined with a knowledge graph, and the method comprises the following steps: S1, constructing a multi-dimensional knowledge graph: integrating a domain ontology, a user portrait and a dialogue context, and forming a structured knowledge network; s2, dynamically generating a dialogue strategy: fusing rule reasoning and a machine learning model, dynamically selecting a dialogue strategy path based on a user response probability, and screening an optimal strategy through conflict detection; s3, real-time interaction control: realizing multi-round management through voice recognition, intention classification and dialogue state tracking, and triggering an emergency strategy in combination with sentiment analysis and silence detection; and S4, dynamically optimizing the system: updating knowledge graph entities / relationships by utilizing incremental learning, and optimizing strategy parameters and business rules in real time through reinforcement learning and association analysis. According to the method, the knowledge integration efficiency is improved, and the CRM data association response time is from gt; the result is reduced to 1t in 2 seconds; 200 milliseconds; the high-net-value customer conversion rate is improved by 42%, and the manual intervention demand is reduced by 70%.

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 the technical field of education systems, in particular to an intelligent teaching assistance system and method based on a skill atlas, and the method comprises the steps: uploading the technical atlas; collecting ideological education events and ideological education vocabularies to obtain a fusion module; performing semantic recognition on the skill map to form a professional text; extracting all keywords in the professional text by using a language model to obtain a plurality of value vectors; after obtaining the ideological education event and / or vocabulary with the highest value similarity with the keyword, forming a mapping relationship; the ideological education events and / or vocabularies mapped by the keywords are selected and packaged as insertion examples to be inserted to obtain a technical map; detecting the learning effect of the student on the technical map through the model; according to the method, the ideological education events corresponding to the keywords are associated with the vocabularies, so that interdisciplinary knowledge integration is realized, and course content upgrading is realized; and finally, the detection module is used for detecting the insertion effect and then adjusting the insertion effect, so that excessive insertion is avoided.

A platform for creating, managing, and deploying digital twins of human experts through automated behavioral capture and analysis. The platform employs a data collection system that monitors and processes digital interactions, communications, and work patterns to create AI-powered digital representations of subject matter experts. These digital twins maintain the knowledge, decision-making patterns, and communication style of the original subject while preserving privacy and confidentiality boundaries. The platform includes systems for managing multiple instances of digital twins across different organizations, with capabilities for instance-level learning and knowledge integration. A comprehensive licensing and rights management system enables controlled distribution of expert digital twins while ensuring appropriate privacy and security controls are in place. The platform maintains continuous compliance monitoring and privacy enforcement across all twin instances, allowing for scalable deployment of expert knowledge while maintaining security and confidentiality requirements.

Ontology-based dynamic learning and knowledge integration are performed from measurement data and text. Relationships between entities and entity states are inferred from data, text, and user input. Searching, integrating, visualizing and comparing relations are used to extract domain-specific knowledge, particularly in bioinformatics.