192 results about "Case base" patented technology

The invention discloses a fault root cause positioning method and system driven by a dynamic knowledge graph, and relates to the technical field of fault root cause localization, and the method comprises the steps: collecting and obtaining a multi-source fault associated data set, carrying out the entity association extraction of the multi-source fault associated data set, and obtaining a fault entity set and an entity relationship set; performing graph node cascading and incremental learning updating, and constructing a fault updating knowledge graph; monitoring and acquiring target fault data, performing mode matching reasoning, and generating a fault mode candidate root cause set; and performing similarity matching on the fault mode candidate root cause set in combination with a historical fault case library, and determining a target fault root cause positioning result. The technical problem of low fault diagnosis efficiency caused by inaccurate fault root cause positioning and knowledge graph updating lagging in the prior art is solved, and the technical effects of realizing accurate positioning of the fault root cause and dynamic improvement of the knowledge graph and improving the fault diagnosis efficiency and accuracy are achieved.

The invention discloses a circuit EMI suppression-oriented multi-knowledge collaborative distillation and optimization method and system, and the method comprises the steps: constructing a basic large language model based on the circuit design of the electronic industry as a student model, and carrying out the adaptive optimization of the circuit design field. Thirdly, integrating the formalized EMI rule base, the simulation data / model base and the expert experience case base, constructing a multi-source heterogeneous teacher knowledge system, and generating a comprehensive guidance signal G; then, candidate circuit design generated by a student model is evaluated through the system, and a multi-objective loss function including basic distillation, rule conformity, performance fitting and expert experience consistency is constructed; according to the method, the universality is reserved by quantifying differences, compliance is ensured through punishment, the performance difference is reduced, dynamic weight adjustment is introduced, and the model performance reaches a preset target through iterative distillation. The model can understand and process terminologies and design rules in the field of circuit design, and the defect that a general AI model lacks domain knowledge is overcome.

The invention discloses a fault diagnosis method and system for a coil cutting all-in-one machine based on a large language model, and relates to the technical field of equipment fault diagnosis, and the system comprises a table data intelligent processing module, a knowledge base construction module, a diagnosis reasoning module and a user interaction module. The table data intelligent processing module is used for carrying out automatic fault mode labeling and description standardization on a cutting and rolling all-in-one machine fault diagnosis case library provided by a user; the domain knowledge graph construction module is used for integrating the standardized table database and automatically constructing a domain knowledge graph; the diagnosis reasoning module is used for performing fault diagnosis reasoning based on a large language model and a knowledge graph; and the user interaction module provides a multi-modal user interaction interface and supports visual display of fault diagnosis. Therefore, by adopting the fault diagnosis method and system for the cutting and winding all-in-one machine based on the large language model, the intelligent level of fault diagnosis can be improved, the knowledge base construction and expansion cost can be reduced, and the usability and maintainability of the system can be enhanced.

The invention discloses an operation and maintenance knowledge intelligent question and answer interaction method, device and equipment based on an LLM large model. According to the method, questions of operation and maintenance personnel are received through a natural language interaction interface, semantics are analyzed through a pre-trained LLM, candidate answers are generated, the accuracy of the answers is verified in combination with a dynamic operation and maintenance knowledge graph (including equipment model and fault code mapping, a historical case library and a real-time updating knowledge base), and finally a verification result is returned. The device comprises an input module, a processing module, a verification module and an output module, the processing module integrates domain knowledge fine tuning and real-time data integration functions, and the verification module supports multi-source data fusion and confidence evaluation. The platform adopts a multi-tenant architecture, supports visual diagnosis, automatic equipment operation and knowledge use report generation, and ensures that data cannot be tampered through a block chain technology.

The invention relates to the technical field of large model algorithms, in particular to a knowledge distillation-based field large model lightweight adaptive method and system, and the method comprises the steps: obtaining knowledge distillation parameters and student model performance parameters, and building a nonlinear mapping relation between the knowledge distillation parameters and the student model performance parameters; the optimal parameter combination is optimized and solved based on the mapping relation, and target knowledge distillation parameters are generated; issuing the target parameters to a training engine, monitoring performance deviation in real time and triggering re-optimization; in the reasoning process, performance fluctuation is monitored, and model characteristics are managed and controlled; target domain data characteristics are collected, a mapping relation is corrected in combination with big data analysis, and the domain adaptation capacity is improved; a knowledge base and a case base of historical distillation data are constructed, a standardized adjustment scheme is formed, and self-adaptive matching is achieved. According to the scheme, through precise modeling, dynamic optimization, real-time monitoring and knowledge reuse, the knowledge distillation efficiency, model robustness and field adaptability are remarkably improved, and systematic technical support is provided for large model lightweight.

The invention relates to a bidding document total-factor blind-state desensitization method fusing multi-modal artificial intelligence, and the method comprises the following steps: S1, obtaining an original bidding document package, carrying out the data preprocessing, and obtaining a standardized document set; s2, according to the standardized document set, performing multi-modal content identification and alignment to obtain a multi-modal content library; s3, constructing a sensitive information classification system based on domain expert knowledge and a historical case library; s4, constructing a dynamic rule base according to the sensitive information classification system; s5, according to the multi-modal content library and the dynamic rule library, in combination with deep learning, multi-modal sensitive information intelligent detection is carried out, and a sensitive area set is confirmed; and S6, based on the dynamic rule base, performing intelligent desensitization on the sensitive area set to obtain a desensitized document. According to the method, the risk of sensitive information leakage is effectively reduced while the bidding file expression effect is improved.

The invention discloses an intelligent class case retrieval method and system based on reinforcement learning self-feedback, and the method comprises the following steps: S1, constructing a multi-level semantic understanding framework, carrying out the semantic understanding of a query case through the multi-level semantic understanding framework, and generating a complete semantic representation; s2, carrying out multi-dimensional similarity calculation and sorting optimization on the query case and historical discriminants in the candidate case library; s3, constructing a dynamic user portrait and optimizing a recommendation strategy; and S4, establishing multiple rounds of dialogues and context awareness, and carrying out visual display and feedback mechanism optimization. According to the intelligent class case retrieval method and class case retrieval system based on reinforcement learning self-feedback, a more accurate, efficient and reliable law intelligent retrieval system is finally achieved, judicial practice requirements are met, and quantitative and measurable technical progress is achieved in the aspects of retrieval accuracy, sorting quality, personalized service, law adaptability and the like.

The invention discloses an LLM central multi-agent tool arrangement and virtual-real closed-loop evolution scheduling system. The system comprises an intelligent sensing module, a knowledge module, an intelligent scheduling decision module and a closed-loop execution module. The intelligent sensing module collects real-time and multi-modal data of a physical environment and outputs structured sensing data, the knowledge module is used for constructing a knowledge graph and a historical task case library, and the intelligent scheduling decision-making module takes a large language model (LLM) as a core scheduling center, receives and analyzes task instructions, fuses the structured sensing data and graph and case information, and performs task scheduling on the knowledge graph and the historical task case library. Generating a decision scheme according with a constraint condition by using knowledge enhanced reasoning, and continuously optimizing in multiple iterations to generate a decision instruction; and the closed-loop execution module receives and drives the execution end to execute the decision instruction. According to the method, an intelligent closed-loop system of perception-decision-execution-evolution is constructed, and global optimization and high-reliability self-adaptive scheduling of multi-machine collaborative welding are realized.

The invention discloses a power grid fault intelligent diagnosis method and system based on multi-mode cooperation, and belongs to the technical field of power system fault diagnosis. The method comprises the following steps: collecting and off-line importing multi-modal data of primary equipment and secondary equipment of a multi-space power system in a power grid fault range in real time and standardizing the multi-modal data, and sequentially inputting the standardized multi-modal data into a local edge professional model, the method comprises the following steps: preliminarily reasoning fault properties in combination with a local knowledge base, inputting a knowledge-embedded causal reasoning large model deployed at a cloud end, generating an edge-cloud fault collaborative diagnosis model, iteratively updating the edge-cloud fault collaborative diagnosis model in combination with a multi-modal fault case library, and converting newest collected and imported power grid fault data into a multi-modal fault case library; and inputting the updated edge-cloud fault collaborative diagnosis model, generating a latest fault diagnosis report, and realizing the intelligent diagnosis of the power grid fault based on multi-modal collaboration. According to the invention, the power grid fault reason analysis performance and the identification accuracy are improved.

The invention relates to the technical field of data governance, and discloses a data governance method based on an intelligent decision engine, which comprises the following steps: carrying out business semantic classification and marking on preliminarily processed real-time streaming data, and constructing a data portrait library; constructing a dynamic topological graph, learning an abnormal propagation rule based on a graph neural network, analyzing an influence range and establishing an influence grading mechanism; performing multi-dimensional quality evaluation on the data, and generating a dynamic data quality score and a grading strategy; constructing a data quality historical problem and reason case library, and generating a quality anomaly root cause judgment and influence quantification report by using a large language model agent; generating a candidate strategy set, and selecting an optimal governance strategy from the candidate strategy set by establishing a multi-objective optimization model; and performing compliance test and conflict identification on the optimal governance strategy by using a large language model agent, and dynamically adjusting the decision weight of a rule engine by using a reinforcement learning algorithm to realize a closed loop of data governance and dynamic learning.

The invention provides an intelligent contract risk identification method and device based on a big language model, and the method comprises the steps: constructing a legal knowledge graph and a risk case library, carrying out the structural processing of a contract text, carrying out the preliminary risk assessment through combining with a big language model, and carrying out the deep reasoning and case verification through combining with the knowledge graph. And generating a final report containing the risk type, the confidence coefficient, the reasoning chain and the modification suggestion, and continuously optimizing the model through user feedback data, so that efficient, accurate, explainable and adaptive optimization of contract risk identification is realized.

The embodiment of the invention discloses a method for intelligently assisting in reviewing a water conservation scheme of a water and soil conservation production and construction project, and the method achieves the intelligent feature matching of a new scheme and similar cases through the construction of a tagged knowledge base integrating historical cases of multiple industries, so as to recognize the generality compliance. A double-engine review mechanism is adopted, a form review module automatically checks document structure integrity and format specifications, and a logic review module executes cross-chapter data consistency check and business logic compliance analysis and highlights and positions error positions in a document. And recording decision logic in real time to form a feedback closed loop. And dynamically optimizing case library matching weight and recognition rules based on high-frequency error statistics and expert correction records. The modes of positioning review key points to chapters and sections, describing specific requirements of each review key point in a language, adding a check formula among data to review content needing to be calculated, determining a check type to which each review key point belongs, and the like are adopted, and the model is trained more clearly, so that the model has relatively professional review ability.

The invention belongs to the technical field of building construction automation and intelligent engineering management, and discloses a BIM-based electromechanical pipeline intelligent avoidance self-adjustment installation system, which comprises the steps of generating a three-dimensional point cloud model based on point cloud data and UWB positioning data, further constructing a four-dimensional space-time model, synchronously generating composite conflict quantification data, and performing BIM-based electromechanical pipeline intelligent avoidance self-adjustment installation. Correlation analysis is carried out in combination with construction specifications, and a space-time coupling semantic model is generated; fusing the penetrating scanning data of the millimeter wave radar and the UWB positioning data, and constructing a two-dimensional conflict thermodynamic diagram of a space margin-time window; generating a risk level conflict list in combination with a historical case library; generating a dynamic avoidance strategy list, refining the dynamic avoidance strategy list into an avoidance path execution scheme, verifying a strategy execution effect, judging a conflict elimination state, and generating an avoidance strategy execution state report; and evaluating the effectiveness of the avoidance strategy, dynamically adjusting the priority of the strategy, synchronously updating the dynamic BIM semantic model and the two-dimensional conflict thermodynamic diagram, and forming a strategy iteration closed loop.

The invention discloses an intelligent voice question-answering system and a knowledge reasoning method for operation and maintenance of power equipment. The system comprises a knowledge base construction module and a core question and answer engine module, the knowledge base construction module is used for constructing a power equipment knowledge graph and a fault case library, and the core question and answer engine module comprises a natural language understanding unit, a multistage semantic retrieval unit and a voice interaction ambiguity resolution unit. A natural language understanding unit identifies intent categories and power entities. The multi-stage semantic retrieval unit executes the following steps: matching in an ontology layer of the knowledge graph; performing extended query to obtain detailed information; and similar case matching is carried out in the fault case library. The voice interaction ambiguity resolution unit is used for executing disambiguation processing; analyzing the confidence and clarifying the dialogue; and triggering knowledge retrieval and reasoning and generating a sorting answer. The operation and maintenance efficiency is improved, the dependence on experts is reduced, the operation and maintenance quality and safety are improved, knowledge precipitation and sharing are promoted, the field work experience is improved, and scientific decision making is assisted.

The invention relates to the technical field of tunnel engineering monitoring and construction, and discloses a shield construction tunnel full deformation prediction method based on artificial intelligence. The method comprises the following steps: acquiring a geological sensing data stream, a construction operation data stream and a historical deformation case library; performing multi-modal data fusion on the geological sensing data flow and the construction operation data flow to generate a construction environment map with consistent time and space; searching a case sequence matched with the current construction environment map from a historical deformation case library, performing feature significance evaluation through the case sequence, and identifying a dominant feature group of full deformation prediction; constructing an algorithm preferential engine based on the dominant feature group; activating an algorithm preferential engine to perform parallel processing on the construction environment map, and generating an adaptability measurement set of each algorithm; integrating the adaptability measurement set and real-time construction limiting conditions, and selecting an optimal prediction algorithm by adopting a trade-off decision-making mechanism; and generating a full deformation prediction model, and integrating the model to a shield construction monitoring platform.

The invention relates to the technical field of power grids, in particular to a vertical domain distribution network planning method and system based on a large language model. The method comprises the following steps: collecting and arranging a distribution network structure and operation data, and constructing a'graph 'management system; extracting historical planning schemes to form a typical case library; fusing external open source data and source side data to establish a big database and an access interface; constructing a bilateral prediction model and a planning scheme generation model based on machine learning; carrying out secondary pre-training and practical packaging on the open source large language model; planning parameters are obtained in a guiding mode in a question-answer mode, and a scheme is generated. According to the method, the problems of high labor cost, long planning time, large error, unstable planning quality, poor interactivity, high learning threshold and the like of traditional distribution network planning are solved, the planning efficiency and precision are improved through an intelligent technology, the professional threshold is reduced, a brand new solution is provided for coping with the new situation of high permeability of new energy and electric energy replacement acceleration, and the method is worthy of popularization and application. And the practical value is remarkable.

The invention provides an external plug-in system based on retrieval enhancement. The external plug-in system comprises an indexing module, a retrieval module and a generation module, the index module is used for performing cleaning, segmentation, organization, semantic coding and storage tasks of text data; the index module comprises a dynamic data management sub-module, a strategy decision case library management sub-module, a Chinese character recursive segmentation sub-module, a tree index structure construction sub-module and a vectorization storage sub-module; the retrieval module is used for completing semantic matching and sorting on the basis of the structured index; the retrieval module comprises a double-tower rough arrangement sub-module, a cross fine arrangement sub-module, a real-time update sensing sub-module and a cache management sub-module; the generation module is used for carrying out integration and semantic modeling on the high-quality intelligence information provided by the retrieval module; the generation module comprises an information integration and reasoning sub-module and a credibility evaluation and feedback sub-module; the method supports fact alignment, real-time updating, logic interpretability and output evaluability.

The invention provides an intelligent auxiliary workflow system based on a localized large model and a dynamic knowledge base. The intelligent auxiliary workflow system comprises a localized large language model, a dynamic knowledge base module and an intelligent interaction engine. The dynamic knowledge base module comprises a policy and regulation base, a historical case base and a dynamic version control module; the intelligent interaction engine comprises an intention analysis module, a multi-stage retrieval strategy engine and a compliance verification module. The localized large language model is deployed in a private server. The policy and regulation library stores policies and regulations, and adopts a block vectorization technology to process long texts; the historical case library stores case information in a structured manner, and a correlation graph is constructed to support similar scene recommendation; and the dynamic version control module monitors a policy and regulation release channel API, automatically updates and marks an influence range, and carries out version management. According to the method, the problems of knowledge base updating lag, low retrieval efficiency, case base experience reuse and privacy security in a traditional office scene are solved.

The invention relates to the technical field of intelligent decision making, is suitable for the field of financial services, and provides a consultation intention recognition method for an insurance claim business, and the method comprises the steps: obtaining the consultation information of a client for the insurance claim business; carrying out vectorization processing on the consultation information based on a BGE-M3 model to obtain a consultation vector; searching a first knowledge fragment set associated with the consultation vector in a preset insurance claim knowledge base; extracting entities in the consultation information; determining an insurance claim settlement logic chain corresponding to the consultation information based on the entity and the first knowledge fragment set; searching case samples related to the consultation information in an insurance claim case library; and taking a preset prompt word, the case sample, the insurance claim settlement logic chain and the first knowledge fragment set of the client as input of a large language model, and determining a service processing analysis result for the consultation information through the large language model. According to the technical scheme, the processing efficiency and the automatic analysis quality of the insurance claim settlement service are improved, and the time and labor cost is reduced.

The invention provides a data analysis method and system based on case self-learning. The method comprises the steps of obtaining a target task input by a user; retrieving a historical case based on the target task; if the historical case is retrieved, extracting context parameters according to the target task to adapt a solution of the historical case, generating a customized solution and obtaining a first analysis result; if not, performing real-time planning through a large language model to generate a new solution and obtain a second analysis result; performing quality evaluation on the newly generated solution and the second analysis result; and when the evaluation result meets a preset storage condition, storing the new solution as a new historical case in the case library. Through double-path processing and quality evaluation feedback closed loop, the problems that in the prior art, a case library is prone to being polluted due to lack of quality evaluation, and multiplexing of historical cases is rigid and low in efficiency are solved, the self-learning quality can be guaranteed, and the analysis efficiency can be improved.

The invention belongs to the technical field of large models and data agents, and particularly relates to a question answering method based on a large model and a data agent, and the method comprises the steps: receiving and preprocessing a user question, and generating a question data set; judging whether external data support is needed or not by utilizing a large model, and if so, dynamically generating an agent calling strategy; real-time data acquisition, domain knowledge analysis, multi-source data fusion and logical reasoning verification intelligent agent cooperative execution tasks are scheduled according to a strategy; fusing the traceability information returned by the intelligent agent and the knowledge of the large model to generate a preliminary answer, and outputting the preliminary answer after interpretable optimization; and finally, optimizing the case library according to user feedback and iterating an agent calling strategy. All data agent processing results are attached with full-link traceability information, data sources and reasoning processes are presented in an explanatory optimization mode, and a user can verify answer basis.

The invention discloses an artificial intelligence-based intelligent question and answer method in the human society field, and relates to the technical field of artificial intelligence and government affair services. Comprising the following steps: collecting and cleaning laws and regulations, files, common questions and case library contents related to human society through a knowledge graph construction module; constructing a structured human social knowledge graph, and performing intention recognition and slot extraction on the content input by the user by using a pre-training language model through a natural language understanding module; context memory and state tracking are carried out through a dialogue management module, and multi-round dialogue logic is controlled for an interaction mode of inquiry, clarification and guidance; providing a voice and character dual-channel input and output interface; an answer generation module generates a natural language answer based on a human society knowledge graph query result, the natural language answer is used for visualized display of structured data, and an API interface can be called to obtain real-time data; user interaction behaviors and identity information are recorded through a user portrait and personalized recommendation module, personalized policy interpretation and service recommendation are provided in combination with a user portrait, and historical question and answer record retrieval and reuse are provided; and obtaining question and answer effect feedback through a feedback learning and adaptive optimization module, carrying out question and answer strategy optimization by utilizing a reinforcement learning algorithm, automatically discovering uncovered questions and triggering a knowledge base updating process.

The invention relates to the technical field of virtual reality simulation, in particular to a virtual reality immersive practical training content generation method, which comprises the following steps of: constructing a domain knowledge graph: extracting atomic knowledge elements representing operation actions, equipment entities, state parameters and safety rules from a standard document and a case library of a target training domain, establishing a multi-dimensional logic relationship including a causal relationship, a time sequence relationship, a hierarchical relationship and a probability relationship among the atomic knowledge elements, and forming and storing a domain knowledge graph; acquiring trainee data in real time; constructing and updating a student state model; a dynamic content decision step; and generating and injecting nonlinear practical training content. By collecting student data in real time and matching the student data with the knowledge graph, the system can provide accurate feedback for the student after each practical training, and help the student find and overcome own knowledge blind spots.

The invention relates to the technical field of enterprise management, in particular to an enterprise process custom configuration method and system based on a code-free technology, and the method comprises the steps: constructing a multi-layer directed hypergraph containing data, control and condition dependence, calculating an edge weight, and converting the dependence into a first-order logic constraint set; performing incremental satisfiability detection, and outputting a conflict core set containing conflict types and severity in combination with minimum unsatisfiability subset mining and strong connected component analysis; mapping the conflicts into modifiable elements, and generating parameterized candidate repair schemes based on a repair operation library and historical cases; converting the candidate scheme into a weighted constraint optimization problem, and solving an optimal scheme by adopting a branch and bound algorithm; influence propagation verification is completed in the copy, a differential patch and a rollback identifier are generated, transactional submission is carried out after passing, and the weight and the case library are updated. According to the method, automatic diagnosis and low-risk repair of implicit dependency conflicts are realized.

The invention discloses a case reasoning-based post-disaster decision scheme generation method, and relates to the technical field of disaster relief emergency decision. Comprising the following steps: establishing a historical case data and quantitative decision scheme library, establishing a post-disaster decision scheme framework, matching target cases by applying a case reasoning technology, selecting similar historical cases, and adopting the similar historical cases to quantify an emergency decision scheme. According to the method, response can be quickly started according to the decision framework, similar historical cases can be matched based on disaster information and disaster situation information, a targeted comprehensive decision scheme is further generated, decision scheme suggestions can be efficiently and accurately provided for decision makers, decision time is shortened, decision cost is reduced, and guidance is provided for post-disaster emergency management.

The invention discloses a volunteer service work order intelligent processing method and system based on multistage classification and similarity matching, and the method comprises the steps: carrying out the differential cleaning of a work order text and case data, constructing a structured template, and carrying out the label mapping coding; through coarse-grained classification of the second-level classification model, triggering fine-grained division of the third-level classification model when a large class is specific and the confidence coefficient is in a preset interval; retrieving associated historical cases based on a semantic similarity algorithm; and constructing a dynamic prompt template according to matched case elements, and calling a large model API to generate a mediation suggestion. Further, a paging mechanism is adopted to asynchronously process the work order, store the result and integrate an exception handling mechanism. According to the method, the work order processing intelligence level can be improved, and the classification and matching efficiency can be optimized. According to the method, field adaptive learning, hybrid index optimization and dynamic Prompt engineering are fused, an intelligent closed loop from work order analysis to mediation suggestion generation is constructed, and the matching efficiency of community service resources and the scientificity of decision making are remarkably improved.

The invention discloses an atmospheric pollution case system, a case analysis method and a medium, and the system comprises a basic information layer which is used for storing the whole-process feature data and treatment measure data of a pollution event; the logic analysis layer is used for carrying out quality control on the data, carrying out source analysis and cause analysis on the whole-process feature data of the pollution event after the quality control, and carrying out effect evaluation on the treatment measures after the quality control; and the comprehensive decision-making layer is used for comparing historical cases according to the retrieval conditions and matching similar historical cases, and finding out treatment measures corresponding to the similar historical cases according to the similar historical cases, or formulating targeted new treatment measures according to the corresponding treatment measures. The invention provides a'basic information-logical analysis-comprehensive decision 'three-layer progressive architecture case library, so that other modules can be conveniently expanded on the architecture of the case library subsequently; and multi-source data are systematically integrated, so that the problem of fragmentation of existing case data is solved.

The embodiment of the invention relates to the technical field of information, in particular to a speech recognition optimization method and system applied to online AI legal consultation. The method comprises the following steps: constructing a legal case library; voice content is recognized in real time, case plots are extracted, and the anxiety degree of a consultant is recognized; obtaining a plurality of prediction similar cases according to the extracted case plots and the identified anxiety degree; reading related legal terms, related subject descriptions and plot descriptions corresponding to all the prediction similar cases, and extracting keywords to obtain a keyword set; according to the plot influence singularity and the judgment trend uncertainty corresponding to all the prediction similar cases, obtaining a fusion singularity; and when the fusion degree exceeds a preset threshold value, matching the recognized words without definite semantics with the keywords in the keyword set again, and taking the keyword with the highest matching degree as a voice recognition result.

The invention relates to a judicial field case similar matching retrieval system and method, an element decomposition module is characterized in that original case materials are subjected to OCR recognition, text denoising and format unification to form a standardized file, and a standardized element set is output through a legal field named entity recognition model; the initial weight assignment module is used for constructing an element matrix for the standardized element set and carrying out weight assignment on each element in the element matrix; the retrieval intention analysis module is used for carrying out semantic understanding on the input application form, analyzing the retrieval intention of the input application form, dynamically adjusting element weights according to the retrieval intention and generating an element matrix after the weights are adjusted; and the vector matching module converts the dynamically adjusted element matrix into case vector representation, performs similarity matching with case vectors in a case library in combination with vector search, and outputs a plurality of historical cases closest to the current case in the aspects of legal structure and semantic key points and matching degree scores of the historical cases. And the response capability of similar case retrieval to the real intention of the user is effectively improved.

The invention discloses a vehicle load identification method based on a multi-modal large model, and the method comprises the following steps: selecting a reference bridge in a region for testing, and obtaining a reference bridge case library; analyzing the new bridge through a multi-modal large model, and matching a plurality of reference bridges most similar to the core characteristics of the new bridge from a reference bridge case library; the multi-modal large model migrates a load response model and model parameters of the reference bridge case to a new bridge through a case reasoning mechanism; and according to the structural difference between the new bridge and the matched reference bridge and the actual working condition of the new bridge, the multi-modal large model carries out architecture reconstruction on the migrated load response model. The method has the beneficial effects that the new bridge can directly reuse the model parameters and the load response rule of the reference bridge through the constructed reference bridge case library in combination with the retrieval enhancement generation and bridge-crossing knowledge migration mechanism of the multi-modal large model, so that the time cost and the economic cost of bridge-crossing deployment can be greatly reduced.