284 results about "Knowledge updating" patented technology

The invention discloses a method for enhancing dynamic knowledge retrieval based on a large language model, belongs to the field of knowledge retrieval, and aims to solve the problems of knowledge solidification, insufficient timeliness and illusion of a traditional LLM (Logistics Language Model). A multi-granularity knowledge base is dynamically constructed, and a rule and semantic partitioning technology is combined, so that a text is converted into a normalized vector, and a hybrid index is established; a two-channel retrieval triggering mechanism is adopted, keyword matching scores and BERT semantic probability analysis are fused, and retrieval requirements are intelligently judged; vectorization retrieval is realized through a BGE-M3 model, and candidate results are reordered in combination with a cross encoder to improve the precision. The system supports multi-language adaptive processing, dynamic switching of word segmentation strategies and cross-language retrieval, and introduces real-time knowledge updating and version control. According to the method, the answer timeliness and accuracy are remarkably improved, the context coherence of multiple rounds of dialogues is optimized, the method can be widely applied to the fields of intelligent customer service, professional questions and answers and the like, the LLM illusion risk is effectively reduced, and the knowledge traceability is enhanced.

The invention relates to the technical field of knowledge graph construction, and discloses a knowledge graph construction method and system based on a large language model technology. The method comprises the following steps: receiving a multi-source heterogeneous data stream, and completing semantic space mapping and cross-modal feature fusion to generate a unified semantic representation vector set; constructing an initial knowledge graph skeleton; performing incremental optimization on the skeleton, and performing entity relationship disambiguation and conflict detection; and iteratively updating the knowledge representation, and outputting a target knowledge graph meeting semantic consistency. The system comprises a data receiving module, a semantic fusion module, a skeleton construction module, an optimization module and a knowledge updating module. According to the method, multi-source heterogeneous data is effectively processed, the accuracy, the dynamic updating capability and the semantic consistency of the knowledge graph are improved, and the method has wide application prospects in the fields of intelligent question answering, information retrieval and the like.

The invention discloses a multi-modal bill processing method based on dynamic knowledge enhancement. The multi-modal bill processing method comprises the following steps: S1, constructing a dynamic knowledge base containing an aging weight; s2, synchronously processing text, image and format features of the bill by adopting a multi-modal feature fusion network to generate a composite feature vector; s3, semantic-level, format-level and timeliness three-level fusion retrieval is carried out based on the composite feature vector, and a three-level fusion retrieval engine comprises dynamic weighted sorting with timeliness attenuation, a difference degree triggered artificial review mechanism and a policy sensitive slope adjustment algorithm; s4, setting a multi-expert cooperative verification system, wherein the multi-expert cooperative verification system comprises cooperative work of a rule engine, a large language model and a logical reasoning module; s5, implementing a dynamic knowledge updating mechanism, and automatically triggering incremental learning of the knowledge base when policy change or format update is detected; and S6, outputting structured data, and synchronously generating an auditing traceability chain containing a decision path. According to the method, the key field identification accuracy can be improved, and auditing traceability and non-perceptual increment updating in the whole process are realized.

The invention provides a minority language professional question and answer method based on mixed retrieval and retrieval enhancement generation, which comprises the following steps: S1, constructing a multi-language knowledge constructing a vector index database and a term knowledge graph by using a multi-language model according to a related minority language document; s2, multi-layer mixed retrieval: cross-language document recall is realized through a multi-layer mixed retrieval module, and the multi-layer mixed retrieval module is composed of keyword retrieval, semantic retrieval and vector retrieval; s3, answer generation: performing answer generation through an adaptive multi-language model by using a retrieval enhancement generation module, and introducing rule constraint decoding and a dynamic attention mechanism in the generation stage to improve the professionality and accuracy of the answer; and S4, self-adaptive optimization and knowledge updating: through a user feedback reinforcement learning module, optimizing the model based on user error correction data and supervising updating of the knowledge base. According to the method, professional questions and answers of the minority language can be realized based on a small amount of professional data of the minority language, the recall rate of the document of the minority language is improved, and the generation quality is improved.

The invention discloses a scenic spot accompanying service method and a scenic spot accompanying service system based on linkage of a generative AI and a knowledge base, particularly relates to the technical field of artificial intelligence and smart tourism, and is used for solving the problems that core knowledge is forgotten and the answer accuracy is reduced due to dynamic knowledge updating of a generative AI model in an existing scenic spot guide system. The method comprises the following steps: extracting tourist question keywords in real time and retrieving a knowledge base to generate associated data; dynamically weighting the associated data priority based on the tourist aggregation density; generating an initial answer through real-time parameter adjustment; fusing the spatial-temporal clustering and the knowledge graph structure entropy to generate a weight factor; correcting the answer coverage defect and evaluating the result; outputting a final answer after directional addition of core knowledge iterative training; it is guaranteed that core knowledge of the scenic area is stably reserved in the dynamic learning process of the generative AI, meanwhile, the real-time scene requirement is accurately responded, and the reliability, accuracy and individuation level of the navigation service are remarkably improved.

The invention relates to the technical field of bidding and tendering, and provides a bidding document generation method, system and device and a storage medium, and the method comprises the steps: constructing a bidding knowledge graph through at least one of a policy and regulation library, a bidding document library and an industry standard library in a bidding knowledge base, and obtaining a bidding document generation result based on the project information of a bidding project and the bidding knowledge graph; and performing bid invitation file generation by applying the bid invitation file generation model to obtain the bid invitation file corresponding to the bid invitation project, thereby overcoming the defects of low efficiency, error proneness, poor flexibility and adaptability, knowledge update lagging and insufficient personalization in the existing bid invitation file production. A large model technology and a dynamically updated bid invitation knowledge graph are introduced to generate the bid invitation file, policies, regulations and project characteristics can be dynamically adapted, rapid and accurate bid invitation file generation is realized, the timeliness and reliability of the generated file are ensured, dependence on personal subjective experience is avoided, the flexibility is extremely high, and the application range is extremely wide.

The invention discloses a knowledge question and answer processing method fusing a large model and a knowledge graph, and relates to the technical field of artificial intelligence and natural language processing. Aiming at the defects of a traditional retrieval enhancement generation technology in the aspects of complex semantic association, context consistency and dynamic knowledge updating, the scheme adopted by the invention comprises the following two stages: knowledge graph construction and mixed index generation: collecting and processing internal and external multi-source data of an enterprise, and performing cleaning preprocessing such as coding normalization and de-duplication to obtain a mixed index; entities and relations are extracted through a pre-training model to generate a triple, a knowledge graph is constructed and stored in Neo4j, then a mixed index is generated through text and graph embedding fusion, and two types of retrieval are supported; retrieval and answer generation: obtaining user query, preprocessing, vectorizing, obtaining a candidate list through low-level semantic retrieval and high-level reasoning retrieval, fusing multi-dimensional indexes, rearranging and screening top-M candidates through Cross-encoder, constructing a JSON evidence list, and generating traceable answers through small model draft, large model fine calibration and consistency verification.

The invention relates to the technical field of the Internet of Things and artificial intelligence, and discloses an equipment maintenance fault intelligent analysis method and system based on the Internet of Things, and the method comprises the steps: representing an entity and a relation as a time function, and constructing a time sequence knowledge graph; monitoring vector change in the knowledge embedding space, detecting a concept drift phenomenon and mining an equipment performance evolution mode; constructing an equipment state transition model by using a recurrent neural network, predicting the future state of the equipment and evaluating the fault risk; collecting feedback processing knowledge conflicts and updating the model; generating multi-time-scale fault risk early warning and maintenance suggestions; according to the method, the knowledge acquisition efficiency is improved, dynamic knowledge support of the full life cycle of the equipment is provided, early recognition of gradient faults is realized, the method has adaptive knowledge updating capability, multi-dimensional fault analysis is provided, maintenance resource configuration is optimized, and the equipment management efficiency is improved.

The invention relates to the technical field of medical decision, and discloses a medical decision support system based on a knowledge graph, and the system comprises a knowledge graph construction module which constructs an initial knowledge graph based on a medical ontology library, and the knowledge graph comprises entities and association relationships of diseases, symptoms and drugs; the data acquisition module is used for acquiring data from an electronic medical record, wearable equipment, a medical literature library and a hospital information system and normalizing the data through a standardized protocol; the dynamic knowledge updating module is used for processing normalized data through an incremental graph neural network; a multi-source knowledge fusion module; a context awareness module; a dynamic deduction module; and a decision optimization closed loop module. And triggering a preset clinical rule in real time based on the pathological state of the patient, dynamically adjusting the intensity value of the related edge in the factor graph, and persistently storing the intensity value back to the knowledge graph, so that logic adaptation and individualized experience precipitation of general medical knowledge in a special pathological state are realized, and the individualized treatment accuracy is ensured.

The invention relates to the technical field of intelligent customer service, and provides an AI intelligent customer service system based on a large model, and the system is characterized in that an unstructured text processed by a multi-source knowledge fusion subsystem is reconstructed into structured knowledge entries with a multi-dimensional label system, intention classification and context association, and the structured knowledge entries are dynamically integrated into an enterprise knowledge graph; the response generation subsystem is used for receiving the content queried by the user, analyzing the intention through a deep semantic understanding model in combination with an enterprise knowledge graph, and dynamically maintaining the context in combination with a multi-round dialogue state tracking technology; meanwhile, emotion dimension analysis is carried out on the content, and a personalized response is generated by fusing user service feedback; and the autonomous optimization subsystem dynamically adjusts the weight distribution of structured knowledge entries in the enterprise knowledge graph and the priority of process nodes in combination with an attribution analysis result, and triggers a knowledge updating and API process reconstruction mechanism. The method has self-learning and continuous optimization capabilities, and continuously improves the service quality and the user experience.

The invention discloses a multi-agent cooperation enhancement method, system and equipment based on a knowledge graph, and the method comprises the steps: obtaining original data in an external environment, carrying out the preprocessing and feature extraction of the original data, generating a knowledge triple, storing the knowledge triple in a local knowledge graph, and submitting the knowledge triple to a shared knowledge graph for knowledge updating; when a to-be-executed task is received, decomposing the to-be-executed task by utilizing the large language model and querying global knowledge in the shared knowledge graph and local knowledge in the local knowledge graph to obtain a plurality of sub-tasks; a bipartite graph minimum cost matching algorithm is adopted to match a plurality of sub-tasks with the capability and availability of each agent to generate a preliminary task allocation scheme, and a large language model is utilized to optimize the preliminary task allocation scheme to generate an optimal task allocation scheme; and sending each task allocation knowledge fragment in the optimal task allocation scheme to a corresponding agent for collaborative execution through a semantic communication protocol.

The invention discloses a tunnel-landslide mass stability evaluation method based on space-time multi-scale coupling, and belongs to the field of tunnel-landslide masses, and the method comprises the following steps: S1, extracting a feature parameter set and an abnormal event mark set; s2, constructing a three-dimensional geological-mechanical model; s3, space-time multi-scale modeling of multi-physics field coupling is carried out; s4, outputting a stability prediction level by using the constructed ISSA-LSTM-GARCH combined prediction model; s5, generating an early warning in combination with an association rule engine; and S6, knowledge updating and systematic evolution of closed-loop optimization are carried out. According to the tunnel-landslide mass stability evaluation method based on space-time multi-scale coupling, multi-source monitoring data and a multi-physical field coupling model are fused, landslide mass stability under the influence of tunnel engineering is accurately and comprehensively analyzed through high-precision positioning and parameter inversion optimization, and powerful support is provided for engineering decision making.

The invention belongs to the technical field of mine ventilation monitoring, and aims to solve the problems that a traditional knowledge system based on a rule base has bottlenecks in the aspects of dealing with sudden working conditions, knowledge updating and semantic reasoning, and is high in construction cost and complex to maintain. The invention provides a mine ventilation knowledge graph construction method based on a large model, and the method comprises the following steps: S100, obtaining and cleaning a multi-source heterogeneous text related to mine ventilation, and obtaining a JSON format knowledge fragment of a unified structure; s200, constructing an ontology model and defining a semantic structure; s300, constructing four types of knowledge extraction tasks, and extracting entities, attributes and relationships; s400, constructing an entity alignment module; and S500, constructing a graph database structure. According to the method, automatic structured expression, semantic consistent fusion and intelligent visual query of knowledge in the mine ventilation field can be realized, and an interpretable, extensible and reasonable intelligent support platform is provided for a mine ventilation system.

The invention relates to the technical field of safety monitoring of constructional engineering, in particular to an intelligent construction safety monitoring system and method based on multi-modal data fusion, and the system comprises a plurality of modules: a 5GMEC-based heterogeneous data space-time alignment module which completes coordinate system conversion between laser point cloud and a BIM model by using an improved Fast-ICP algorithm; the feature level fusion network comprises a geometric feature branch (improved unscented Kalman filter processing point cloud normal vector) and a time sequence feature branch (LSTM processing stress sensor data); the NeRFXL fusion engine is used for fusing the point cloud and the video data by adopting a multi-scale neural radiation field; the multi-task anomaly detector is used for constructing a hierarchical Transform architecture and introducing a modal gating mechanism; and the dynamic knowledge graph engine constructs a knowledge graph updating module based on a graph neural network, and all the modules are in communication connection with one another and work cooperatively, so that functions of data processing, fusion, anomaly detection, knowledge updating and the like are realized.

The invention relates to the technical field of artificial intelligence, and discloses a professional knowledge question and answer intelligent customer service system based on a self-optimization mechanism. The system comprises a user intention analysis module, a knowledge processing module, a self-optimization learning module and an interactive presentation module. A semantic understanding unit of the user intention analysis module generates a user intention signal; after the knowledge processing module receives the signal, a knowledge retrieval unit outputs related knowledge fragments and confidence, an answer generation unit forms candidate answers, and a quality evaluation unit determines an optimal answer according to the confidence; in the self-optimization learning module, a feedback analysis unit adjusts answer generation parameters according to user interaction data, a strategy adjustment unit optimizes a retrieval strategy in combination with an optimal answer and a historical dialogue, and a knowledge updating unit updates a knowledge base depending on an external knowledge source; and a multi-round dialogue management unit of the interactive presentation module adjusts a dialogue process, and a visual presentation unit outputs a natural language text and collects user feedback to a feedback analysis unit.

The invention belongs to the technical field of new-generation information, and particularly relates to a power plant metal supervision entity relationship extraction method based on dual coding, which comprises the following steps: multi-modal data preprocessing: collecting and cleaning data, and carrying out data labeling; constructing a dual coding joint learning model: designing a network layer architecture, and training the dual coding joint learning model; constructing and querying a dynamic knowledge graph: extracting a model to generate a triple, and performing time sequence evolution analysis, causal reasoning interface and dynamic updating; and incremental knowledge updating and dynamic model optimization: an incremental learning and feedback module forms a bidirectional closed loop between the knowledge graph and the relationship extraction model, and continuous evolution of the system is ensured through dynamic knowledge updating and adaptive model optimization. According to the method, through bidirectional feature modeling of dual paths, collaborative representation optimization between entities and relationships is realized while context information is captured, so that the requirements of complicated data types and diversified semantic associations in an engineering scene are met.

The invention relates to the crossing field of industrial control system (ICS) safety and artificial intelligence, and particularly discloses a PLC high-interaction honeypot system based on multi-agent task splitting and RAG enhancement, which adopts a localized multi-agent collaborative architecture based on edge computing and is composed of a high-simulation equipment layer and an intelligent decision-making layer. The high-simulation equipment layer comprises a PLC dynamic mirror image, an HMI interface and a sensor data generator, and an active trapping environment is constructed through protocol fingerprint confusion and virtual and real data fusion technologies. The decision-making layer deploys a multi-agent task scheduling engine, integrates four kinds of agents including protocol analysis, behavior analysis, threat assessment and response generation, and realizes attack context perception and strategy dynamic generation based on a local RAG knowledge base. The load balancing agent dynamically allocates tasks according to equipment resources, and cooperates with offline knowledge update (USB flash disk encryption synchronization threat features) to form a closed-loop defense system, thereby ensuring physical isolation of an industrial network and realizing high-fidelity active defense.

The invention provides a multi-modal knowledge graph construction method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining a traditional Chinese medicine text; according to the traditional Chinese medicine text, candidate triples are generated through a large language model; generating a structured definition according to entities and relationships in the candidate triple; according to the structured definition, performing standardization processing on the candidate triad to obtain a standardized triad; according to the standardized triple, constructing an initial multi-modal knowledge graph by integrating multi-modal data; according to the initial multi-modal knowledge graph, constructing a theoretical layer knowledge graph through a neighbor perception filtering strategy; updating the theoretical layer knowledge graph through a dynamic knowledge updating mechanism; acquiring medical record data; constructing a real-world medical record layer knowledge graph according to the medical record data; and fusing the updated theoretical layer knowledge graph and the real-world medical record layer knowledge graph through an entity alignment mechanism and confidence fusion to form a multi-modal knowledge graph.

The invention discloses a medical knowledge question-answering system based on an RAG (Retrieval-Augmented Generation) architecture, relates to the field of artificial intelligence and natural language processing, and specifically comprises an input representation module, a knowledge retrieval module, a context construction module and a generation reasoning module. The input representation module is used for encoding user query and medical knowledge entries into high-dimensional dense vectors and comprises a semantic encoder; the knowledge retrieval module comprises a sparse retrieval unit, a dense retrieval unit and a fusion sequencing unit; the context construction module comprises a feature splicing unit and a code fusion unit; and the generation reasoning module calls a large language model based on the fused context to generate medical question and answer content in a natural language form. According to the system, by introducing the structured medical knowledge base and a mixed retrieval mechanism, the accuracy and specialty of questions and answers are effectively improved, the language model illusion phenomenon is reduced, the knowledge updating capacity is enhanced, and the system is suitable for application scenes such as clinical consultation and intelligent medical questions and answers.

The invention discloses an intelligent policy question-answering method and system based on retrieval enhancement generation and a medium. The method comprises the following steps: constructing a universal knowledge base and a plurality of mutually independent domain knowledge bases; in response to user input, the following steps are executed: performing routing analysis on the user input through a first large language model to generate a structured routing decision; retrieving the general knowledge base to obtain related general knowledge text segments and vectorization expressions thereof; according to the routing decision, a domain knowledge base corresponding to the at least one policy domain identifier is retrieved in parallel, and related policy text fragments corresponding to the at least one domain knowledge base and vectorization expressions of the related policy text fragments are obtained; obtaining an initial answer set based on retrieval results of the general knowledge base and the domain knowledge base; and performing intelligent fusion processing on the initial answer set through a second large language model, and generating and outputting response content. According to the method, the problem of knowledge updating lag is effectively solved, and the accuracy, timeliness and cross-domain specialty of policy questions and answers are improved.

The invention discloses an automatic building design modeling method and system combining LLM and MCP, and a whole-process design management system from user demands to automatic modeling and then to intelligent drawing checking and knowledge updating is constructed through four core mechanisms of'native large model reasoning + local knowledge base constraint + MCP protocol driving + man-machine closed-loop drawing checking '. Compared with a traditional single Revit secondary development framework, the design degree of freedom, the generation accuracy, the operation automation, the continuous optimization capability and the like are remarkably improved.

The invention provides a multi-modal big language model inference engine which comprises a pre-training big language model adaptation layer, a pollution remediation knowledge graph enhancement module, a multi-modal information understanding and fusion unit, a technology implementation optimization module and an inference chain and decision interpretation generator. The system adopts a hierarchical modular design, all components communicate through a standardized API interface, efficient and stable data circulation is ensured, and the problems of knowledge application limitation, opaque reasoning process, difficulty in professional knowledge fusion, knowledge updating lagging, limited multi-modal data processing capability and the like in the existing contaminated site remediation decision process are solved.

The invention belongs to the technical field of intelligent question-answering systems, and particularly relates to an intelligent question-answering inference system based on a knowledge graph, which is characterized in that firstly, a knowledge graph construction module fuses multi-source data to generate a structured graph, and after a user inputs a natural language question, a question-answering analysis module completes intention classification and entity disambiguation and converts the question into structured query; an inference engine module fuses symbol rules and graph neural network inference through a hybrid inference sub-module, and a dynamic weight adjustment sub-module optimizes weights according to errors and attenuation factors to generate an inference result; the knowledge updating module incrementally updates the atlas in real time and detects conflicts, the interactive interface module visually presents a result, and the evaluation optimization module iteratively optimizes parameters in combination with offline evaluation and online feedback. The whole process is from user question asking to result output, accurate reasoning and continuous performance improvement are achieved, and multi-field question and answer requirements are met.

The invention discloses a dynamic knowledge updating method and system based on an industry large model, and belongs to the technical field of natural language processing and machine learning, and the method comprises the steps: building a comprehensive knowledge base through systematic data collection and analysis, and precisely extracting key knowledge points through a natural language processing technology; through a dynamic and flexible knowledge updating system, industry dynamics and market trends are monitored in real time, and new knowledge is automatically identified and integrated by using a pre-trained industry large model; a knowledge fusion algorithm is adopted to intelligently identify and integrate association points between new and old knowledge, and conflict detection and multi-level verification are carried out; optimizing an industry large model by using the latest knowledge base data, including retraining and performance evaluation, and managing the updated model through a version control system; integrating and deploying the system; and continuous monitoring and maintenance are realized. According to the invention, when the user uses the industry large model, the latest industry knowledge information can be quickly and accurately obtained, so that the use experience of the user is greatly improved.

The invention relates to the technical field related to medical systems, in particular to a medical teaching and research integrated system based on a common bottom layer, and aims to break through information islands among medical treatment, teaching and scientific research and realize closed-loop linkage and dynamic knowledge conversion of a whole process. The system comprises a diagnosis and treatment decision subsystem, a scientific research queue management subsystem and a teaching subsystem, integrates data through a three-in-one data engine, and realizes information sharing and cooperative work. The diagnosis and treatment decision subsystem provides diagnosis and treatment support for severe diseases based on an expert thinking chain. And the scientific research queue management subsystem is responsible for screening cases, sorting data, implementing quality control and statistical analysis, and adjusting an expert thinking chain according to scientific research results. And the teaching subsystem carries out teaching by using a standardized case presentation mode. Through a feedback closed loop of clinical discovery, scientific research verification, knowledge updating and teaching feedback, rapid propagation and application of medical knowledge are promoted, and the medical service quality and the medical education level are improved.

The invention relates to the technical field of private domain knowledge updating, and discloses an MCP protocol-oriented private domain knowledge dynamic updating method and system, which monitor the change of a private domain knowledge source in real time through an updating agent component, and calculate a hierarchical hash abstract to efficiently detect a change event. Once the change is found, the change is compared with the root hash which is successfully notified last time, and if the change is different from the root hash which is successfully notified last time, an update notification is sent to a knowledge update service component through an MCP protocol. And after confirming the root hash difference, the receiving end requests the increment message to obtain the specific change content. And then, the updating agent component accurately locates the changed knowledge unit, extracts an incremental data packet and transmits the incremental data packet to the knowledge updating service component for application through an MCP protocol. Therefore, not only are unnecessary network bandwidth and computing resource consumption greatly reduced, but also the real-time performance and accuracy of data updating are remarkably improved, and powerful support is provided for efficient decision making of enterprises.

The invention discloses a flood control and emergency rescue plan generation method, which comprises the steps of S1, collecting flood control and emergency rescue original data, performing preprocessing and feature extraction, and labeling and confirming extracted feature data to serve as a training set; s2, performing LoRA fine tuning of a low-rank decomposition matrix on the basis of a pre-trained large language model, and performing large language model training operation through the training set; s3, constructing a flood control and emergency rescue field ontology model, learning distributed representation of the knowledge graph by adopting a graph neural network technology, and dynamically updating the knowledge graph and executing reasoning query according to real-time dangerous case information by establishing a dynamic reasoning mechanism; and S4, constructing a multi-modal information fusion framework which is used for carrying out information fusion processing on the knowledge graph reasoning result and then guiding the big language model to generate an emergency plan as a control signal. According to the method, the technical bottlenecks of low plan generation quality, difficulty in knowledge updating, insufficient multi-source information fusion and the like of a traditional method in a complex dangerous case scene are effectively solved.

An approach is provided for enhancing a generative large language model (LLM). An encoder, decoder, and generative associative memory network set are jointly trained to learn to store sentence encodings in a memory matrix used during decoding. The encoder and decoder are included in the generative LLM. The generative associative memory network set is included in an external memory unit. The external memory unit is external to the encoder and decoder. The generative LLM is augmented with the external memory unit in a framework that enhances the generative LLM. The external memory unit is updated with new information. Using the new information in the updated external memory unit, a knowledge update of the decoder is performed during an inference without fine-tuning or re-training the generative LLM. A response to a prompt during the inference is generated. The response is based on the knowledge update of the decoder.

The invention provides an intelligent question and answer method and device based on domain knowledge lightweight fine tuning and a cross-domain dynamic knowledge base and a readable storage medium thereof.The method comprises the steps that the cross-domain dynamic knowledge base is constructed, and multi-domain heterogeneous data is processed through a grading and blocking strategy; dynamic expansion and incremental updating are realized through hierarchical vector indexing (bottom-layer knowledge block embedding + upper-layer field incidence matrix); a two-stage lightweight fine tuning strategy is designed, a high-rank adapter is used for roughly aligning a field semantic space in a pre-access stage, and a low-rank adapter is switched for optimizing a retrieval result in a post-access stage, so that the consumption of computing resources is remarkably reduced; and on the basis of a domain correlation reordering model, the retrieval result is optimized by fusing the original similarity, the term coverage and the historical matching degree, and the cross-domain knowledge correlation is improved. Through closed-loop cooperation of the knowledge base, the fine tuning model and reordering, the problems of poor migration ability, knowledge updating lagging, high customization cost and the like in the traditional system field are solved.

The invention provides an emergency decision-making auxiliary system based on a knowledge graph. Comprising a data acquisition and processing module, a knowledge graph construction and reasoning module, an information retrieval and generation module, a multi-level reasoning and thinking chain prompting module, a multi-agent cooperation and game optimization module, an incremental learning and dynamic knowledge updating module and a block chain trust guarantee module. The emergency decision-making efficiency, accuracy, cooperation capability and safety are broken through, dynamic and complex emergency scenes can be effectively dealt with, and efficient, reliable and intelligent technical support is provided for decision makers.