118 results about "Dynamic reasoning" patented technology

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 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 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 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 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 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 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 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.

The invention relates to the technical field of fault positioning, and discloses an indoor distribution multi-source data fusion fault positioning system based on reinforcement learning, which comprises a space-time tensor construction module, a federated collaborative detection module, a map reasoning positioning module and a prediction scheduling module, and is characterized in that a multi-source space-time data federated learning framework under privacy protection is constructed; and cross-physical domain dynamic reasoning and resource elastic scheduling of the fault propagation chain are realized. According to the method, through fusion of multi-source spatio-temporal data and federal collaborative learning, fundamental transformation from passive response to active prediction is realized, fault root causes in a complex environment can be accurately identified, and the false alarm rate is significantly reduced; equipment deadlock is effectively avoided by a dynamic resource scheduling mechanism, and the operation and maintenance efficiency is improved; the privacy protection design ensures the safety of cross-domain cooperation, meanwhile, the environmental perception capability enhances the robustness to hidden faults such as electromagnetic interference, and finally, a fault prediction-positioning-scheduling full-process closed loop is constructed.

The invention provides a medical diagnosis reasoning method and system based on multi-agent coevolution, and the method comprises the steps: driving a large-scale language model to decompose a medical problem through a problem decomposition agent, and determining a to-be-retrieved sub-problem through a self-adaptive retrieval agent, and selecting a proper knowledge base and a proper retrieval algorithm to obtain multi-source retrieval data, and verifying that the intelligent agent performs de-reforming synthesis on the data to obtain an integrated abstract. The expert recruitment agent builds an expert team according to the abstract, the expert agent diagnoses and reasones to build a dynamic reasoning library, the reasoning library is iteratively optimized through judgment, cross reasoning and the auto-reflection physician agent, the dynamic convergence controller monitors the reasoning library, iteration is terminated when conditions are met, and a final diagnosis decision is output. According to the method, information is directionally obtained from a plurality of authoritative and professional medical knowledge bases through problem multi-granularity retrieval and population evolutionary reasoning, and reasoning efficiency can be improved while reasoning correctness is guaranteed.

The invention discloses an artificial intelligence model dynamic reasoning method and system based on a consumer-level heterogeneous chip, and relates to the technical field of artificial intelligence and computer processing. The method is operated on a heterogeneous processor integrating a CPU (Central Processing Unit), a GPU (Graphics Processing Unit) and an NPU (Network Processing Unit), by monitoring hardware states such as load, temperature and available memory in real time and combining an AI model hierarchical structure and operator characteristics, reasoning calculation tasks are dynamically allocated to an optimal processing unit, namely, the CPU is responsible for task arrangement and serial logic, the GPU executes large-scale parallel calculation, and the NPU processes and optimizes a neural network layer. And the results are integrated cooperatively. The system adopts a dynamic inference engine, realizes efficient and low-energy-consumption operation of a large-scale AI model on resource-constrained equipment, improves response speed, protects local data privacy, and is suitable for various consumer electronics needing AI capability.

A multi-hop reasoning method based on dynamic reasoning guidance and multistage self-feedback retrieval belongs to the field of natural language processing, and comprises the following steps: deconstructing a multi-hop reasoning process into a target-oriented sequence decision problem, carrying out dynamic reasoning guidance by using a large language model, generating a sub-problem sequence matched with a reasoning progress in real time, and carrying out multi-level self-feedback retrieval on the sub-problem sequence; target document retrieval is guided, and sub-questions are dynamically generated; according to the generated sub-questions, obtaining associated documents by adopting a three-level collaborative retrieval mechanism; and performing information refining on the associated document through a large language model, fusing the refined information into an inference chain, and performing inference to generate an answer. The invention further discloses a multi-hop reasoning system, a storage medium and a computer program product. The method aims at solving the complex multi-hop problem that multiple dispersed knowledge fragments need to be integrated, high-accuracy and high-efficiency reasoning is achieved, the retrieval requirement is dynamically generated through an explicit thinking chain guiding mechanism, and evidence obtaining is optimized and redundant information is filtered in combination with a three-level self-feedback retrieval mechanism.

The invention provides an educational policy retrieval method and system fusing a policy corpus and a large model, and relates to the technical field of artificial intelligence. Firstly, through a dynamic knowledge network construction module, an educational policy knowledge graph capable of being dynamically updated is constructed from four dimensions of time, space, effectiveness and a subject, version evolution, regional application and effectiveness relationships among policies are accurately modeled, and a structured basis is provided. And secondly, based on the map, a collaborative inference engine analyzes the complex intention of natural language query of the user by using a generative artificial intelligence model subjected to field fine tuning, and ensures that interpretation answers are accurate and compliant through a controllable generation technology under knowledge constraints. And finally, the feedback optimization system enables the system to be continuously adaptive and evolved by collecting multi-dimensional user behaviors and dominant feedback, mining high-frequency contradictory points in policy execution and driving bidirectional optimization of a knowledge graph and a generative model, and dynamic reasoning and closed-loop optimization of educational policy interpretation are realized.

The invention provides a dynamic reasoning chain construction and dependency task arrangement method and device based on an MCP agent, and relates to the field of artificial intelligence. The method comprises the following steps: acquiring context information input by a user, and acquiring a current task environment of a target agent based on the context information; based on a task environment, combining context information and taking a task target as a guide to construct a target reasoning chain; performing task dependency analysis on the target reasoning chain, and constructing a target dependency graph based on element constraint conditions; performing topological sorting on the target dependency graph through a graph isomorphic coding sorting model, and outputting an ordered task sequence with priority labels; and constructing a dynamic scheduling framework based on the ordered task sequence, and outputting a task processing result corresponding to the task target according to the dynamic scheduling framework. According to the method, the problem that the task execution efficiency of an existing multi-agent task arrangement method is remarkably reduced when the task targets are diversified and a complex dependency relationship exists among the task nodes is solved.

A neural network compression system based on lexical attention score dynamic pruning comprises an input module, a mask generation module and a dynamic reasoning module, attention scores are directly introduced into a pruning decision to quantify the importance of an internal structure of a model, fine pruning based on real attention distribution is achieved, and the accuracy of pruning is improved. The distortion problem of a traditional weight amplitude-based method is avoided; according to the method, lexical elements are divided through semantic clustering, independent masks are generated in each class, and class-level pruning granularity is constructed, so that a model structure is more adaptive to input semantic features, performance stability is kept under a high pruning rate, lexical element classes are identified based on a KNN algorithm, and the masks are dynamically called; sparse strategy switching during reasoning is realized, reasoning efficiency and model precision are both considered, and a new dynamic control path is provided for lightweight reasoning of a large model.

The invention relates to a fault prediction method and system for parameter fine tuning and adaptive structure pruning based on business influence driving, and belongs to the technical field of artificial intelligence, time series data analysis and intelligent operation and maintenance. Comprising the following steps: S1, business influence data modeling: integrating multi-source operation and maintenance data and historical business fault event data, and constructing a business influence quantitative model; s2, efficient fine tuning of service influence guide parameters: loading the pre-training fault prediction model, and performing efficient fine tuning of the parameters on the basis of service influence signals; s3, business influence driven adaptive structure pruning; S4, dynamic reasoning and alarm generation: realizing a dynamic reasoning mechanism of a pruned fault prediction model, and generating a structured and business value oriented fault prediction alarm according to a reasoning result; and S5, performing closed-loop optimization and continuous evolution. According to the invention, the configuration accuracy of the operation and maintenance resources is improved.

The invention discloses a real-time dynamic reasoning optimization method and system for an AI gateway, belongs to the technical field of artificial intelligence and edge computing, and aims to solve the technical problems of how to optimize the real-time dynamic reasoning capability of the AI gateway, improve the real-time reasoning efficiency of the AI gateway under complex tasks and improve the real-time reasoning efficiency of the AI gateway under complex tasks. According to the technical scheme, the method comprises the following steps: model lightweight preprocessing: constructing an AI model by adopting a lightweight network architecture, and reducing the model calculation complexity and the number of parameters by using a deep separable convolution and channel shuffling technology; carrying out model compression processing of pruning, quantification and knowledge distillation on the constructed model; real-time dynamic reasoning and decision making: in the operation process of the AI gateway, monitoring the complexity of input data, the real-time requirement of a current task and the use condition of computing power resources of the AI gateway in real time, and performing self-adaptive reasoning strategy decision making according to a monitoring result; reasoning engine and compiling optimization; data preprocessing and edge intelligence are realized; and edge-cloud collaborative reasoning.

The embodiment of the invention provides a test case generation method and device, a storage medium and a program product. In the embodiment of the invention, in the process of converting the historical path record of the UI automatic test into the structured knowledge graph, semantic modeling of the path unit is realized through the entity relationship template, so that the test logic has a cross-device and cross-version abstract reuse capability, and most logic can still be reused when the actually measured display interface element changes; a page-element-relation triple is automatically extracted by using a large language model, and a queriable three-dimensional network structure is constructed, so that the complex path analysis efficiency is greatly improved; based on the dynamic reasoning ability of the knowledge graph, advanced test cases for abnormal path detection, behavior prediction and the like can be automatically generated, and the case design time is remarkably shortened. Therefore, cross-version, cross-device or cross-resolution multiplexing of the test case is realized, the test efficiency can be improved, and the test cost can be reduced.

The invention relates to the technical field of model training, in particular to a dynamic retrieval enhancement reasoning method based on reasoning compression, which comprises the following steps of: performing sub-query generation task training and query feedback generation task training on a retrieval enhancement model to obtain a supervision fine tuning model; and performing reinforcement learning on the supervision fine tuning model and then outputting the model, and optimizing configuration format rewards and reasoning rewards of the supervision fine tuning model in the reinforcement learning process. In order to solve the problems that in the prior art, a dynamic retrieval enhancement model is low in retrieval efficiency and too long in reasoning chain, sub-query generation and query feedback generation processes of the retrieval enhancement model are trained in a supervised fine tuning mode, the sub-query generation accuracy and query feedback generation accuracy of the retrieval enhancement model are optimized, and the retrieval efficiency of the dynamic retrieval enhancement model is improved. And the length of the inference chain is optimized through the format reward and the inference reward, so that generation of unnecessary inference chains is reduced while the problem feedback response effect is ensured, and efficient dynamic inference application of an external knowledge base is realized.

The invention discloses an investment strategy configuration method and device based on form semantic analysis and dynamic reasoning, relates to the technical field of strategy configuration, and discloses an investment strategy configuration method based on form semantic analysis and dynamic reasoning. Performing semantic analysis on the investment task description and the structured form field to obtain structured task description; generating multi-source investment information according to the structured task description; according to the structured task description, the multi-source investment information and the historical market data, generating a target combination scheme in a preset market scene; determining a disturbance feature vector according to the target combination scheme, and generating a re-optimization task description according to the disturbance feature vector; and optimizing the candidate asset weight configuration scheme according to the re-optimization task description, a preset difference penalty coefficient and the weight vector of the current position, and determining an investment strategy configuration scheme. Therefore, the self-adaptive construction of the investment portfolio under the market disturbance is realized.

The invention discloses a dynamic reasoning method and system for industrial design multi-modal constraint verification. The method comprises the steps that an input geometric image and a problem text are converted into formalized language description of the same symbology system through an analyzer; inputting the formalized language description into a symbol solver, and solving the symbolized representation of the geometric problem by introducing a named relationship and a state machine; under the condition that input questions are given, similar questions with question solving theorem guidance are found out, and contents and thinking directions of the similar questions serve as a part of cue words Prompt to participate in construction of the thinking tree; a geometric reasoning normal form of a tree-shaped structure is adopted according to the thinking tree, proposal and evaluation are conducted in combination with a large language model, whether a stopping condition is met or not and whether searching is continued or not are judged through a controller, and the optimal problem solving path and the problem solving process are determined. The method can fully stimulate the capability of a large model in the field of plane geometry problems, effectively fuses geometric information and text logic, and achieves a good question and answer effect.

The invention discloses a cross-domain multi-modal dynamic reasoning and generating method and system for space sensing equipment linkage, a terminal and a storage medium, and the method comprises the steps: carrying out the weighted fusion and space-time alignment of multi-source heterogeneous equipment sensing data, and forming a cross-domain space sensing data flow with a unified reference; based on real-time spatial topology and business constraints, dynamically dividing semantic collaboration areas and establishing visual mapping; for each region, fusing spatial semantics, text and visual information, and generating a region cooperative control strategy; rendering the visual content in parallel according to the mapping relation and synchronizing the equipment state; and outputting a result through area-level quality reflection evaluation, if all the data reach the standard, carrying out protocol adaptation and linkage output, otherwise, starting a local regeneration protocol for an area which does not reach the standard, re-calibrating data, updating a strategy and rendering. According to the invention, multi-device collaborative millisecond response, cross-protocol non-stop adaptation and anomaly localization repair are realized.