11 results about "Knowledge organisation" patented technology

The application discloses a kind of publishing field knowledge service construction methods based on knowledge graph, it is related to intelligent digital publishing technical field, including, according to publishing content structure node set, constructs publishing content structure diagram, and in combination with publishing original resource set executes publishing field semantic information extraction and semantic correlation analysis, obtains publishing semantic diagram;From the structural distribution characteristics and content anchoring characteristics of semantic node in publishing resource in publishing semantic diagram are extracted, and the anchor point edge between publishing semantic diagram and publishing content structure diagram is established, and the multi-granularity anchor point double diagram is formed;Based on graph service execution plan, execute double diagram collaborative retrieval and service path generation, obtain knowledge service candidate set, and carry out service ordering and arrangement, generate publishing field knowledge service content.The application realizes the collaborative mapping of semantic relationship and content bearing position, enhances knowledge organization precision and service direction.

The present application relates to the technical field of ecological environment management, in particular to a knowledge graph construction method and system for regional ecological environment management technology, wherein the method comprises: receiving a standardized technology template file to be constructed as a knowledge graph to read a technology library worksheet; performing a preset normalization processing on the technology library worksheet to obtain a normalized technology library worksheet; taking the key technology of ecological environment management as a root node, generating a stable node identifier of the normalized technology library worksheet to construct a multi-level node relationship; taking the stable node identifier as a unique index, performing attribute validity determination, attribute fusion and relationship deduplication on the multi-level node relationship to obtain a unified graph data file. Thus, the problem of lack of a high-quality, consistent and knowledge organization conversion method for regional ecological environment management technology data in the prior art is solved.

The application discloses an audit literature mind map generation method and system based on feature refining and a large language model, first extracts object theme information, text information, reference object information and hierarchical information in target audit literature and converts them into structured audit text information, and then adopts a hybrid weight model to calculate the global importance of keywords in the structured audit text information and extract target text keywords; the application realizes the function of efficiently generating corresponding audit mind maps for audit literature, and through the adoption of a graph neural network, the logical coherence of text object information can be enhanced and the logical relationship between different nodes can be ensured to be rigorous, and through rule constraints, the text information can be ensured to conform to the audit field specifications, which not only can enhance the systematicness and logicalness of knowledge organization, but also can finely control the generated content, and at the same time, can provide accurate audit literature reading assistance for users and greatly improve the understanding and analysis efficiency of audit literature.

This invention relates to the field of database construction technology, and discloses a knowledge base construction method and system based on AI text parsing and hybrid retrieval. By integrating semantic relevance and document layout features through adaptive block segmentation, it achieves accurate identification of core semantic units in the text and maintains logical integrity in the division, fundamentally avoiding information fragmentation and laying the foundation for high-quality knowledge organization. Secondly, through a hybrid retrieval mechanism combining keyword, semantic vector retrieval, and multi-dimensional re-ranking, it effectively balances retrieval response speed with the depth and accuracy of results, meeting users' multi-level query needs from rapid location to in-depth correlation mining. Finally, through dynamic updates and automatic association mapping functions, it achieves real-time synchronization and intelligent association of newly added knowledge, not only ensuring the timeliness of the knowledge system but also proactively building a cross-document knowledge network, thereby breaking down information silos and enhancing the overall utilization value and discovery capability of knowledge.

The application relates to the technical field of knowledge graphs, can be applied to business scenarios such as financial technology, and discloses a time-series knowledge graph driven knowledge retrieval method, device, equipment and medium, which comprises the following steps: subjecting unstructured text in a target field to field adaptability training to obtain a field-specific large model, using the model to extract entity relationship triples from business source text and construct a dynamic time-series knowledge graph, simultaneously performing comparative learning training on multi-modal data to establish cross-modal semantic indexing, and when a query request is received, performing joint retrieval and outputting feedback content. Through the fusion of field semantic modeling, time-series knowledge organization and cross-modal retrieval mechanism, the application enables scattered unstructured and multi-modal data to form a knowledge system that can evolve over time and be uniformly retrieved, thereby improving the accuracy of knowledge acquisition and the efficiency of business response.

The application relates to a law enforcement document element extraction and law article matching system based on retrieval enhancement generation, which comprises the following modules: document access, text analysis, element modeling, law regulation knowledge organization and joint index, retrieval enhancement, law article matching, risk identification, result generation and audit record, etc. Through the structural analysis and case element modeling of law enforcement documents, the candidate law articles are recalled by combining keyword retrieval, semantic retrieval and relationship retrieval, the law article matching is completed through the alignment and consistency checking of conditions, the risks of law article omission, insufficient evidence, procedure loss and abnormal punishment are identified, and finally the standardized results are generated and the whole process is left with traces and traced back. The system can improve the processing efficiency of law enforcement documents and the accuracy of law article application, and enhance the standardization and auditability of law enforcement.

The application discloses an audit literature mind map generation method and system based on feature refining and a large language model, first extracts object theme information, text information, reference object information and hierarchical information in target audit literature and converts them into structured audit text information, and then adopts a hybrid weight model to calculate the global importance of keywords in the structured audit text information and extract target text keywords; the application realizes the function of efficiently generating corresponding audit mind maps for audit literature, and through the adoption of a graph neural network, the logical coherence of text object information can be enhanced and the logical relationship between different nodes can be ensured to be rigorous, and through rule constraints, the text information can be ensured to conform to the audit field specifications, which not only can enhance the systematicness and logicalness of knowledge organization, but also can finely control the generated content, and at the same time, can provide accurate audit literature reading assistance for users and greatly improve the understanding and analysis efficiency of audit literature.

The application discloses a medical personal knowledge base management method and system based on a large model, equipment and a medium, mainly related to the technical field of knowledge base management, to solve the problems that the existing scheme has multiple sources of medical knowledge, it is difficult to realize cross-modal unified modeling and integrated analysis, it lacks personalized knowledge organization and calling mechanism, and it cannot support context understanding and weak retrieval ability. Including: configuring a semantic question and answer framework in a reading interface, obtaining actual retrieval requirements through an input box in the semantic question and answer framework; obtaining semantic structure and keyword information by analyzing the actual retrieval requirements through a large model; determining corresponding knowledge segments from a preset knowledge database according to the relationship between the keyword information and the knowledge label vector; and obtaining an output answer result by using a medical AI large model based on the corresponding knowledge segments, the actual retrieval requirements and the preset knowledge database.

This application relates to the fields of artificial intelligence and natural language processing, and particularly to a method and apparatus for generating structured documents. Designed for structured document generation tasks, it integrates an autoencoder semantic compression mechanism, an adaptive clustering strategy, and a structured field-driven method to address issues in existing solutions such as static knowledge organization, weak control over generated content, and poor system self-optimization capabilities. Employing a modular architecture, it integrates multiple functional modules including structure parsing, semantic encoding, clustering construction, field matching, content generation, and feedback optimization. It can be deployed on local terminals or in cloud service environments, achieving fully automated generation of structured documents. This application significantly improves the automation level and knowledge adaptation capabilities of structured document generation, making it particularly suitable for document scenarios requiring long-term evolution, structural stability, and semantic accuracy, such as government documents, research materials, and corporate reports. It possesses significant engineering deployment value and application prospects.