44 results about "Hierarchical relation" patented technology

The invention discloses a question answering method based on structured document retrieval enhancement, and belongs to the technical field of artificial intelligence. The method comprises the following steps: performing structured information analysis and blocking processing on a structured document to construct a tree structure reflecting a hierarchical relationship of the document; based on a cross-document association relationship, combining the tree structures corresponding to the plurality of structured documents to form a multi-document tree structure network; and when a question request is received, generating corresponding retrieval enhancement information through the tree structure network, and inputting the retrieval enhancement information into the question and answer model to obtain answer information matched with the question request. According to the method, the multi-document tree structure network which takes the tree hierarchical relationship of the structured document as a core and fuses cross-document topic clustering and reference mapping is constructed, so that efficient retrieval enhanced questions and answers oriented to the structured document are realized, and the accuracy, context consistency and traceability of answers are remarkably improved.

The invention discloses a crowd test report sorting method based on big language model multi-modal multi-layer clustering tree analysis. A clustering module, a structuring module and a sorting module are included. And the clustering module comprises feature extraction and clustering, performs semantic understanding on the image and the text by utilizing LLM, constructs a clustering prompt according to a preset prompt template, and inputs the LLM to generate a clustering result. The structuring module analyzes the clustering result output by the LLM into a multi-level clustering tree so as to represent the hierarchical relation and category between the defect reports, and metadata such as access time and accessibility are recorded on nodes. And the sorting module generates a report sorting sequence which covers different categories and is not repeated by adopting a recursive selection strategy based on the clustering tree and the node metadata so as to improve the examination efficiency and the defect discovery capability of the test report.

The embodiment of the invention provides an audit path generation method and device, a medium and a program product, and relates to the technical field of artificial intelligence. The method comprises the following steps: extracting multi-source heterogeneous data from an audit system document, a historical audit report and / or business system data; identifying auditing entities in the multi-source heterogeneous data and association relationships thereof through a natural language processing model, and generating a structured entity set and an association relationship set; storing the structured entity set and the incidence relation set in a graph database to obtain an audit knowledge graph with a hierarchical relation; and generating an audit path based on the audit knowledge graph. By adopting the method, the auditing path with high coverage degree and high auditing efficiency can be generated based on the auditing knowledge graph, and the auditing coverage rate and the auditing efficiency are improved.

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 invention belongs to the technical field of natural language processing and dialogue systems. It discloses a multi-target dialogue recommendation method based on hierarchical prompt optimization, including hierarchical target label modeling, learnable prompt embedding initialization, graph attention enhancement mechanism, multi-task learning framework, and response generation model. Hierarchical target label modeling encodes the hierarchical relationships between target labels into a graph structure. Learnable prompt embedding initialization integrates label semantics and deep hierarchical information into the encoder input space. The graph attention enhancement mechanism enhances the label vector structure perception ability through information transmission and aggregation between label prompts. The multi-task learning framework jointly optimizes masked language modeling and hierarchical multi-label classification. The response generation model uses the predicted target as a control signal to guide generation. This method effectively models the hierarchical dependency relationship between target types and target entities, enhances the structure perception ability of label vectors, maintains the model's language understanding ability, and improves the accuracy of target prediction.

This invention discloses a safety analysis method for ship SOFC systems, belonging to the field of risk prevention and control technology. It includes: identifying the causative factors of the ship SOFC system; constructing a failure fault tree and event tree model; constructing a Bow-Tie model based on the failure fault tree and event tree model; quantitatively analyzing potential causative factors to identify key factors affecting the SOFC system; combining the analyzed ship SOFC system accident causation data and collected ship fuel cell standard and specification data to form a data system and construct a ship SOFC system accident risk prevention knowledge graph; and conducting SOFC system safety analysis based on the ship SOFC system accident risk prevention knowledge graph. This invention clarifies the criticality, hierarchical relationship, and action path of each causative factor; constructs the causative factors into a complex accident causation network; and, combining the semantic information of the knowledge graph and the capabilities of complex network analysis, deeply reveals the accident causation propagation mechanism, providing a comprehensive perspective for understanding the occurrence and development of accidents.

A computer-implemented system and method for identifying citations within regulatory content is disclosed. The method involves receiving image data representing a format and layout of the regulatory content, receiving a language embedding including a plurality of tokens representing words or characters in the regulatory content, and generating a token mapping associating each of the tokens with a portion of the image data. The method also involves receiving the plurality of tokens and token mapping at an input of a citation classifier, the citation classifier having been trained to generate a classification output for each token based on the language embedding and the token mapping, the classification output identifying a plurality of citation tokens within the plurality of tokens. The method further involves processing the plurality of citation tokens to determine a hierarchical relationship between citation tokens, the hierarchical relationship being established based at least in part on the token mapping for the citation tokens.

The invention discloses an LLM-based system-level demand modeling and analysis method and platform, and belongs to the field of demand engineering and system modeling. The invention provides an LLM (Logical Language Model)-driven automatic demand behavior model construction and conflict detection method aiming at the problem that accurate modeling and consistency verification of natural language system-level software demands are difficult. According to the method, control flow logic in a demand text is recursively analyzed by simulating an expert stratified analysis process, and a behavior model is automatically generated. The modeling process comprises the steps of recognizing atomic activities, extracting a hierarchical relation and constructing a behavior model. On the basis, a system-level behavior tree is constructed based on preposition and postposition conditions of behavior nodes, a plurality of demand models are comprehensively analyzed, and behavior consistency analysis and conflict detection on the system level are achieved. According to the method, automatic expansion from the demand-level behavior model to the system-level behavior model can be realized, and an effective technical scheme is provided for automatic modeling and analysis of system-level demands.

The invention provides an R-KGCN emergency disposal method for the silt danger of a floating wing suspension door in the storm surge period of a super-huge tide gate. According to the method, a system framework covering knowledge modeling, reasoning definition and reasoning optimization is constructed on the basis of a relationship-enhanced knowledge graph convolutional network, and structured expression and intelligent reasoning of sediment disaster emergency disposal knowledge are realized. The method comprises the following main technical links: (1) constructing a knowledge graph mode layer and a data layer oriented to a sediment disaster scene, and establishing a'feature-event-disposal 'ternary model and a hierarchical relationship; (2) proposing a structured reasoning problem definition framework of an emergency processing task, and supporting modeling requirements of multi-source, multi-scale and multi-relation semantics; (3) designing an R-KGCN inference algorithm integrated with a semantic relationship enhancement module, and improving the accuracy and interpretability of inference; and (4) forming a knowledge reasoning and intelligent recommendation method oriented to sediment dangerous cases, and providing decision support and emergency response guarantee for operation scheduling of the oversize tide gate.

This invention belongs to the field of web page data parsing technology, specifically relating to a web page data parsing method based on a large language model. The method includes: obtaining the target website URL input by the user; performing preliminary parsing of the input URL using a large language model; parsing the DOM structure of each website and extracting HTML elements and their hierarchical relationships; generating corresponding data crawling scripts based on the parsing results; executing the data crawling scripts to extract the required data from each website; preprocessing the extracted data; fusing the preprocessed data from multiple sources; extracting key information from the fused data; and storing the finally processed and extracted information in a database. This invention achieves automatic parsing of complex web page data, intelligent entity extraction and knowledge expansion, as well as efficient data fusion and deduplication.

This invention relates to a method and system for constructing geographic entities and generating relationships, specifically including: identifying target vector layers from multiple sources, and extracting layer names, attribute field names, and their corresponding attribute values ​​from the target vector layers; performing multi-level filtering and comprehensive scoring based on layer names to determine the standard layer category for optimal alignment of layer names; mapping the attribute field names of the target vector layers to target standard fields using the standard layer category as a reference, and converting the attribute values ​​corresponding to the attribute field names into standard codes to achieve attribute standardization; acquiring the geometric data of the target vector layers, generating target vector entities based on the geometric data, and binding the corresponding standard attributes to the target vector entities; establishing topological relationships, hierarchical relationships, and cross-source entity referencing relationships between entities based on spatial topology analysis and semantic association analysis, thereby forming a structured geographic relationship network.

The invention discloses a hierarchical ontology construction method fusing a large language model and expert knowledge, which fuses field expert knowledge and strong semantic comprehension and generation capability of the large language model, and comprises the following steps: firstly, specialists predefine an initial ontology seed set following a generalization-specialization principle; automatically extracting candidate entity types and attribute types from the unstructured text by utilizing a large language model; through combination of semantic calculation and large language model deep reasoning, the hierarchical relationship between candidate entities and the existing ontology is accurately judged, and the hierarchical structure of the ontology is dynamically adjusted and expanded according to the hierarchical relationship; and finally, strict attribute inheritance consistency verification and redundancy elimination are carried out to ensure the logic consistency of the ontology structure. According to the method, the ontology construction efficiency and quality are remarkably improved, automatic maintenance and evolution of the ontology are achieved, and the technical problems that a traditional domain ontology construction method is low in efficiency, neglects the hierarchical relation between entity types and is difficult to adapt to dynamic evolution of knowledge are solved.

According to the implementation of the present disclosure, a solution for parsing the hierarchical relationship of elements in an image is provided. According to the solution, the second element in the first element is determined based on a feature(s) of the input image and the first element in the input image. The third element in the second element is detected based on the feature and the second element. The first element, the second element and the third element correspond to corresponding regions in the input image. Based on the determination of the second element and the detection result of the third element, a hierarchy indicating the relationship between elements in the input image is determined. In this way, the hierarchy of elements in the image can be obtained without post-processing.

This invention discloses a method for generating and reviewing structured text code. It receives user-inputted control task requirements, supporting input in natural language, structured forms, or graphical flowcharts. A requirement parsing module performs deep semantic analysis to identify control conditions, control actions, and constraints. The task is then transformed into multiple control units via an SCoT chain. An SCoT chain reader generates semantic vectors based on the task requirements, while an AST reader generates an AST representation based on grammatical rules, structure, and hierarchical relationships. A decoder combines the SCoT chain and AST features to predict the next grammatical rule and generate ST code. An interactive automatic review and repair mechanism verifies the syntax and logic of the ST code. If compilation errors occur, a teacher model analyzes the errors and provides repair suggestions, while a student model repairs the code according to the guidance until it meets the expected functionality and passes compilation.

The invention discloses an incremental implicit refinement image classification method based on hyperbolic hierarchical modeling and two-way knowledge transmission, and the method comprises the steps: 1, carrying out the incremental task division of a data set: reconstructing an original image data set into a data set with a two-stage hierarchical structure, and carrying out the division of each task data set; step 2, network training: inputting a training set of a current task, training the hyperbolic hierarchical modeling and knowledge two-way transmission network, and updating model parameters; step 3, testing and outputting classification accuracy: testing on a test set of all the seen tasks and outputting an average increment classification accuracy; and repeating the steps 2 and 3 until no new task appears. According to the method, the dynamic hierarchical relationship is continuously constructed in the hyperbolic space, and the dynamic hierarchical relationship is used as a transmission cost to guide bidirectional optimal transmission between new and old knowledge, so that the problems of poor effect and insufficient knowledge utilization of a static hard hierarchical relationship adopted by a current method are solved, and the accuracy of incremental implicit refined image classification is improved.

The application discloses a code block segmentation method and device, a program product, an electronic device and a storage medium, and relates to the technical field of code segmentation. In view of the problem that a traditional code segmentation method is difficult to balance semantic integrity and information density, a code block segmentation method is provided, which is based on an abstract syntax tree and realizes hierarchical segmentation of code through a parent-child abbreviated block strategy. The core idea is to recursively subdivide code blocks according to needs under the premise of maintaining the integrity of code semantic units, and to organize the code blocks in a parent-child relationship. When a code block is too large or contains a complex internal structure, the code block is divided into a plurality of child blocks. The original parent block does not disappear, but is retained in the hierarchical structure as an abstract parent block, the structural information is retained, and the actual implementation details are carried by the child node blocks. The AST provides a structural guide, the parent-child abbreviated block guarantees dynamic adjustment of the division granularity, and finally output data contains code content and hierarchical relationships.

The invention discloses a complex specification multi-mode understanding method and system based on YOLO two-stage segmentation. The complex specification multi-mode understanding method comprises the following steps that an input specification image is preprocessed; inputting the preprocessed image to a coarse granularity detection stage of an improved YOLOv8 network, and generating a coarse granularity 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 relation structure based on an accurate layout segmentation result; according to the layout hierarchical relation structure, multi-modal feature extraction is carried out on the accurate layout segmentation result, and a matching weight is calculated; jointly inputting the image-text semantic alignment result and the layout hierarchical relation structure into a logic structure modeling module, and constructing a layout element graph; and generating a knowledge graph semantic output result according to the structured logical reasoning result. According to the method, YOLO two-stage segmentation and multi-modal semantic alignment are adopted, and automatic structured understanding of a complex specification is achieved.

According to embodiments of the present disclosure, a method, an apparatus, a device and a storage medium for generating code are provided. The method comprises: obtaining interface design data for a target interface; generating an intermediate design representation based on the interface design data; generating a structured design representation with a hierarchical structure by identifying a layout and a hierarchical relationship of at least one interface element in the intermediate design representation; updating the structured design representation by identifying at least one component corresponding to a predetermined computer language in the structured design representation using a component identification model; and generating a target code of the target interface based on the updated structured design representation, the target code having a format of the predetermined computer language. In this way, the flexibility and reliability of the code generation process can be improved.

The invention discloses a code block segmentation method and device, a program product, electronic equipment and a storage medium, and relates to the technical field of code segmentation. Aiming at the problem that semantic integrity and information density are difficult to consider in a traditional code segmentation method, the invention provides a code block segmentation method which is based on an abstract syntax tree and realizes hierarchical segmentation of codes through a father-son thumbnail partitioning strategy. According to the core idea, on the premise that code semantic units are kept complete, code blocks are subjected to recursive subdivision according to needs, and the code blocks are organized according to the set membership. When a certain code block is too large or contains a complex internal structure, the code block is split into a plurality of sub-blocks. The original parent block does not disappear, but is reserved in the hierarchical structure as an abstract parent block, structural information is reserved, and actual implementation details are borne by child node blocks. The AST provides structural guidance, father-child thumbnail partitioning ensures dynamic adjustment of partitioning granularity, and finally output data contain code content and have a hierarchical relationship.

The application belongs to the technical field of software security, and discloses a terminal open source software security detection and early warning method, system, device and terminal. The open source software dependent library and hierarchical relationship are parsed according to the SBOM file of the software, and external threat information sources are accessed according to preset conditions. The latest vulnerability threats are extracted from the vulnerability information shared by the official information security vulnerability sharing platform and the open source software development platform, and are matched with the hierarchical relationship based on the SBOM knowledge, so as to analyze whether the terminal exists software system vulnerability threats and potential security risks caused by the hierarchical relationship of the software supply chain. If risks are found, safety early warning information is produced, and understandable safety alarms are sent to users. Recommended safety solutions are generated according to preset models or intelligent algorithms, and users are reminded to take relevant safety measures, including updating software and disabling software. The application can be used on various terminals to detect the security risks of software systems, and to upgrade and guarantee the security of software systems.

The invention relates to the technical field of time sequence knowledge graph reasoning, and provides a knowledge graph representation learning model based on multi-view and long-short term hierarchical relationship, which comprises a multi-view construction module, an embedded coding module and a fusion decoding module. The multi-view construction module extracts a complete view, a query-related view and a query-unrelated view from the historical sub-graph sequence, and connects the same entities with different timestamps to construct a global graph. The embedded coding module comprises a multi-view cyclic encoder and a hierarchical relation graph neural network, the multi-view cyclic encoder processes three views through a graph convolutional network and a time gate mechanism to learn short-term dynamic conditions, and the hierarchical relation graph neural network processes a global graph through a time coding function and an attention mechanism to learn long-term features. The fusion decoding module carries out weighted fusion on long and short term historical embedding through a gating integration unit, and then a convolution decoder carries out convolution and similarity matching on the fused embedding so as to calculate probability distribution of each candidate entity.

The invention provides a method and device for checking a classification result and related equipment, a computer constructs a local expert knowledge base and expert information based on the digitization ability of expert experience, and a big language model is combined with the local expert knowledge base and the expert information to automatically check the classification result. The method for checking the classification result comprises the steps of obtaining a target classification result obtained by classifying target data through a target classification algorithm; according to knowledge involved in the classification process of the target data, a verification prompt word prompt is constructed, and the knowledge comprises at least one of a classification rule and a hierarchical relation referred to in the classification process of the target classification algorithm; a first large language model LLM is called, the target classification result is verified according to the verification prompt word, a verification result is obtained, and the verification result indicates whether classification of the target data by the target classification algorithm is correct or not.

The application relates to a spacecraft intelligent software virtual simulation test scene intelligent generation method, and belongs to the technical field of spacecraft software testing and simulation, which comprises the following steps: an IR structure with rich semantics is defined in advance; through a preset structured prompt word, a large language model LLM is called to recognize and extract task targets, entities, behaviors, environments, constraints and disturbance elements in natural language instructions; the LLM analyzes the extracted elements into nodes, node attributes and time sequence relationships, logical relationships and hierarchical relationships between the nodes in the predefined IR structure, generates a structured IR; a generated IR JSON file is loaded, and according to a preconfigured conversion rule library of the IR structure to a scene description language, the structured IR is converted into an executable simulation script; a simulation engine analyzes and executes the script, and instantiates a specific and high-fidelity test scene. The problems of low automation, high professional threshold and poor scalability in the simulation test of spacecraft intelligent software are solved.

The application provides a tree structure-based automatic configuration method for depth contour notes of a navigation chart, and belongs to the technical field of marine surveying and mapping. The application overcomes the two shortcomings of the current automatic configuration method for depth contour notes, i.e., the lack of coordination between the hierarchical relationship and spatial arrangement of the depth contour notes and the lack of consideration of the trend of the depth contour notes. Experiments show that the method can ensure the readability of a single note, and can configure depth notes that are coordinated with the hierarchical relationship and spatial arrangement of the depth contour notes and are evenly distributed along the trend of the depth contour notes.

The application discloses a kind of manufacturing equipment design requirement intelligent auxiliary acquisition method and system, belong to the technical field of industrial design;Among them, the hierarchical relationship of manufacturing equipment design requirement is established, and then the hierarchical relationship database of manufacturing equipment historical design requirement is constructed;Design requirement intelligent auxiliary acquisition model is constructed, and the design requirement intelligent auxiliary acquisition model is trained based on the hierarchical relationship database of manufacturing equipment historical design requirement;The original design requirement information of new manufacturing equipment is collected, and the design requirement information is obtained using the design requirement intelligent auxiliary acquisition model, and the design requirement information includes design requirement information hierarchical relationship and labeled abnormal requirement;Modification, confirmation and output calculated design requirement information.The manufacturing equipment design requirement intelligent auxiliary acquisition method and system provided in the application not only improve the accuracy and completeness of equipment design requirement acquisition, but also greatly improve the acquisition efficiency and reduce the acquisition cost.

The present application relates to a kind of PEG-based AADL code to graph multilevel conversion method, belong to embedded system architecture modeling and analysis field.The present application defines PEG grammar rule.The grammar rule can accurately describe the basic element of AADL language, recursive structure and grammar priority;Build AADL code parser;Based on the defined PEG grammar rule, the parser can be built layer by layer AADL code, identify each design element, and capture and feedback grammar semantic problem in the parsing process;Generation multilevel abstract syntax tree AST.AST can clearly express the node construction of AADL, hierarchical nesting, attribute mapping and element relationship.The fourth step, multilevel abstract syntax tree AST is converted into graphical expression.Each level of system architecture is intuitively presented by graphical way.The present application can clearly present the hierarchical relationship between different design elements, facilitate designer and developer to analyze, understand and modify.

The application provides a network attack hierarchical detection model training method, a detection method and equipment. The training method comprises: based on a hierarchical label system containing attack scene labels and attack type labels, using a graph attention network to encode the hierarchical relationship; using the encoding result and network traffic data to train a classification model based on prompt learning, outputting a collaborative prediction result of attack scenes and types by calculating the similarity between traffic prompt representation and global label embedding; determining a supervision signal according to real labels, optimizing the classification model through adversarial training, and obtaining a final detection model. The application can realize collaborative identification and hierarchical tracing of attack scenes and types, provide more fine-grained threat perception, significantly improve the robustness, generalization ability and detection stability of the model in a dynamic adversarial environment, thereby improving the network attack identification accuracy, and improving the accuracy and efficiency of network security operation and maintenance.

The invention discloses a method for realizing accurate intention recognition in an AI question and answer application. The method comprises the following steps: pre-defining a semantic analysis dimension; constructing a semantic analysis dimension tree before system deployment based on semantic analysis dimensions, and defining a hierarchical relationship between the dimensions and a semantic path from a root node to a leaf node; making a dimension value rule, deeply associating the dimension value rule with nodes and semantic paths in the semantic analysis dimension tree, and constructing a dynamic rule constraint engine; and analyzing user input based on a structured framework of a semantic analysis dimension tree in combination with a dimension value rule, generating a structured semantic intention, and performing semantic task distribution and execution. According to the method, a hierarchical semantic analysis dimension tree is constructed, intention analysis is converted from point mapping to structured path searching, and the problem that structured analysis of the composite intention is missing is effectively solved; through deep collaboration of a dynamic rule constraint engine and a semantic analysis dimension tree, logic consistency and stable output of an analysis process are ensured.

The application provides a kind of complex equipment system fault propagation analysis method and system based on hierarchical model, it is related to security analysis technical field, first determine analysis purpose and security demand;Then successively establish the hierarchical model of analysis object, function model and behavior model;Again, according to the hierarchical model, function model and behavior model of analysis object, the failure logic of analysis object is analyzed;Failure logic refers to the specific form of behavior deviation caused by analysis object;Finally, by traversing the cause-effect relationship defined in the failure logic of each component, the failure output of the previous component is taken as the failure input of the next component, the output of the next component is obtained by calculation and reasoning according to the logical relationship, and the analysis of fault propagation path is completed through the layer-by-layer transmission of failure deviation.The application is aimed at the complexity, hierarchy and other characteristics of complex equipment system, and comprehensively analyzes the hierarchical relationship of the system from the two-dimensional perspective: longitudinal and transverse.