93 results about "Logical reasoning" patented technology

This invention relates to a method and system for mining potential user needs based on hierarchical temporal memory enhancement. First, a dynamic time window hierarchical slicing mechanism is used to decouple the cleaned multimodal user behavior sequence into long-term historical sequences and short-term real-time sequences. A semantically approximate nearest neighbor graph is constructed from the long-term historical sequence, and adaptive community discovery is performed. This is combined with a large language model to generate a high-semantic-density long-term memory abstract representation. Then, a hybrid prompt template integrating system instructions, long-term memory representation, and short-term sequences is constructed to drive the large language model to complete a three-stage thought chain reasoning process: focused denoising, scene instantiation, and function completion, generating a structured reasoning data package. A dual-tower semantic retrieval and scene-constrained filtering architecture is employed to achieve accurate mapping between the reasoning results and the product database, outputting a product list with recommendation reasons. This invention endows the recommendation system with deep logical reasoning and cross-domain association capabilities, improving the accuracy and interpretability of e-commerce recommendations.

The work ticket intelligent checking method based on multi-modal large model knowledge graph and large model reasoning belongs to the field of power system application technology, first extracts text feature vectors and image feature vectors through an OCR module and an image encoder, forms a comprehensive semantic representation after multi-modal fusion. Extract entities and relationships from power safety regulations and historical operation data to generate a power safety knowledge graph. Check the format and integrity of the basic fields on the ticket, use LLM to combine context and graph nodes for semantic reasoning to generate semantic judgment results. Fuse three layers of results to calculate a comprehensive checking score and output an intelligent determination result. The present application introduces multi-modal input analysis, knowledge graph construction and large model semantic reasoning technology to construct a structured, interpretable and iteratively optimized intelligent work ticket checking system that realizes the full-process intelligentization from ticket image recognition to semantic understanding and from explicit rule checking to implicit logical reasoning.

The application discloses a kind of based on natural language's traffic event's question and answer method and system, belong to intelligent question and answer field, first acquisition roadside image and user query, respectively by visual encoder and natural language encoder extraction multiscale visual feature set and text feature;Then utilize pre-training cross-modal intent alignment and focus module, with text feature as guide to spatial attention anchor and cross-modal intermingling to visual feature, output joint representation feature;Again, the feature is input light-weight decoder obtained by structured logic decoupling and migration strategy distillation, so that it executes step-by-step logical inference and coordinate regression based on spatial response graph in parallel, synchronously output natural language answer text and target bounding box coordinates;Finally generate traffic event question and answer result containing semantic answer and visual mark.The application effectively solves the problem that prior art cannot accurately and efficiently based on natural language to traffic event intelligent question and answer.

The application discloses a complex specification multi-modal understanding method and system based on YOLO two-stage segmentation, comprising the following steps: performing pre-processing on an input specification image; inputting the pre-processed image into a coarse-grained detection stage of an improved YOLOv8 network to generate a coarse-grained candidate region set; inputting the coarse-grained candidate region set into a fine-grained segmentation network based on an improved YOLOv8 feature extraction structure; constructing a layout hierarchical relationship structure based on an accurate layout segmentation result; according to the layout hierarchical relationship structure, performing multi-modal feature extraction on the accurate layout segmentation result, and calculating a matching weight; inputting a graphic-text semantic alignment result and the layout hierarchical relationship structure into a logical structure modeling module together to construct a layout element graph; and generating a knowledge graph semantic output result according to a structured logical reasoning result. The application realizes automatic structured understanding of a complex specification by adopting YOLO two-stage segmentation and multi-modal semantic alignment.

This application proposes a problem classification method, a problem classification device, and a computer storage medium. The problem classification method includes: acquiring mathematical problem information; extracting mathematical features from the mathematical problem information, wherein the mathematical features include text features, formula features, and / or graphic features; performing logical reasoning on the mathematical features according to a preset mathematical logic chain; inputting the logical reasoning result into a multi-task output branch to determine the problem classification result of the mathematical problem information. This problem classification method achieves end-to-end multi-label classification of mathematical problems.

This invention discloses a method, device, and storage medium for identifying potential hazards in power transmission channels based on collaborative reasoning using object detection and knowledge graphs. The method generates a knowledge graph of potential hazards in power transmission channels, a rule base for reasoning about potential hazards in power transmission channels, and an object detection model. The object detection model detects and identifies multiple current entity target categories from the current power transmission channel image. These multiple current entity target categories are associated with entity types in the knowledge graph of potential hazards in power transmission channels, resulting in a knowledge graph of potential hazards in power transmission channels that incorporates a transient semantic subgraph. Then, the knowledge graph of potential hazards in power transmission channels that incorporates a transient semantic subgraph is traversed and matched based on the rule base for reasoning about potential hazards in power transmission channels. Reasoning is performed using the obtained hazard reasoning rules to obtain the hazard identification result for the current power transmission channel. The device and storage medium are used to implement the method. This invention can obtain accurate hazard reasoning results, and the hazard logical reasoning process is interpretable.

This disclosure relates to a method and apparatus for processing text requests. The method includes: in response to receiving a text request input by a user, triggering an operation event for the text request; and during the execution of the operation event, performing the following processing: for each detected model call request used to invoke a large language model, triggering a generation event for each model call request; during the execution of the generation event, by triggering and executing an inference flow event and a content increment event, obtaining the inference process and processing result of the text request under the generation event, respectively, wherein the inference process is the logical inference process by which the large language model obtains the processing result. Through this disclosure, the front end can accurately distinguish the processing cycle of a single text request, the generation cycle of each model call, the inference flow, and the content flow, etc., within the processing process of a single text request.

This application discloses an intelligent question-answering method, apparatus, computer device, storage medium, and product, belonging to the field of artificial intelligence technology. It includes: displaying an intelligent question-answering interface; obtaining input question information based on input operations on the intelligent question-answering interface; performing a statement matching query in a structured database based on the question information to obtain a first query result; performing a semantic similarity query in an unstructured knowledge base based on the question information to obtain a second query result, wherein the unstructured knowledge base includes multiple unstructured knowledge items, and the second query result includes the retrieved candidate unstructured knowledge items; determining candidate answer information based on the first and second query results; and performing logical reasoning and natural language generation on the candidate answer information to obtain a first target answer information, wherein the first target answer information is used to describe the candidate answer information using natural language, and the first target answer information contains the logical reasoning process of the candidate answer information.

The application relates to a kind of intelligent question and answer methods of digestive system disease based on knowledge graph, specifically to disease learning and question and answer field, through fusing deep semantic understanding and knowledge graph reasoning, the accurate response of complex multi-round question and answer in digestive system disease field is realized;It first aligns the user dialogue with the medical knowledge graph in depth, dynamically focuses on the relevant knowledge subgraph, then explores the logically coherent reasoning path in the subgraph through reinforcement learning, and finally generates traceable answers based on the path and dialogue history;This process ensures that the reply is not only accurate in information, clear in logic, but also has good interpretability;More importantly, by feeding back the quality of the generated answer to the optimization process of the reasoning path, it realizes the end-to-end collaborative optimization from semantic understanding, knowledge retrieval, logical reasoning to language generation, significantly improving the overall performance and practicality of the system.

This application provides a reasoning and decision-making method, apparatus, device, and storage medium based on a large language model. The method includes: acquiring a decision instruction input for a target scene and a video frame sequence corresponding to the target scene; when the decision instruction corresponds to a logical reasoning task, identifying at least one object to be analyzed, and using a first large language model to perform dynamic trajectory analysis and scene association analysis on the object to be analyzed based on the video frame sequence to obtain corresponding scene description information; combining the decision instruction and scene description information, performing semantic retrieval in a preset domain rule base to obtain at least one target rule information; combining the decision instruction, video frame sequence, scene description information, and at least one target rule information to generate corresponding text prompt information; and using a second large language model to perform logical reasoning based on the text prompt information to obtain the corresponding decision result. This improves the accuracy of decision results for dynamic environments.

The power grid standard analysis method, device, equipment and storage medium provided by the application relate to the field of power systems. The method comprises the following steps: obtaining a power grid standard document, wherein the power grid standard document comprises standard text clauses, circuit diagram images and parameter table data; performing semantic labeling on the standard text clauses to identify power terminology entities; performing disambiguation processing on the power terminology entities to obtain disambiguated standard text clauses; generating standardized knowledge units based on the disambiguated standard text clauses, the circuit diagram images and the parameter table data; and performing logical reasoning on the standardized knowledge units to determine a content consistency checking result of the power grid standard document. Through the application, the drawbacks of low efficiency, strong subjectivity and unstable quality of manual analysis are overcome, and efficient, objective and standardized processing of the power grid standard is realized.

This invention relates to the field of data analysis technology, and in particular to a query analysis method, apparatus, device, and storage medium based on a large language model. The method provides comprehensive and effective data support for enterprise decision-making. It achieves semantic fusion of multi-source heterogeneous data through a unified knowledge graph, breaking the limitations of traditional data silos and providing a comprehensive and accurate business knowledge foundation for the large language model, reducing model illusions from the source. It achieves differentiated analysis processing through task type classification, automatically scheduling different capability modules of the large language model according to user needs, balancing the efficiency of basic queries with the accuracy of in-depth analysis. It obtains the full business context through entity links, limiting the reasoning process of the large language model to the enterprise's real business scenarios, significantly improving the business relevance of the analysis results. It achieves in-depth diagnostic analysis through causal attribution, fully leveraging the logical reasoning capabilities of the large language model and overcoming the limitations of descriptive analysis.

This invention relates to the field of artificial intelligence technology, specifically to an AI-based medical information consultation method and apparatus. The method includes: acquiring multimodal medical consultation input from a user; preprocessing and extracting features from the multimodal input, and fusing them to generate a unified multimodal feature representation; based on the feature representation, performing topic indexing in a pre-constructed medical knowledge graph, and extracting a set of highly relevant medical knowledge using unsupervised clustering analysis and a dynamic threshold filtering mechanism; inputting the filtered medical knowledge set and multimodal features into a medical large-scale language model for logical reasoning, and running a multi-turn dialogue intent tracking algorithm during the reasoning process to complete missing entities; intercepting high-risk behaviors and correcting compliance issues in the preliminary response generated by the large-scale language model, and outputting a safe and professional medical information consultation response. This invention significantly improves the cross-modal perception capability, logical reasoning accuracy, and clinical application legitimacy of medical AI.

This application provides a method and system for optimizing user input information based on a large language model, belonging to the fields of artificial intelligence and regional management technology. The method receives initial user information and extracts key semantic features such as entities and actions through deep learning algorithms. An expanded semantic set is generated based on a dynamically updated semantic association rule base, and a precisely targeted subset is obtained through a specially trained large language model. The initial information and the subset are fused according to relevance weights, and optimized information is output after verification and correction through syntactic analysis and logical reasoning. Parameters can be dynamically adjusted based on user feedback. This invention solves the problems of low accuracy and insufficient standardization in existing technologies, improves information completeness and adaptability, and enhances the usability of user input information.

The present application relates to a method, device, equipment and medium for verifying the commissioning status of power equipment, and relates to the technical fields of power engineering auditing and artificial intelligence. It includes: parsing the submitted review materials using a multimodal document parsing model; inputting the dispatching operation power time series into a variational autoencoder model for sequence reconstruction calculation to obtain the reconstruction error and generate a time series anomaly feature component; generating a trajectory space anomaly feature component based on the spatio-temporal data of project personnel clock-in and the benchmark coordinates of the equipment ledger, and at the same time performing error level analysis on the on-site commissioning image data to generate an image anti-counterfeiting anomaly feature component; submitting the above multi-source heterogeneous data to a multimodal large model for cross-comparison and logical reasoning, breaking the limitation of only relying on the submitted review materials by a single party, identifying forgery behaviors from the source. With the equipment identifier as the only primary key, in the face of false commissioning scenarios with strong concealment and across multiple links, a multi-dimensional cross-verification closed loop is formed to identify deep造假行为 is misspelled. It should be "deep造假行为 is misspelled. It should be "deep forgery behaviors" here. So the corrected translation is as follows: The present application relates to a method, device, equipment and medium for verifying the commissioning status of power equipment, and relates to the technical fields of power engineering auditing and artificial intelligence. It includes: parsing the submitted review materials using a multimodal document parsing model; inputting the dispatching operation power time series into a variational autoencoder model for sequence reconstruction calculation to obtain the reconstruction error and generate a time series anomaly feature component; generating a trajectory space anomaly feature component based on the spatio-temporal data of project personnel clock-in and the benchmark coordinates of the equipment ledger, and at the same time performing error level analysis on the on-site commissioning image data to generate an image anti-counterfeiting anomaly feature component; submitting the above multi-source heterogeneous data to a multimodal large model for cross-comparison and logical reasoning, breaking the limitation of only relying on the submitted review materials by a single party, identifying forgery behaviors from the source. With the equipment identifier as the only primary key, in the face of false commissioning scenarios with strong concealment and across multiple links, a multi-dimensional cross-verification closed loop is formed to identify deep forgery behaviors.

The application discloses a semiconductor thin film deposition process intelligent recommendation system and method based on a knowledge graph, belongs to the technical field of semiconductor manufacturing processes, and comprises the following: a semiconductor thin film deposition process knowledge graph construction module; a prompt word template generation module: used for receiving process requirements and constraint conditions input by a user, performing semantic analysis on the process requirements and constraint conditions, filling the analysis results into a preset prompt word template, and outputting standardized instructions meeting the calling requirements of a large language model; and a large language model reasoning module: used for receiving the standardized instructions, performing semantic retrieval and logical reasoning on the standardized instructions within the constraint range of the semiconductor thin film deposition process knowledge graph, generating a plurality of candidate thin film deposition process schemes meeting process constraint conditions based on entity relationships and causal associations in the semiconductor thin film deposition process knowledge graph; and the application constructs a complete process recommendation solution and exhibits significant advantages in multiple aspects.

The application provides a kind of underground pipeline pipe gallery resource interconnection method and device based on large language model, belongs to computer technology field, specifically includes obtaining the pipeline detection data of all underground pipelines in target area, constructs global topology knowledge graph;Extract local topology knowledge graph from global topology knowledge graph;The structured text is obtained by converting local topology knowledge graph, and the pipeline gallery resources in structured text are evaluated and filtered using a large language model, to obtain structured text with compatibility evaluation label;Using a large language model, execute logical reasoning based on the local topological relationship represented by the structured text with compatibility evaluation label, generate reasoning results that meet pipeline planning and complete path chain from start to end;Based on the reasoning result, a candidate interconnection scheme is generated. Through the processing scheme of the present application, an interconnection scheme is generated that takes into account the reuse of existing resources, cost control and safety compliance, improving the intensive utilization efficiency of urban underground space.

A human problem-solving thinking driven embedded enhancement method for logical reasoning problems, the present application relates to a multiple-choice logical reasoning question and answer problem in the field of natural language processing, which aims to solve the technical problems of unclear text structure analysis, insufficient use of problem related elements and difficult logical reasoning problem semantic mining in the existing logical reasoning question and answer problem solving method. The method mainly includes data preprocessing, arranging the sample into a text sequence suitable for neural network model processing, designing a question-based embedding update module based on human problem-solving thinking, first initializing character embedding representation, using a pre-trained language model to vectorize the characters in the sample, then using the embedding sequence of the question part to construct a logical information filtering vector, and then updating the embedding representation of the stem and options using the filtering vector, and a semantic relationship modeling module referring to human reading habits, analyzing the basic semantic unit of the neural network.

This invention relates to the field of clinical medical education technology and discloses a cloud-based clinical medical fundamentals education system, including a client terminal, a cloud server, and a storage device. The cloud server receives action instruction data packets and updates the cumulative time, economic cost, and trauma cost. The cloud server includes a physical evolution layer module, a gateway mapping layer module, a logical reasoning layer module, and an evaluation and settlement layer module. The physical evolution layer module performs dynamic calculations based on time cost and outputs a continuous state vector. The gateway mapping layer module converts this vector into a discrete semantic feature subset. The logical reasoning layer module uses the feature subset to update the diagnostic probability vector and cumulative information gain. When a termination condition is triggered, the evaluation and settlement layer module calculates the path efficiency index based on various costs and information gain and generates an evaluation report. This invention achieves an objective and quantitative evaluation of the evolution of dynamic physiological states and the efficiency of comprehensive clinical decision-making.

This invention provides an interactive semantic segmentation and volume measurement method for complex geometric structures, belonging to the field of image processing technology. To address the problem of excessive reliance on manual annotation for text input in current semantic segmentation methods, this invention introduces the SAM model and the Describe Anything model to provide a preliminary segmentation foundation for subsequent processing and generate complex and detailed natural language descriptions of regions of interest. Based on this, a feature extraction module is designed, using a text encoder to extract word features and utilizing MLP to obtain Gaussian positional features, laying the foundation for subsequent feature fusion steps. To address the lack of spatial logical reasoning capabilities in previous methods, this invention designs a feature fusion module for describing complex spatial relationships. It utilizes positional and word features to optimize the semantic feature parameters in the Gaussian field, thereby obtaining spatially aware semantic features to support higher-level natural language semantic parsing.

This invention relates to the field of equipment operation and maintenance, and particularly to a predictive maintenance method, system, equipment, and medium for rail transit platform screen doors. The method includes: acquiring multimodal sensing data and time-varying operating condition characteristics of the station area; inputting the sensing data into a multimodal fusion model, and extracting physical loss, time-series load, and operation and maintenance semantic feature vectors through heterogeneous parallel branches; performing self-learning alignment and fusion of features based on a cross-attention mechanism, and outputting an operating status score and associated text; inputting the associated text into a large language model, using a fault causal logic chain to back-verify and correct candidate root causes; analyzing the fault root causes and multimodal sensing data to obtain an initial maintenance strategy, and performing dynamic optimization to generate a maintenance plan. Therefore, this invention, through deep fusion of multimodal data and causal logic reasoning, realizes fault early warning, root cause localization, and operation and maintenance resource scheduling for rail transit platform screen doors, improving the intelligence level of operation and maintenance management and the equipment operation guarantee capability.

The application relates to the technical field of artificial intelligence, and provides a plan management method and device, electronic equipment and a storage medium, the method comprising the following steps: determining a demand text and user individual information; based on an expert rule model, applying the demand text and the user individual information to generate a current plan; based on a logic reasoning model and the user individual information, performing feasibility reasoning on the current plan; and based on a reasoning result of the current plan, adjusting the current plan until a stage plan is obtained; the expert rule model and the logic reasoning model are obtained based on large language model training; and based on an execution situation of the stage plan, the stage plan is managed.The plan management method and device, electronic equipment and storage medium provided by the application can discover and correct unreasonable places in a plan in a timely manner, ensure smooth execution of the plan, and thus enhance the feasibility and reliability of the plan.

This application relates to the interdisciplinary field of artificial intelligence and reliability systems engineering, and provides a method and apparatus for intelligent generation of equipment fault behavior logic models based on LLM (Limited Linear Modeling). This method combines a vector database to achieve enhanced retrieval, constructs an agent-based framework for generating equipment fault behavior logic models, and then generates structural elements in the agent for each business component involved in the equipment fault behavior logic. Based on the model structure, the results are integrated and merged, ultimately achieving a complete and runnable equipment fault behavior logic simulation model. This method integrates the interactive modeling capabilities of agents with the semantic understanding and logical reasoning capabilities of large language models, enabling intelligent generation of fault behavior models for complex equipment and effectively improving the generation efficiency of equipment fault behavior models.

This invention relates to the field of port equipment scheduling technology, specifically to a port intelligent scheduling method, device, and medium based on a reinforcement learning system. The method includes: acquiring modification information from a dispatcher who modifies a port equipment scheduling plan output by the reinforcement learning system; performing logical reasoning on the modification information to obtain expert intentions and corresponding confidence levels; if all confidence levels are less than a preset threshold, generating intention options from expert intentions with confidence levels less than the preset threshold and sending them to the dispatcher, and receiving the intention option selected by the dispatcher, using the expert intention corresponding to that intention option as the dominant preference intention; if the confidence level is greater than or equal to the preset threshold, using expert intentions greater than or equal to the preset threshold as the dominant preference intention; setting an intention matching reward for the reinforcement learning system based on the dominant preference intention to adjust the weights considered by the reinforcement learning system when generating port equipment scheduling plans, thereby improving the operational economy and energy efficiency of port equipment scheduling decisions.

The application discloses a kind of construction safety log intelligent filling system, it is related to building information technology field, the system includes multidimensional field perception layer, multi-agent collaborative computing layer, semantic modeling and conflict resolution layer, safety risk reasoning layer and log automation generation layer.Multidimensional field perception layer real-time acquisition original data stream and carry out time and space marking;Multi-agent collaborative computing layer extracts feature and local decision by multiple heterogeneous function agents in parallel;Semantic modeling and conflict resolution layer exports consistent semantic event by construction safety ontology library and collaborative filtering mechanism;Safety risk reasoning layer executes logical reasoning to identify irregular events in combination with knowledge graph;Log automation generation layer encapsulates and translates into standardized text.The application effectively solves the problem of manual filling omission, realizes the active inference and automatic generation of log, and ensures the consistency of data processing logic.

The application discloses a heat release tracing method for new energy station debugging quality problems and a related device, comprising: preprocessing environmental data and equipment data of the new energy station to obtain preprocessed data; constructing a standardized event stream according to the preprocessed data; calculating the dynamic failure rate of each basic event in the standardized event stream; based on the dynamic failure rate of each basic event in the standardized event stream, hierarchically combining each basic event according to system function relationship and logical dependence to construct a dynamic fault tree model of the new energy station; based on the dynamic fault tree model of the new energy station, through a time progression logic reasoning algorithm, combining the dynamic failure rate of each basic event, calculating the delayed probability contribution degree of each basic event, identifying the key root cause event and the propagation path, and the method and the related device can improve the tracing accuracy and response efficiency of the new energy station debugging quality problems.

The invention discloses a program control instruction generation method based on large model federation prompt fine tuning, which realizes the collaborative utilization of multi-party data on the premise of protecting the data privacy of each party by constructing a multi-level conditional diffusion model federation learning architecture. The problem of rapid adaptation of new equipment is solved through a heterogeneous document-oriented hierarchical retrieval enhancement generation method, and the problems of information fragmentation and text discontinuity in the traditional RAG technology are solved by constructing an operation process knowledge graph and a multi-granularity semantic representation learning framework and adopting a continuous perception retrieval mechanism. And finally, solving a fundamental contradiction between large model probability generation and test instruction preciseness through a constraint satisfaction deterministic generation mechanism, and converting a probability generation process into a strict logical reasoning process by adopting a beam search algorithm guided by a complete deterministic constraint. By constructing a three-dimensional constraint system of grammar constraint, semantic constraint and security constraint and a multi-stage verification mechanism, each generated instruction is ensured to have uniqueness, correctness and security.

The application discloses a construction behavior anomaly detection method and system based on a lightweight large model, and relates to the technical field of artificial intelligence; the method comprises the following steps: collecting multi-source heterogeneous data of a construction site, including video streams, sensor data and building information model (BIM) data, and performing spatiotemporal alignment preprocessing; constructing a construction behavior analysis architecture based on a lightweight large model, utilizing a lightweight visual feature extraction network and a spatiotemporal graph convolution behavior recognition network to extract entity features, position information and action spatiotemporal features of personnel, equipment and materials; generating a fusion feature vector through a cross-modal feature fusion encoder combined with a self-attention mechanism; finally, utilizing a multi-modal large language model reasoning engine combined with a preset knowledge graph to perform logical reasoning, identifying the interaction relationship between personnel and the environment, thereby determining construction behavior anomalies and generating early warning information. The method effectively improves the accuracy and efficiency of construction site anomaly behavior detection, reduces the consumption of computing resources, and enhances the intelligent level of safety monitoring.