50 results about "Hybrid reasoning" patented technology

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

The invention is suitable for the field of power station equipment management, and provides a power station equipment health management system based on multi-modal perception and hybrid reasoning, and the system comprises a data perception layer which is used for obtaining and preprocessing multi-modal perception data of power station target equipment, and obtaining multi-modal feature data; the hybrid reasoning layer is used for taking the multi-modal characteristic data as input of a pre-constructed hybrid reasoning model to obtain an equipment fault diagnosis result; the decision management layer is used for generating an equipment health management decision according to the diagnosis result and outputting the decision; the hybrid reasoning model comprises a rule reasoning sub-layer, a deep learning sub-layer and a case reasoning sub-layer, the deep learning sub-layer adopts a lightweight Transform model, and the lightweight Transform model comprises a cross-modal attention enhancement module and a fault feature intensified training module. In conclusion, the hybrid reasoning architecture is constructed, so that the fault diagnosis accuracy of the power station equipment is obviously improved, the false alarm rate is reduced, and the technical problems of few unconventional fault samples and difficulty in diagnosis of the power station are solved.

The invention discloses an Internet of Things alarm root cause analysis method based on gas Internet of Things construction, and belongs to the technical field of gas pipe network safety monitoring. The method aims at solving the problems that in the prior art, alarm root cause analysis is low in efficiency and poor in accuracy, and particularly composite alarms are difficult to process. The method comprises the steps that firstly, multi-dimensional data such as alarms, equipment attributes, pipe network topology and historical cases are comprehensively collected and subjected to standardization processing; then, a dual-drive hybrid reasoning strategy is adopted, rule reasoning based on a knowledge graph and case reasoning based on a machine learning model are operated in parallel, two paths of results are subjected to weighted fusion, and candidate root causes are generated; particularly, aiming at composite alarms generated in a short time, a complex alarm disassembling module is used for carrying out hierarchical analysis on time sequence and space dimensions, and core influence factors are positioned based on dynamic weight calculation. The most innovative part of the method is that a closed-loop feedback mechanism can be constructed according to a final verification result of field operation and maintenance personnel, and dynamic weights of influence factors are automatically updated, so that self-adaptive optimization of an analysis model is realized. According to the method, the accuracy and efficiency of alarm root cause positioning are remarkably improved, and self-learning and evolution of the system are realized.

The invention provides a vulnerability discovery method and system based on symbol-semantic hybrid reasoning, and belongs to the technical field of software security. The method comprises the steps that a target program is analyzed, and an event sequence is extracted; converting the event into a symbol with a time sequence label and confidence, and constructing a symbol dependency graph; reasoning based on the dependency graph, calling a large language model to generate a semantic reasoning action when the certainty is insufficient, and updating the state after symbol verification; new rules are extracted from the inference chain passing verification through reinforcement learning, and self-evolution is achieved; and outputting a vulnerability report containing the reasoning path and the confidence coefficient. The system correspondingly comprises a time sequence probability symbol module, a symbol-semantic bidirectional coupling reasoning module, a reinforcement learning self-evolution module and a report generation module. According to the method, the preciseness of symbol logic and the generalization ability of a semantic model are fused, the accuracy, interpretability and adaptive ability of vulnerability detection are effectively improved, and the method is suitable for security audit and code review of a complex software system.

The invention discloses a disease medical case deep derivation system based on medical case cross-domain fusion, and the system comprises a data collection and preprocessing layer which is used for carrying out the collection and preprocessing of multi-source medical case data, and obtaining initial data; the knowledge fusion and representation layer is used for converting the initial data into structured knowledge and generating a target medical case knowledge graph with a unified semantic basis; the intelligent derivation and reasoning layer is used for performing deep mining and intelligent reasoning through the target medical case knowledge graph; the application interface layer receives medical case information of a patient and inputs the medical case information to the intelligent derivation and reasoning layer; and deriving the medical case information based on the intelligent derivation and reasoning layer to obtain a derivation result. The data coverage capability is improved based on multi-source heterogeneous medical case deep fusion, the analysis depth is improved based on multi-level deep derivation and hybrid reasoning, the reasoning capability is improved based on combination of semantic reasoning, case reasoning and deep learning, knowledge discovery is achieved based on intelligent mining of deep diagnosis and treatment rules, and meanwhile all-around clinical decision support is facilitated.

This invention relates to a segmented hybrid inference method for large language models based on uncertainty-driven approaches. The method includes acquiring current text data and historical state features to estimate the uncertainty index of the current segment; minimizing a unified scheduling objective function based on the uncertainty index to obtain a target inference pattern; performing inference calculations based on the target inference pattern to generate information contribution values ​​corresponding to key-value pairs; calculating the corresponding dynamic merging control probabilities based on the uncertainty index and information contribution values, and performing weighted merging or pruning on the key-value pairs to be merged to obtain compressed key-value pairs; defining a deviation metric and limiting the deviation metric to not exceed a preset upper bound determined by the dynamic merging control probability set and the uncertainty index; triggering a rollback process when the deviation exceeds this limit; otherwise, feeding back the compressed key-value pair state to the next segment for iterative iteration until the inference of all segments is completed; thereby reducing memory usage and inference latency while ensuring accuracy.

The invention discloses a synchronous phase modifier fault diagnosis method based on a knowledge graph and a large language model, and the method comprises the steps: obtaining the operation data of a synchronous phase modifier, and carrying out the preprocessing of the operation data, so as to form a unified corpus and a standardized data set; based on the unified corpus, using a BERT model to encode the corpus to obtain context perception vector representation, and based on the context perception vector representation, performing sequence labeling and relation extraction, and outputting structured knowledge data; based on the structured knowledge data, constructing a synchronous phase modifier fault diagnosis knowledge graph; based on a pre-trained large language model, performing model training and optimization by using the standardized data set, understanding and analyzing a fault phenomenon described by a natural language, and outputting a semantic analysis result; and in combination with the output of the knowledge graph and the semantic analysis result, performing hybrid reasoning to obtain a fault diagnosis result. The method has the advantages of high diagnosis precision, high diagnosis efficiency and the like.

A hybrid inference system for a coding assistant utilizes a routing model to predict whether output generated by a large language model for a given prompt would be accepted by a user of the coding assistant. The routing model routes the prompt when the routing model indicates that the output generated by the large language model is likely to be accepted. The routing model routes the prompt to a local model when the output generated by the large language model is not likely to be accepted. The routing model is trained on the historical output generated by the large language model for various prompts and the acceptance or rejection of the output by users of the coding assistant.

The present disclosure provides an inference optimization method and apparatus for a language model, an electronic device, and a storage medium. The inference optimization method comprises: in response to acquiring at least one piece of request information requesting inference of input information using a preset language model, dividing first request information into a plurality of segments of request information according to a preset length; using the language model to perform full inference and hybrid inference on the plurality of segments of request information and second request information, so as to obtain a plurality of first inference results, wherein the second request information is at least one piece of request information obtained simultaneously with the first request information or obtained during the process of performing full inference or hybrid inference on the plurality of segments of request information; and using the language model to perform incremental inference on the plurality of first inference results, so as to obtain an inference result output by the language model when performing inference on the input information. The method reduces video memory occupancy during language model inference and improves the inference efficiency of the language model.

The invention discloses a river-sea direct ship design optimization method and system based on CBR-RBR hybrid reasoning, and relates to the field of ship design, and the method comprises the steps: obtaining a design target parameter input by a user and an initial weight of an evaluation index; according to the design target parameters, case retrieval is carried out in a river-sea direct wide, flat and narrow ship type design knowledge base, and an initial design scheme is obtained; determining a search space of an optimization variable according to a main scale and a ship form coefficient in the initial design scheme; performing Pareto optimization on the evaluation indexes in the search space of the optimization variables by using a multi-objective evolutionary algorithm to obtain a non-dominated solution set; determining a score sequence according to the non-dominated solution set and the initial weight of the evaluation index; and selecting the design scheme of which the score sequence is within a set range as a user preference scheme. According to the method, the preliminary design scheme of the river-sea direct ship can be efficiently and intelligently generated and optimized.

The invention discloses a chat record crime element automatic labeling method based on natural language processing, and relates to the technical field of electronic data intelligent analysis, and the method comprises the following specific steps: sequentially carrying out data preprocessing to analyze multi-platform data and uniformly encode, carrying out semantic analysis to identify crime intentions and entities, and carrying out entity association reasoning on crime elements; and marking elements by using a structured label, and finally carrying out risk scoring and generating a judicial analysis report so as to form a complete crime element analysis process. According to the method, multi-language processing, dynamic weight and hybrid reasoning technologies are integrated, multi-platform data are compatible, the multi-language analysis problem is solved, the criminal entity recognition precision is improved, and the labeling efficiency and accuracy are greatly improved; meanwhile, a full-link judicial system is constructed, crime elements are standardized, electronic evidence export is supported, case mastering is assisted through risk scoring and multi-dimensional reports, a rule base is dynamically updated to adapt to new crimes, the working intensity of judicial personnel is reduced, and reliable support is provided for network crime attack.

The application discloses an industrial intelligent agent system and method fusing digital twin and a four-element core, belongs to the field of artificial intelligence, and comprises a digital twin perception layer, a four-element fusion core layer, a hybrid reasoning engine and an interpretable report generator.The digital twin perception layer is used for acquiring real-time state data of a physical entity; the four-element fusion core layer integrates OWL ontology modeling, graph database storage, large language model interaction and multi-physical field agent model, and generates a four-element collaborative knowledge processing result; the hybrid reasoning engine performs parallel rule reasoning, graph algorithm mining, large language model reasoning and agent model reasoning and fuses to generate a comprehensive reasoning conclusion; and the interpretable report generator generates a multi-modal report containing a reasoning path and physical evidence.The application realizes interpretable tracing of a decision-making process through four-element collaboration, realizes millisecond-level physical quantity prediction through an agent model, realizes continuous evolution of knowledge through a dynamic evolution module, and significantly improves the reliability, real-time performance and adaptability of an industrial intelligent system.

The application provides a symbol graph-oriented influence maximization method and system, and the method comprises the following steps: acquiring symbol graph data, and performing representation learning on nodes by using a symbol-aware attention layer to generate symbol-aware node embedding; a seed set representation module based on a variational autoencoder is constructed, a conflict-aware regularization term is introduced to punish negative relationships in the seed set and encourage positive cooperation; a double-path diffusion model is used to simulate the propagation dynamics of positive and negative influences to obtain node net influence; the modeling capability of a complex teacher model is transferred to a lightweight student model through knowledge distillation; finally, a hybrid reasoning strategy is used to output a seed node set with high net influence and minimum internal conflict. The application can effectively process positive and negative edge heterogeneity information in the symbol graph, accurately simulate the inhibition effect in the influence propagation, generate a high-quality seed set, and has important application value in the fields of social network analysis, viral marketing and the like.

The invention discloses a standardized data partitioning processing system supporting a multi-source data format, which relates to the field of data processing and comprises a preprocessing and format unification module, an intelligent pre-analysis and strategy selection module, a hybrid reasoning depth partitioning engine, a partitioning result optimization and verification module and a structured data output module. The method supports compatible processing of multi-source data formats; dynamic division is carried out based on a chapter structure of text content and a logic unit, semantic association content is ensured, and cross-modal semantic segmentation is avoided; the universality of the partitioning strategy is improved; intelligent partitioning of multi-source data is achieved, the requirement for manual intervention is remarkably reduced, the processing speed and efficiency are improved, and the method is particularly suitable for a large-scale document processing scene; downstream applications such as knowledge graph construction and intelligent retrieval can be directly connected, and the data utilization efficiency is remarkably improved.

The invention discloses a hybrid reasoning BIM (Building Information Modeling) design achievement auditing method for complex standard specification provisions. The method comprises the following steps: S1, defining a grammar structure and an entity class in a standard specification ontology; s2, constructing a standard specification knowledge graph based on the natural language large model; s3, constructing a mapping table; s4, constructing a design result file and text description information; s5, generating an executable rule statement; and S6, performing hybrid reasoning based on a rule reasoning engine and a natural language large model cue word technology. The method comprises the following steps: disassembling a standard text by using a natural language large model cue word technology, and constructing a knowledge graph; the natural language standard specification text is converted into an executable rule, and compliance auditing of the BIM design result is supported; and a rule inference engine and a large language model are combined to perform hybrid inference, so that the BIM model auditing precision is improved.

The invention discloses a construction technical scheme compilation adaptive optimization method and system based on multi-source data, and relates to the field of construction management.The method comprises the steps that all kinds of data in the whole construction period are collected through a distributed terminal, and a dynamic data resource pool is constructed after standardization processing; cleaning data by using a classification preprocessing model, and extracting a construction scheme associated feature set through cosine similarity and deep learning; generating an initial scheme by combining case reasoning and rule reasoning, and performing multi-target dynamic optimization by applying reinforcement learning; and verifying the feasibility of the scheme through virtual simulation and trial construction, finally establishing a real-time monitoring feedback mechanism, and automatically triggering scheme updating when actual data deviates from a threshold value. The method has the advantages that multi-source data full-process driving is adopted, a scheme is generated through preprocessing, feature extraction and hybrid reasoning, reinforcement learning optimization, virtual simulation verification and a real-time deviation updating mechanism are combined, accurate adaptation and dynamic optimization of a construction technical scheme are achieved, and engineering comprehensive benefits are efficiently improved.

The invention discloses a code collaborative management system and method based on AST semantic capitalization and a knowledge graph, and belongs to the technical field of software engineering and artificial intelligence. The system comprises an AST semantic capitalization module, a multi-dimensional knowledge graph engine module, a knowledge graph visualization and interaction module, a graph version management and timeline playback module, an automatic document synchronization module, a real-time multi-person cooperation module, an intelligent notification aggregation module and an intelligent batch import module. According to the method, incremental AST analysis is performed on source codes through a Tree-siter analysis engine, and code fingerprints are generated by adopting a Merkle tree Hash algorithm to realize capitalized management; mapping the code warehouse into a knowledge graph covering multi-dimensional relationships such as function call, class inheritance and module dependence, and realizing hybrid reasoning query in combination with a GraphRAG technology; driving LLM to automatically synchronize the document through AST change perception; based on WebSocket, realizing multi-user real-time collaborative annotation and collaborative cursor synchronization; and functions of graph snapshot comparison, timeline playback, intelligent batch import verification, multi-level notification aggregation and the like are provided. The problems that in the prior art, code analysis granularity is insufficient, the relation modeling dimension is single, document synchronization is disjointed, cooperation lacks real-time performance, and data import lacks intelligent verification are solved.

The invention provides an intelligent optimization method and system based on knowledge engine construction, relates to the field of water conservancy knowledge construction, and solves the technical problems of difficulty in rule maintenance and complexity in reasoning calculation in an existing large-scale water conservancy project knowledge graph. The method comprises the steps of obtaining historical information of related water conservancy domain knowledge from a water conservancy database based on the related water conservancy domain knowledge asked by a user; based on a pre-constructed water conservancy project knowledge map, reasoning related water conservancy field knowledge asked by the user to obtain a reasoning result; analyzing a matching index between the reasoning result and historical information to obtain a candidate scheme; obtaining a preliminary optimal scheme from the candidate schemes through a hybrid inference engine; and inputting the preliminary optimization scheme into a self-defined workflow, carrying out multiple rounds of optimization and verification, and outputting a final optimization scheme. According to the method and the system, the efficient intelligent optimal reasoning logic method and the system are realized.

The invention discloses a railway tunnel BIM model automatic construction system and method based on natural language processing and hybrid reasoning. The system comprises a natural language processing module used for analyzing a user instruction into a structured parameter through large language model function call; the hybrid reasoning engine is used for retrieving from a case library or reasoning a complete modeling parameter set based on an ontology rule library according to core parameters by adopting a case reasoning priority and rule reasoning bottom strategy; and the parametric modeling module is used for driving scripts to automatically generate a BIM model containing geometric and semantic information according to the complete parameter set. According to the method, end-to-end automatic construction from the natural language to the three-dimensional tunnel BIM model is realized, the professional modeling threshold is greatly reduced, the modeling efficiency and the intelligent level are remarkably improved, and effective technical support is provided for digital transformation of railway engineering.

The invention discloses an insurance clause explanation method, system and device and a storage medium, and the method comprises the steps: constructing a multi-modal knowledge graph which integrates multiple fields and comprises multiple nodes, and building the incidence relation between the nodes based on language mapping; the method comprises the following steps: receiving insurance clause consultation content input by a user, and extracting related multi-domain terms; based on the multi-modal knowledge graph, performing cross-domain semantic reasoning on the multi-domain terms by using a hybrid reasoning engine to generate a preliminary interpretation result; and carrying out confidence fusion on the preliminary interpretation result to generate final interpretation content. Through integrated innovation of a multi-modal knowledge graph, a hybrid inference engine, a dynamic association algorithm, a full life cycle prediction model and a man-machine collaborative learning mechanism, intellectualization, credibility and individuation of life insurance clause explanation are realized, and a new technical path and innovation support are provided for intelligent service and risk management of the insurance industry.

The application discloses a kind of standardization data block processing systems of supporting multi-source data format, it is related to data processing field, the system includes preprocessing and format uniformity module, intelligent pre-analysis and strategy selection module, mixed inference depth block engine, block result optimization and check module, structured data output module.The application supports the compatible processing of multi-source data format;Based on the dynamic division of chapter structure and logic unit of text content, ensure semantic association content, avoid cross-modal semantic fragmentation;Improve the universality of block strategy;Intelligent block of multi-source data is realized, significantly reduces the demand of manual intervention, improves processing speed and efficiency, especially suitable for large-scale document processing scene;It can be directly connected knowledge graph construction, intelligent retrieval and other downstream applications, significantly improve data utilization efficiency.

The invention provides a GPU operation and maintenance intelligent system integrating anomaly perception, semantic-level reasoning, causal chain reconstruction, intelligent repair decision and self-feedback learning. According to the system, interpretable root cause tracking is achieved through a retrieval-enhanced generation (RAG)-map hybrid reasoning mechanism, automatic repair action planning is achieved through a strategic generation model, and knowledge edge weight self-updating and reasoning ability self-evolution are achieved through verification feedback. According to the method, the normal form transition of GPU fault handling from post analysis to real-time deduction and self-healing regulation is realized, and a full-process intelligent closed loop of sustainable evolution is formed.

In one implementation, a device obtains performance metrics for a sequence of partitions of a first language model that sequentially process requests. The device makes, based on the performance metrics, a determination that a bottleneck partition exists in the sequence of partitions and represents a potential bottleneck or failure point for the first language model processing a request from a requester. The device identifies a partition of a second language model as an alternate for the bottleneck partition of the first language model. The device configures, based on the determination, a preceding partition that precedes the bottleneck partition in the sequence of partitions to send an output of the preceding partition to the partition of the second language model to process the request in lieu of the bottleneck partition.

Methods and systems of building a knowledge graph based on event-based ontology of a scene and vehicle trajectory in the scene. Image data corresponding to a plurality of scenes captured by one or more cameras is received. Event-based ontology data corresponding to events occurring in the plurality of scenes is received. Via an object-tracking machine-learning model, the system determines (i) a presence of a plurality of vehicles in the image data, and (ii) a plurality of vehicle trajectories, each vehicle trajectory associated with a respective one of the vehicles. Using a clustering model, the vehicle trajectories are clustered. A knowledge graph is augmented based on the clustered vehicle trajectories and the event-based ontology.

This invention discloses a ternary fusion knowledge processing system and method based on ontology, graph database, and large language model, comprising: an ontology construction module constructing a formal conceptual model; a knowledge graph construction module extracting instance data from multi-source heterogeneous data and storing it in a graph database based on the conceptual model to form knowledge graph instances; a large language model interaction module receiving natural language queries and parsing user intent; a hybrid reasoning engine invoking rule-based reasoning, graph algorithm mining, and large language model reasoning in parallel according to user intent, processing the conceptual model, knowledge graph instances, and queries, and fusion results to output a comprehensive conclusion; an interpretable report generation module recording the reasoning basis and generating an interpretable report; and a dynamic evolution module updating the conceptual model and knowledge graph instances based on newly accessed event data. This invention integrates symbolic reasoning and neural networks, improving the interpretability, accuracy, and dynamic evolution capability of reasoning.

The application discloses an AI-driven construction process recommendation and mixed reasoning optimization method and system. The method comprises the following steps: receiving project characteristic input, loading expert rule template; taking the project characteristics and the expert rules as the context, calling a large language model to output structured process network data, including process identification, construction period, preposition relationship type, resource demand reference and construction process label; cross-verification checking the integrity of the LLM generation result and the expert rules; supplementing auxiliary processes from the process template library to form a candidate scheme pool; taking the candidate process network as the input, constructing a four-dimensional target model for simultaneously optimizing the minimization of the total construction period, the minimization of the artificial load balance degree, the minimization of the material daily supply pressure and the maximization of the mechanical utilization rate, and solving a Pareto optimal scheme set. The application integrates the LLM structured process network generation, the expert rule mixed reasoning and the multi-dimensional resource optimization into an integrated process, so that the AI-assisted scheme preparation is upgraded from a text suggestion to a deducible process network.

The application relates to the technical field of intelligent operation and maintenance. A hybrid reasoning acceleration method, device and equipment for an operation and maintenance intelligent agent and a medium are disclosed. The method comprises the following steps: obtaining operation and maintenance request data; performing intention recognition on the operation and maintenance request data based on a pre-set intention recognition model and a complexity evaluation model, and determining the complexity score corresponding to the operation and maintenance request data; determining a target reasoning path based on a pre-set routing strategy model according to the intention and the complexity score of the operation and maintenance request data, wherein the target reasoning path is a rule engine path, a small model reasoning path or a large model reasoning path; and generating an operation and maintenance decision suggestion according to the intention of the operation and maintenance request data based on the target reasoning path. The application reduces the processing request amount of a large model, significantly improves the utilization rate of computing resources, reduces operation costs, improves throughput and reduces delay under the premise of guaranteeing decision quality, and improves the landing application of the operation and maintenance intelligent agent in a large-scale production environment.

The invention discloses a recommendation method and device for low-code process design and a medium, and the method comprises the steps: obtaining a current node type, a node connection sequence and a node configuration parameter in a design canvas, and generating a process context vector; performing sub-graph matching on the process context vector according to a pre-constructed process modeling knowledge graph to generate a target process sub-graph; analyzing the input natural language through a preset natural language model to obtain a business keyword and a design target; according to the graph neural network, the business keyword and the design target, confidence calculation is carried out on the target process sub-graph, and final recommendation content is obtained; and by designing a canvas, displaying the final recommended content. Through a collaborative method of context modeling, map intelligent retrieval and hybrid reasoning, the process design operation complexity is greatly reduced, and the process design efficiency is remarkably improved. And through multi-modal presentation and map industry compliance constraint, the process design reliability is improved.

The invention discloses an intelligent line selection architecture and method for large-size transportation, and the architecture comprises a front-end request access layer which is used for receiving a transportation request of a client, carrying out the intelligent shunting through an API gateway, and forwarding a real-time transportation request to a graph structure construction module; the rear-end intelligent analysis layer is used for analyzing the transportation request of the client, generating a candidate route set through a hybrid reasoning architecture, and screening out an optimal route by utilizing a reinforcement learning optimizer; the result return and feedback layer is used for receiving the optimal cache route, precipitating the transportation data to a historical database, and dynamically updating and optimizing the weight by using actual transportation feedback; compared with the prior art, the transport request is received through the hierarchical service architecture, intelligent analysis is executed, the optimized route is returned, meanwhile, data precipitation, feedback updating and full-process automation are achieved, the dependence on artificial experience is greatly reduced, the route planning efficiency is remarkably improved, and the transport request can be quickly responded.