154 results about "Dynamic reasoning" patented technology

A scalable platform for orchestrating networks of specialized AI multi-agent networks that enables secure collaboration through token-based protocols and real-time result streaming with advanced dynamic chain-of-thought pruning. The central orchestration engine manages domain-specific agents, implementing sophisticated multi-branch reasoning with contribution-estimation layers that evaluate each agent's utility using Shapley value-inspired metrics. The system employs information-theoretic and gradient-based surprise metric to guide memory updates and dynamic reasoning expansion, preventing local minima stagnation while preserving valuable insights through adaptive forgetting mechanisms. The platform unifies Monte Carlo tree search with contribution-aware estimation to detect high-synergy expert combinations while maintaining privacy through partial data approaches. It scales across distributed computing environments, enabling complex collaborative tasks like materials discovery, product engineering and manufacturing process design, biomedical research, and drug development. The system supports multi-party economic rewards through systematic contribution effort, cost and importance tracking, while standardized interfaces manage security, privacy, and policy constraints across heterogeneous agents.

The invention relates to the technical field of artificial intelligence, and discloses an AI intelligent auxiliary question answering system for student practice. According to the system, various interactive data such as texts, voices and handwritten formula images of students are collected through a multi-modal data acquisition module, semantic feature vectors of all modals are generated through a multi-dimensional feature analysis module, and then the semantic feature vectors are mapped to a unified semantic space through a cross-modal fusion module. The double-layer graph construction module constructs a domain knowledge graph and a learning behavior graph, and the dynamic reasoning and recommendation module generates a personalized problem solving path recommendation and knowledge point completion strategy based on fusion semantic representation and a graph library. In addition, the system also has the functions of interactive behavior log anomaly detection, path backtracking, knowledge forgetting curve prediction and the like. The system can comprehensively understand questions of students, provides personalized question answering service, and effectively improves the learning efficiency and knowledge mastering degree of the students.

The invention provides a vehicle active service system based on an end-side multi-modal large model and a dynamic reasoning method thereof, and belongs to the field of Internet of Vehicles, and the system comprises a multi-modal data collection module which collects multi-modal perception data of a vehicle; the multi-modal large model processing unit is used for carrying out feature extraction on the multi-modal sensing data to obtain features of different modals; the cross-modal attention fusion module is used for converting the feature data of different modals into a query, key and value triple and fusing the query, key and value triple to obtain fused features; the MCP dynamic reasoning controller is used for carrying out preliminary judgment on a vehicle scene based on the fusion features, collecting specific parameter data when further confirmation is needed, and generating an active service decision in combination with a user portrait and historical behavior data; and the active service execution module is used for generating a vehicle-mounted equipment control instruction and executing active service operation. According to the invention, real-time response and intelligent decision-making of vehicle-mounted active services are realized through an end-side multi-modal large model and an MCP dynamic reasoning protocol.

The invention discloses a large language model low-delay reasoning method based on dynamic reasoning graph optimization, and provides a low-delay reasoning method based on dynamic reasoning graph optimization. Constructing a template inference graph which can be rewritten and replayed, and establishing a template library according to input shape vectors; during reasoning, a template is matched with a distance threshold value, and only the attention / feedforward sub-graph is locally recaptured when the distance threshold value exceeds the threshold value; executing a forward execution graph, injecting a key value cache page pointer, numerical value precision and an adapter identifier, and performing playback; dividing the pre-filling and decoding sub-graphs to implement graph-level scheduling; switching the key operator when the key operator operates between a standard / fast kernel and different precisions; page-level backspacing of speculative branches is achieved through a shadow page table and reference counting, and batch and template selection is adjusted in a self-adaptive mode based on online indexes; compared with the prior art, the method has the advantages that the recapture and start overhead is reduced, tail delay and jitter are inhibited, and the hardware utilization rate and the service stability are improved.

The invention relates to the technical field of artificial intelligence and edge computing, in particular to an end-side cloud collaboration system based on a hybrid scheduling strategy. The end-side cloud cooperation system based on the hybrid scheduling strategy comprises a model segmentation module, a state sensing module, a reasoning scheduling module, a model compression and deployment module, an edge optimization engine and a communication synchronization module. According to the end-side cloud cooperation system based on the hybrid scheduling strategy, elastic deployment and dynamic reasoning of a complex model in a multilayer heterogeneous environment are supported, the system state can be sensed in real time, a scheduling path can be optimized, and the robustness of the system is improved; and in combination with model compression and edge operator optimization, the reasoning efficiency is remarkably improved, the communication load is reduced, and then low-delay cooperation between the terminal and the cloud is ensured.

The invention relates to a data query analysis method based on a natural language, which comprises the following steps of: analyzing a natural language query request input by a user into a dynamic semantic intention tensor which comprises an operation type, a comparison relationship, a time constraint and a data role semantic dimension, and dynamically combining according to task semantics to form a complete data query and analysis operation expression; mapping the natural language intention to a controllable data operation space of a database, and generating a preliminary data operation chain; performing side effect perception processing on the operation tensor, predicting a potential execution consequence of the operation, generating a side effect tensor for simulating a side effect of the database operation, and if any index in the side effect tensor exceeds a preset threshold value, performing local correction on the operation tensor; according to the method, a complex natural language query task is disassembled into a plurality of minimum semantic units by adopting a step-by-step semantic resolution mechanism, each unit is mapped into a specific tensor operation, and a dependency relationship between operation units is dynamically reasoned to generate an operation execution chain.

The invention discloses a multi-modal perception and optimization method and system for a low-power-consumption AR device, and the method comprises the steps: collecting multi-modal data, task demands, resource state data and environment data for the AR device; lightweight processing is carried out on the multi-modal neural network model through model pruning, parameter quantification and distillation technologies; inputting the collected data into a lightweight multi-modal neural network model for dynamic reasoning to obtain a multi-modal recognition result; comprising the steps of executing modal adaptive weight acquisition based on task requirements and environment data; executing energy consumption constraint scheduling according to the equipment resource state data, dynamically selecting a reasoning path strategy, and obtaining corresponding modal feature output; multi-modal feature fusion is carried out, task reasoning is completed, and a multi-modal recognition result is obtained; early-leaving control is executed based on a middle-layer confidence coefficient threshold value in the reasoning process; and interactively outputting a real-time multi-mode identification result. According to the invention, energy efficiency and precision balance and multi-mode fusion low-power-consumption optimization can be realized.

The invention provides an index-based data attribution analysis system, which relates to the technical field of data analysis, and comprises a data fusion layer, a dynamic graph engine and an attribution calculation layer, the data fusion layer is used for uniformly processing and integrating data from different sources to form a triple knowledge graph, and the sources comprise a service database, an event stream and an expert knowledge base; the dynamic graph engine is used for processing and analyzing real-time data, generating a corresponding risk propagation model and updating the knowledge graph to obtain a dynamic graph; the attribution calculation layer is used for dynamically calculating the risk value and the influence of each node according to the dynamic graph; and carrying out dimension contribution degree fusion attribution calculation to obtain a dimension contribution value. According to the method, the problems of poor adaptability and insufficient interpretability of attribution analysis are solved through a dynamic reasoning mechanism and a risk propagation model of the knowledge graph, and more accurate and real-time risk assessment and contribution degree analysis can be provided.

The invention discloses an intelligent construction and tracing method and device for an attack graph, and relates to the technical field of network security. The method comprises the steps of performing semantic analysis and entity relationship extraction on a multi-source heterogeneous security log according to a predefined structured security data model, and generating a standardized security entity relationship triple set; based on the set, taking an entity in an initial alarm as a starting point, and adopting an iterative closed loop driven by a large language model to dynamically construct an attack graph; and carrying out attack technique and tactics mapping and threat attribution based on the final map, and generating a response strategy of priority ranking. According to the method, automatic and high-precision source tracing and response of the attack chain are realized, and the problems that the prior art depends on static rules and semantic segmentation and lacks dynamic reasoning capability are effectively solved.

The invention provides a multi-agent cooperative task inference and robot scheduling system, which comprises an interaction unit used for acquiring a natural language instruction issued by a user, sending the natural language instruction to an intelligent processing unit and interacting with the intelligent processing unit, receiving an execution result of a task and body state information of a robot, and sending the received execution result to the intelligent processing unit; sending a task missing information supplementing request when the task information is missing; the intelligent processing unit is used for dynamically sensing an environment and a task state according to a user instruction, a body state and environment information fed back by the robot and stored memory, and performing dynamic planning and decision making based on a sensing result and an inverse result of a task execution result to realize task reasoning and robot scheduling; and the robot cluster executes tasks according to the action sequence and feeds back own body state information and environment information. According to the invention, through a multi-agent cooperation framework based on a large model, the robot is endowed with dynamic reasoning and active interaction capabilities, and the requirements of efficient task reasoning and cooperative execution in a dynamic environment are met.

The invention belongs to the technical field of neural network architecture, and particularly relates to a dynamic reasoning path optimization method based on neural architecture search, which comprises the following specific steps: S1, designing a neural architecture search algorithm: firstly defining a search space, then selecting a search strategy, and then setting constraint conditions; s2, constructing a dynamic reasoning path: firstly performing input data feature analysis, then performing reasoning path guidance based on a knowledge graph, and then predicting the reasoning path by using a model according to the input data features and the knowledge graph; and S3, model training and optimization: firstly carrying out joint training, and then carrying out model compression and acceleration. According to the method, through neural architecture search algorithm design and dynamic reasoning path construction, the problem of computing resource waste is effectively solved.

The invention relates to the technical field of intelligent teaching, and discloses an intelligent teaching system and method based on a large language model. The system comprises a teaching intention analysis module, a knowledge graph adaptation module, a dynamic reasoning engine module, a teaching strategy generation module and a feedback optimization module. The teaching intention analysis module is used for disassembling the teaching interaction instruction into a knowledge domain label and a teaching behavior sequence through a semantic segmentation engine; and the knowledge graph adaptation module is used for matching the subject knowledge graph and extracting an associated knowledge node set. The dynamic reasoning engine module inputs the node set into a large language model to complete multi-hop reasoning, and an intermediate state vector containing a reasoning path is generated; and the teaching strategy generation module generates a hierarchical teaching strategy in combination with the vector path weight and the behavior sequence timestamp. The feedback optimization module collects user behavior data, updates knowledge graph matching rules through incremental learning, and adapts to diversified teaching requirements.

The invention belongs to the technical field of data analysis, and provides a questionnaire-based sentiment analysis method, system and equipment in order to solve the problem of inaccurate user sentiment analysis in the existing questionnaire. Using a pre-trained language model to extract a semantic vector of the topic text, and combining with the co-occurrence frequency of the multiple topic options to generate node-level local features; carrying out dynamic reasoning by adopting an improved graph neural network model, calculating a dynamic attention coefficient based on semantic similarity calculated by a topic text semantic vector and a jump probability between topics, and weighting and aggregating neighbor features, so as to obtain context-associated topic node features; the global emotion is calculated by using the PageRank thought, a final emotion analysis result is obtained, dynamic context association generated due to questionnaire jump logic is effectively captured, and the reliability of grasping the overall emotion venation of the user is improved.

The invention discloses an autoregressive language model training process-oriented data leakage risk quantification method, which comprises the following steps of: executing enhanced member data division processing on an original training text set, and generating a ternary partition text set containing member, non-member and key boundary texts through an optimization function; for each text, using the target model to extract member attributes from three channels of forward reasoning, back propagation and state evolution, and fusing the member attributes into member attribute vectors; inputting the member attribute vector into a hierarchical comparison embedded network, and mapping the member attribute vector into an optimized embedded representation vector through comparison learning including similar clustering, heterogeneous separation and boundary positioning; and inputting the embedded representation vector into a dynamic reasoning classifier capable of perceiving a training stage, judging the risk membership degree of the dynamic reasoning classifier, and generating a data leakage risk quantification result. According to the invention, real-time and fine-grained dynamic quantification can be carried out on the leakage risk, and timely early warning is provided for model training.

The invention relates to the technical field of software architecture design, and discloses a software architecture design method based on intelligent bionic implementation of a large model group. The method comprises the steps of obtaining software design requirement input; performing multi-level semantic analysis on software design requirement input to generate an initial component set and context environment description; based on the context environment description, candidate component knowledge related to the initial component set is retrieved from a distributed knowledge base; performing consistency verification on the candidate component knowledge and the initial component set by utilizing a dynamic inference engine to generate a verified component map; according to the verified component atlas, candidate software architectures are generated through an architecture template matching algorithm; and performing iterative adjustment on the candidate software architecture by adopting an optimization strategy, and outputting a target software architecture design. Through collaborative analysis and intelligent reasoning of the large model group, automation and intelligence of software architecture design are achieved, and the efficiency and quality of software design are improved.

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.

The invention discloses an energy internet intelligent key node identification and elasticity enhancement method and system, and the method comprises the steps: 1, constructing and dynamically maintaining a semantic enhanced energy internet digital twin super network and a multi-modal knowledge graph, fusing multi-dimensional information, and achieving the self-evolution and dynamic reasoning capability; 2, based on the model, fusing multi-time scale prediction data, and adaptively evaluating the dynamic comprehensive criticality of the node through an intention-function-resource-vulnerability four-layer penetrating traceability model; 3, aiming at the key nodes, generating an intelligent attack strategy by utilizing a generative adversarial network, deducing an information physical cascade failure process by combining multi-agent deep reinforcement learning, and quantitatively evaluating the system elasticity; and step 4, based on an evaluation result, generating a self-adaptive security reinforcement and dynamic reconstruction decision oriented to active immunity and elastic optimization. According to the method, the accuracy and the dynamism of key node identification can be remarkably improved.

The invention discloses a task disassembling method based on a large model, and aims to automatically disassemble requirements input by a user into a series of independent and accurate minimum sub-tasks so as to support high efficiency and intelligence of task execution. Different from a traditional natural language processing method, the method adopts a large model technology to intelligently analyze and optimize input demand content, so that task description is clearer, and operability is achieved. The method comprises the following steps: firstly, deeply analyzing and adjusting a demand by utilizing the understanding ability of a large model to make the demand accord with a logic structure of task execution; then required core steps and logic levels are extracted through a multi-level task decomposition algorithm, and clear sub-task chains are generated through step-by-step decomposition; by means of the adaptability and dynamic reasoning ability of the large model technology, the decomposition efficiency and accuracy of complex tasks are remarkably improved, the burden of a user in the aspects of task planning and execution is relieved, and efficient and automatic development of intelligent task management is promoted.

The invention relates to the technical field of natural language processing, in particular to an AIGC content safety monitoring system and method based on dynamic reasoning and context awareness, and the system comprises a semantic graph construction module which is used for extracting entity nouns and predicate verbs in a text according to a received AIGC interaction text flow, generating a semantic concept node set, and sending the semantic concept node set to a database; and performing directed connection and hierarchical nesting on the concepts in the semantic concept node set according to a logic direction according to a subject-predicate-object dependency relationship rule. According to the method, the curvature value of the semantic track is calculated, and the similarity between the direction vector and the center of the sensitive semantic cluster is combined for double verification, so that sudden turning of an intention in a dialogue process or progressive induction to a sensitive field can be perceived, and abnormal mutation can be recognized through a curvature pulse form; therefore, hostile attack behaviors are accurately captured in real time in dynamic interaction, and the defense capability for context dependent attacks and implicit induction behaviors is improved.

The invention discloses a knowledge graph-based intelligent question and answer method for text travel. The method comprises the following steps of: obtaining and preprocessing related data in a text travel service system; constructing a structured knowledge graph in the text travel field; constructing a candidate entity pair and executing relation extraction and weight updating guided by a behavior sequence; dividing and generating a behavior preference sub-graph according to a behavior mode, and extracting a text travel knowledge slice set according to a theme; natural language questions of tourists are received, and path search and semantic aggregation with behavior weights and path structures as constraints are executed; and generating a text travel intelligent question-answer result through a question-answer generation engine, and recording a text travel question-answer interaction log for iterative updating. According to the method, knowledge graph modeling and behavior guiding relation extraction technologies are fused, dynamic reasoning and personalized question and answer generation of the travel knowledge are achieved, and the method has the advantages of being accurate in semantic understanding, high in answer association degree and continuous in self-adaptive evolution.

The invention provides a video question-answering system and method based on iterative multi-mode, and the method comprises the steps: carrying out the preprocessing of an input original video file and natural language query, extracting a key frame sequence, and generating an initial subtitle sequence; performing multi-granularity retrieval based on the preprocessed natural language query and the current subtitle sequence, and determining a candidate region; carrying out fine-grained frame selection in the candidate region by using a large language model, and identifying a key frame; based on the candidate area and natural language query, determining the type of the visual information to be supplemented and generating a multi-modal cue word corresponding to the type, and extracting the visual information by the visual language model according to the multi-modal cue word to update the subtitle sequence of the candidate area; generating a prediction answer by adopting a large language model and a visual language model; and judging the confidence of the generated predicted answer, and outputting a final answer. According to the method, the processing mode of video understanding can be optimized, and an accurate cross-modal coordination solution is provided through dynamic reasoning-sensing coordination.

The invention provides a college laboratory safety management and risk identification intelligent agent platform, which relates to the technical field of safety management, and comprises the following steps: obtaining environmental parameters through edge computing nodes to carry out real-time risk analysis, and setting multi-level safety threshold grading early warning; a mixed decision framework combining a graph neural network and reinforcement learning is adopted, a dynamic reasoning mechanism is constructed based on a security management knowledge graph, and intelligent research and judgment and co-processing of multi-dimensional security risks are realized; and finally, feeding back a disposal result to a safety management personnel terminal. According to the invention, the laboratory safety risk identification precision and the emergency disposal efficiency are improved, and intelligent safety management is realized.

The invention discloses a multi-modal data dynamic reasoning system and method based on a cognitive map, and relates to the technical field of map data management.The method comprises the steps that text, voice and image data input by a user are extracted, user data are analyzed, and a structured interaction record is generated in combination with a user identifier and a timestamp; analyzing historical interaction records, detecting continuous query events of the same user for similar questions, gathering negative feedback signals, analyzing repetition frequencies of repeated events in the used user, and analyzing feedback intensity coefficients of output repeated behaviors; positioning corresponding nodes in the cognitive map according to the repeated behavior characteristics, analyzing attenuation coefficients, activating associated alternative reasoning paths, and outputting a to-be-updated node set and candidate paths; and adjusting the node weight based on the attenuation coefficient, updating the weight according to the semantic relevancy of the candidate path, updating the atlas connection relationship, and outputting the optimized cognitive atlas. Abnormal conditions are identified, the knowledge graph node weight is adjusted, and the analysis accuracy is improved.

The invention is suitable for the technical field of artificial intelligence, and provides a reinforcement learning-based child rearing question and answer reasoning large language model generation method, which comprises the following steps of constructing a multi-source heterogeneous child rearing knowledge base, and generating a professional knowledge vector database; generating a complex professional thinking chain data set through multi-stage data screening and dynamic reasoning engine design; performing full-parameter supervised learning fine tuning on the basic question and answer model based on the thinking chain data set to obtain a fine tuning question and answer model; based on the composite reward function, reinforcement learning optimization is carried out on the fine tuning question and answer model, and a child rearing question and answer reasoning big language model is generated; utilizing the RAG technology to assist the reasoning process of the child rearing question and answer reasoning big language model, and combining with the latest professional knowledge to generate a final reasoning conclusion; according to the method, the problem that base model knowledge falls behind is solved through the RAG technology and the professional child rearing knowledge database, and the answer accuracy of the child rearing question-answer reasoning large language model is improved through assistance of external knowledge.

The invention discloses a cross-modal-based multi-modal neural network dynamic reasoning path optimization method and system, and the method comprises the steps: carrying out the modal type classification of original multi-modal data, carrying out the quick feature extraction, carrying out the feature fusion of all modal early features obtained through the quick feature extraction, and obtaining multi-modal early features; reasoning path selection is carried out according to the multi-modal early-stage features to obtain each modal reasoning path, and feature fusion is carried out on the late-stage features of the modal obtained after full-quantity feature extraction is carried out on the modal selected as full-quantity feature extraction and the modal early-stage features corresponding to the modal selected as the modal skipping full-quantity feature extraction; and reasoning to obtain a specialized task result. According to the characteristic that a correct prediction result can be obtained by using a partial modal reasoning result according to some multi-modal tasks, an improved self-adaptive reasoning path selection method is constructed, the overall multi-modal network calculation amount is fully reduced, delay is reduced, energy overhead is reduced, and the prediction efficiency is improved. And finally, the deployment and landing of the multi-mode network in a future autonomous system scene are accelerated.

The invention belongs to the technical field of the vertical field, and particularly relates to a bid invitation file intelligent editing system based on a vertical model, which comprises a data acquisition module, a data processing module, a knowledge graph construction module and a bid invitation file generation module. The data acquisition module acquires project information and multi-modal data of a bid invitation project; the data processing module preprocesses unstructured files in the bid invitation knowledge base by using a TextRank algorithm and a BiGRU algorithm to generate structured data with dynamic weight tags; the knowledge graph construction module constructs a bid invitation knowledge graph based on a time sequence knowledge graph, an entity life cycle management algorithm and relation dynamic reasoning; the bid invitation file generation module generates a preliminary bid invitation file through a vertical generation model, and generates a final bid invitation file through multi-dimensional verification. According to the system, intelligent and efficient compilation of the bid invitation file is realized, and the compliance, integrity and standardization degree of the file are remarkably improved.

The invention discloses an intelligent sports event decision-making system based on causal-driven multi-modal fusion and spatio-temporal dynamic reasoning. The system comprises a multi-modal causal data acquisition and preprocessing module; a causal-oriented multi-modal knowledge graph construction and updating module, wherein the causal-oriented multi-modal knowledge graph construction and updating module is provided with a causal structure learning algorithm and an online learning framework; a space-time perception hybrid agent module; the causal constrained dynamic decision optimization module is provided with a deep reinforcement learning algorithm; and the interpretability analysis and visualization module is used for receiving the decision strategy sent by the space-time perception hybrid agent module, generating decision explanation according to the decision strategy and visually presenting the decision explanation. The objective of the invention is to construct an intelligent system capable of providing high-precision, interpretable and adaptive decision support by integrating causal reasoning, multi-modal learning and reinforcement learning, so as to significantly improve scientificity and effectiveness of sports event analysis and decision.

The invention provides a dynamic retrieval enhancement recommendation method based on graph reasoning, and aims to solve the problems that an existing recommendation system is difficult to capture dynamic interest changes of a user and the article recommendation effect is poor, and intelligent recommendation is realized by constructing a dynamic reasoning graph structure of user behaviors, memories and candidate articles in combination with a graph neural network. Specifically, a dynamic memory retrieval module is designed, and key modes are extracted from historical behaviors of a user to construct a memory library; the current state of the user, the retrieval memory and the candidate items are constructed into a heterogeneous reasoning graph, and dynamic classification and weight distribution are carried out on memory nodes through a graph attention network; meanwhile, a reinforcement learning mechanism is introduced, recommendation effect indexes serve as reward signals, and a graph reasoning strategy is optimized in an end-to-end mode; according to the method, the problems of user interest drifting and object exposure insufficiency in a recommendation system are effectively solved, the transparency of recommendation decisions is improved through an interpretable graph reasoning path, and the performance of the recommendation system and the user experience are improved.

The invention discloses a disease type prediction method and system based on a medical bill and a pseudo-label mechanism, and the method comprises the steps: obtaining a medical bill set which comprises a medicine list, a doctor-seeing department and patient portrait information, and carrying out the standardization preprocessing, and generating standardized bill data; respectively inputting the standardized bill data into a dynamic reasoning knowledge base and a pre-trained large language model, generating a first pseudo-label disease set through a rule reasoning engine, and generating a second pseudo-label disease set through the guidance of a semantic understanding cue word template; and fusing the two pseudo-label disease category sets to obtain a fused pseudo-label, training a multi-label disease category classification model by taking the fused pseudo-label as a target, and finally realizing disease category prediction of the to-be-predicted medical bill data. According to the invention, through a dual pseudo-tag generation mechanism fusing rule reasoning and a large language model, the problem that the medical bill data lacks a real disease category tag is solved, the accuracy and reliability of disease category prediction are improved, and a reliable solution is provided for deep utilization of the medical bill data.

The invention provides an intelligent scheduling, scheduling and handover system based on a multi-modal AI and a knowledge graph, and the system comprises a scheduling unit which determines scheduling information according to multi-modal data, an AI scheduling model and a dynamic knowledge graph; wherein the dynamic knowledge graph is of a personnel-shift-handover event-business rule-equipment five-layer association graph structure, and updating is completed according to a scene inferred by the scene-based dynamic inference engine and a conflict arbitration mechanism; the shift change unit determines shift change information according to the shift arrangement information and the service information of the previous shift; and the intelligent interaction unit responds to an interaction instruction of the user and completes a shift change process according to the shift change information. According to the invention, the dynamic knowledge graph of five-layer association of personnel-shift-handover event-business rule-equipment is constructed, and the multi-modal AI technology is combined to realize intelligent cooperation of the whole process of shift arrangement and handover, so that a data island is effectively broken, the shift arrangement rationality and handover normalization are improved, the operation risk is reduced, and the scheduling efficiency is improved.