63 results about "Hierarchical relation" patented technology

The invention discloses a structured text code generation and review method, which comprises the following steps of: receiving a control task demand input by a user, supporting natural language, structured form or graphical process input, performing deep semantic analysis by utilizing a demand analysis module, identifying control conditions, control actions and constraint factors, and generating and reviewing a structured text code. The task is converted into a plurality of control units through the SCoT chain; the SCoT chain reader generates a semantic vector according to a task demand, the AST reader generates AST representation through a grammar rule structure and a hierarchical relationship, and the decoder predicts a next grammar rule and generates an ST code in combination with the SCoT chain and AST features; and verifying grammar and logic of the ST code through an interactive automatic review and repair mechanism, if compiling errors occur, analyzing errors by the teacher model and providing repair suggestions, and performing code repair by the student model according to guidance until the code conforms to an expected function and passes compiling.

This invention introduces a Hierarchical Tree-Based Attention (HTA) mechanism to optimize transformer-based large language models (LLMs) for processing hierarchical documents. HTA leverages a lineage-based approach to model parent-child and sibling relationships, preserving document hierarchy while reducing memory and computational demands. A novel data processing pipeline segments content into blocks, establishes hierarchical relationships, and produces annotated input for LLMs. During attention calculation, embeddings for lineage-related blocks compress information outside the immediate hierarchy, ensuring scalability without sacrificing accuracy. HTA enables efficient applications in structured document processing, such as legal, healthcare, and education, while improving generative tasks like summarization and question answering. This approach advances hierarchical NLP with superior fidelity and reduced latency.

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 provides a fine-grained multi-dimensional configuration permission control method and system, electronic equipment and a storage medium, and aims to solve the problem that permission division cannot meet fine-grained permission control requirements, the method comprises the following steps: on the basis of an RBAC model, adding organization elements, and adding an organization structure hierarchical relationship, the relationship between the organization structure and the content of each part in the model is obtained; a dynamic role allocation and role inheritance mechanism is introduced, the inheritance relation between roles is specified when the roles are defined, so that the child-class roles can inherit the permission set of the parent-class roles, and permission expansion is carried out; performing permission configuration, performing cross organization on the function permission and the data permission, then distributing the function permission and the data permission to corresponding organization roles, ensuring that each organization role has the basic permission, and expanding private permissions for the organization roles according to different business requirements; the organization roles are distributed to the users, so that authority distribution of the users is realized. According to the invention, validity and timeliness of authority management can be ensured.

The invention discloses a complex table question-answering method based on a tree structure, electronic equipment and a medium, and the method comprises the following steps: responding to header information of a complex table, and outputting a header tree structure by a large language model; decomposing the question into a plurality of keywords through a large language model, and aligning the keywords with the header tree structure to obtain a keyword-tree structure; and in response to the keyword-tree structure, guiding the large language model to carry out iterative reasoning through a React-Style prompt method to retrieve from the complex table, and outputting an answer. According to the method, the multi-level titles of the table are organized into the tree structure, so that the large language model can more clearly understand the hierarchical relationship of the table, and related information can be more accurately positioned when questions are answered.

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 present disclosure relates to systems, non-transitory computer-readable media, and methods for hierarchical entity segmentation. In particular, in one or more embodiments, the disclosed systems receive a digital image comprising a plurality of object entities. In addition, in some embodiments, the disclosed systems generate, utilizing a segmentation model comprising parameters generated according to pseudo-labels indicating hierarchies of segmentation masks for a set of training digital images, a hierarchical segmentation indicating hierarchical relations of the plurality of object entities of the digital image. Moreover, in some embodiments, the disclosed systems generate, for the digital image, a segmentation map from the hierarchical segmentation of the plurality of object entities.

The invention relates to the technical field of aircraft manufacturing, and discloses a design method and system for an aircraft assembly technological procedure template and a storage medium. According to the method, the assembly type, the technological procedure template type and the process type of aircraft assembly and key conditions influencing the process appearance are analyzed from the essential angle of assembly; logic rules of key conditions influencing process contents are combed, and process procedure contents with fixed rules are presented in a process procedure template in a certain structural form and hierarchical relationship, so that rapid compiling of aircraft assembly process procedures is realized, and a final complete process procedure document is formed; the technical problems that technological procedure compiling is not combined with the assembly technological process, the technological procedure compiling efficiency is low, and the technological procedure compiling accuracy is low are solved.

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.

The present invention discloses a semantic alignment method for XBRL financial information elements based on domain ontology. The method comprises the following steps: extracting candidate domain concepts and constructing a domain dictionary; obtaining financial report annotation text as a corpus; performing word segmentation, part-of-speech tagging, and named entity recognition on the corpus to obtain all part-of-speech tagging results and constructing a stop word vocabulary for the financial report domain; expanding the corpus based on an LDA model and semantically expanding the financial report annotation text based on the expanded corpus; converting the vocabulary in the new corpus into vocabulary feature vectors; extracting hierarchical relationships and non-classification relationships; establishing an alignment method and performing semantic alignment of financial information elements. The present invention uses domain ontology to formally represent financial report terms and calculates the semantic similarity between tags in a tag link library, thereby achieving semantic alignment between financial information elements and maintaining consistency between XBRL reports.

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.

The present application discloses an API task requirement processing and access method for a browser, and related devices. The method includes: inputting an API task requirement into a large language model to obtain an initial API code file output by the large language model; using a parser to generate a corresponding abstract syntax tree from the initial API code file; using the abstract syntax tree to extract context information and establish a hierarchical relationship; inputting the hierarchical relationship into the large language model again to obtain a target API code file output by the large language model; when the target API code file meets the API task requirement, using the target API code file as the final API file corresponding to the API task requirement. Through the above method, the adaptation degree between the API code file and the API task requirement is improved.

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 cognitive diagnosis method based on multi-level interaction constraint perception, relates to the technical field of cognitive diagnosis, and aims to more accurately perform quantitative analysis on cognitive states of students, firstly, based on historical performance data of the students, a hierarchical relation graph of knowledge concepts, practice and student abilities is constructed, and the knowledge concepts, the practice and the student abilities are obtained; the hierarchy and relevance among the three are comprehensively described, then a multi-round iteration hierarchical perception neural network is designed, through gradually associating knowledge concepts with practice hierarchies and practice and student ability hierarchies, features of different hierarchies are fused in multi-round iteration, question difficulty and student ability features with more expressive force are generated, and finally, the question difficulty and student ability features are extracted. In the diagnosis stage, the framework further combines student ability characteristics and personalized knowledge proficiency of multi-level interaction constraint perception to realize accurate evaluation of the student knowledge state, and the question difficulty and the multi-level characteristics thereof are fused to provide more comprehensive support for cognitive diagnosis.

The present invention discloses a method for updating out-of-vocabulary words in a knowledge graph considering precise semantic relationships, including: extracting entity multi-modal features such as names, name characters, synonymous features, etc. from the target graph and the graph to be matched containing out-of-vocabulary words; performing representation learning on the multi-modal features through a feature encoding method to generate embedding vectors and normalizing them; using an attention mechanism to dynamically assign weights according to the feature importance, and fusing the weighted multi-modal feature vectors to obtain the joint feature vector of the entity; evaluating the similarity by calculating the Manhattan distance between the entity joint feature vectors, completing entity alignment matching, and realizing the association of entity hierarchical relationships. The method of the present invention not only improves the ability of the knowledge graph in dealing with out-of-vocabulary words, but also enhances the semantic richness and hierarchical structure of the knowledge graph, and has important practical significance for the construction and application of the knowledge graph.

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 present disclosure provides systems, devices, and methods for using a user interface associated with musical composition. An example method may comprise outputting interface objects representing musical properties and establishing hierarchical relationships between the objects. A first interface object may visually represent a first musical property. A hierarchical relationship may be determined between the first object and a second object, indicating inheritance of the first property. Changes to the first property in the first object may update the second object.

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.