25 results about "Knowledge framework" patented technology

The invention relates to the technical field of crime abnormity early warning, and particularly provides a crime abnormity early warning method based on a legal knowledge framework and a star graph neural network. The method comprises the steps of obtaining crime determination abnormal data through a judgment document; obtaining normal crime determination data through the legal data set; constructing two types of legal knowledge frameworks of offender name exclusiveness and cross-offender name universality; a Qwen3-14B model is utilized to construct a structured legal element data set with double aligned frames; the method comprises the following steps of: embedding legal elements into dense vectors through a bert-based-history model, and constructing a star graph neural network crime determination model; based on the two crime abnormity early warning mechanisms, performing crime abnormity early warning to obtain a crime abnormity early warning model; according to the method, the problem of the existing AI-assisted law application technology in crime name false complaint recognition is solved, and the recognition accuracy of crime name application errors in judicial scenes is improved.

The invention relates to a multi-source information knowledge fusion and intelligent retrieval method and system, and the method comprises the steps: obtaining multi-source heterogeneous data, and carrying out the unified knowledge modeling of the multi-source heterogeneous data, and obtaining a unified knowledge framework; and based on the unified knowledge framework, calling a large language model to perform structured preprocessing on the multi-source heterogeneous data to generate a structured knowledge triple. And performing structured processing on the structured knowledge triple through the attribute graph, and performing vectorization storage on each entity associated data through the embedded model to obtain a fused knowledge body. And receiving a user query request, and in response to the user query request, performing deep analysis on the user input data to obtain a user query intention and query elements. According to the method, the condition graph is constructed according to the query intention and the query elements of the user, and the condition graph is mapped into the knowledge network for entity positioning and condition graph matching to generate the structured retrieval result, so that the network overhead and scheduling delay are reduced, and the retrieval response speed and accuracy are improved.

Current generative AI systems using large language models (LLMs) face challenges including non-deterministic outputs, hallucinations, outdated information, and resource-intensive training. This disclosure introduces topic maps for constrained retrieval augmented generation to address these issues. The technique leverages existing LLMs while constraining outputs to specific, user-defined content domains. Topic maps, composed of topic names, descriptions, and relevant resource references, create a curated knowledge base that guides agent responses. This approach reduces hallucinations, improves consistency, and allows for dynamic updates without model retraining. The method involves receiving a query, identifying relevant topic maps, transmitting the query and references to an AI agent, and generating constrained responses. By providing a structured, updatable knowledge framework, this method enhances the accuracy, reliability, and adaptability of generative AI systems.

This invention relates to a method and system for multi-source information knowledge fusion and intelligent retrieval. The method includes: acquiring multi-source heterogeneous data and performing unified knowledge modeling on the multi-source heterogeneous data to obtain a unified knowledge framework. Based on the unified knowledge framework, a large language model is invoked to perform structured preprocessing on the multi-source heterogeneous data to generate structured knowledge triples. The structured knowledge triples are then structured using attribute graphs, and the associated data of each entity is vectorized and stored using an embedding model to obtain a fused knowledge body. User query requests are received and responded to by performing deep analysis on the user input data to obtain the user's query intent and query elements. A condition graph is constructed based on the user's query intent and query elements, and the condition graph is mapped to a knowledge network for entity localization and condition graph matching to generate structured retrieval results. This reduces network overhead and scheduling latency, and improves retrieval response speed and accuracy.

The invention provides a transformer fault maintenance virtual training method and system based on multi-modal cooperation. The method comprises the following steps: constructing a multi-modal knowledge graph of transformer fault data; pre-testing the trainee by adopting a preset collaborative training system, determining the initial proficiency of the trainee, and determining an eye movement triggering threshold of the trainee by adopting a preset fault complexity optimization algorithm and a preset eye movement triggering threshold algorithm; according to the eye movement data of the trainee and the eye movement triggering threshold value of the trainee, fault associated data in the multi-mode knowledge graph are called, a preset virtual-real feedback intensity algorithm is adopted, fault interaction data of the trainee and the collaborative training system are obtained, and then a personalized training scheme is generated. According to the invention, trainees are assisted to construct a complete fault maintenance knowledge framework, knowledge fragmentation is avoided, association understanding is enhanced, the problem of missing practical operation is solved, a personalized training scheme is generated, the training pertinence and efficiency are improved, and the skill improvement period is shortened.

The invention provides a normal school student teaching ability evaluation method based on a affair knowledge graph fused with a big language model. The method comprises the following steps: S1, acquiring graphic and text information of teaching content and video information of a target object; s2, extracting knowledge content from the graphic and text information, and constructing a subject knowledge graph according to the knowledge content; s3, according to the video information and the subject knowledge graph, event elements in the video information are extracted, and event coding data are obtained; s4, constructing a affair knowledge graph based on the event coding data; s5, calculating a teaching ability score of the target object according to the event coding data; and obtaining personalized ability evaluation feedback of the target object based on ability interpretation of the large language model. According to the method, the behavior data and the image-text data of the target object are collected, and the teaching behavior and the knowledge framework in the teaching process of the normal school students are used as characterization of the teaching ability of the normal school students, so that the teaching ability can be evaluated more comprehensively and accurately.

The invention relates to the field of multi-modal modeling, and provides a three-dimensional enterprise knowledge base construction method and system. The method comprises the following steps: classifying and marking knowledge assets to be constructed according to a preset dimension system, and extracting semantic feature information corresponding to multiple dimension knowledge nodes to obtain a multi-dimensional cross knowledge framework; knowledge nodes in the multi-dimensional cross knowledge framework are stored in a graph database, a knowledge association network is established, and a dynamic knowledge graph is obtained; collecting user feature data, and generating a user knowledge demand portrait according to the user feature data; performing matching calculation on the user knowledge demand portrait and knowledge nodes in the dynamic knowledge graph, and screening matching results to obtain a target knowledge push list; and determining an access permission level according to the role permission attribute of the user, performing permission verification on the knowledge nodes in the target knowledge pushing list based on the access permission level, and generating personalized knowledge content. According to the invention, the knowledge management efficiency, the delivery accuracy and the security are improved.

This invention discloses a system for converting tacit knowledge into explicit knowledge based on knowledge graphs and large models. It includes a knowledge system ontology modeling and management module for constructing and maintaining the knowledge system ontology model in large model applications; a data access and knowledge graph construction module for mapping and loading multi-source heterogeneous data onto the knowledge system ontology; an ontology virtual business environment engine module; a tacit knowledge mining and explicit knowledge generation module that, in a virtual environment, uses graph analysis and large model reasoning to mine tacit knowledge and generate explicit knowledge; and a business strategy planning and workflow orchestration module that transforms explicit knowledge into executable business strategy plans and workflow orchestrations. Through the knowledge system ontology modeling and management module, a systematic knowledge framework is constructed, achieving systematic accumulation of enterprise tacit knowledge, effectively preventing knowledge loss, and improving knowledge reusability and scalability.

The invention discloses a knowledge graph construction method and system, and the method comprises the steps: carrying out the feature extraction of obtained multi-source operation and maintenance text data, and generating a context vector feature, a static word vector feature and a statistical text feature; carrying out weighted fusion on the three types of features to generate text representation; wherein the time sequence and causal ontology serves as a weight adjustment basis, the larger the similarity between the multi-source operation and maintenance text data and the ontology is, the larger the weight coefficient corresponding to the context vector feature is, and the time sequence and causal ontology is a structured knowledge framework about a time sequence rule and a causal mechanism; recognizing an entity and an entity association relationship based on the generated text representation, and generating a target result through entity alignment and information fusion processing; and finally, constructing the knowledge graph according to the target result. According to the embodiment of the invention, through multi-dimensional feature extraction and in combination with the weighted fusion strategy guided by the time sequence and the causal ontology, accurate identification of the entity and the entity association relationship is realized, and then the accuracy of knowledge graph construction is improved.

The application provides an intelligent international education management method and system, comprising: obtaining term interpretation text content and corresponding involved knowledge point list in each language version teaching resource, identifying interpretation difference degree and semantic deviation degree of the term in different teaching systems, and obtaining preliminary evaluation result of meaning deviation of the term between different languages; obtaining term application instances and context expression methods in student homework, extracting actual application scene of the term in the homework text and matching with the involved knowledge point list, combining the preliminary evaluation result of the meaning deviation, and determining the semantic deviation distance; according to the interpretation version of the divergence classification result and the unified semantic benchmark, dynamically updating the reference relationship of the term in the teaching resources between the chapters and the hierarchical structure between the knowledge points in the teaching materials, and obtaining the aligned knowledge framework.

The invention provides a dialysis patient management system and method based on mobile medical treatment, and the system comprises a multi-dimensional data collection module which is used for collecting the multi-dimensional data of a dialysis patient; the dynamic data display module is used for displaying the collected multi-dimensional data; the self-management module is used for analyzing the physiological index data of the patient and giving a self-management suggestion for the dialysis patient according to an analysis result; the cloud database is used for storing knowledge architecture of related diseases of the dialysis patient, so that the dialysis patient can perform self-retrieval according to requirements; and the grading alarm system is used for analyzing the physiological index data and the self-management data of the dialysis patients, dividing alarm grades according to analysis results and crisis degrees, and giving an alarm according to the alarm grades. According to the invention, comprehensive and multi-dimensional evaluation and systematic intervention on the dialysis patient can be realized, the self-management ability of the dialysis patient is improved, and the dialysis sufficiency and life quality of the dialysis patient are further improved.

The invention discloses an automatic bid invitation file generation method and system based on a large model, and the method comprises the steps: obtaining and analyzing a bid invitation demand document, and determining a plurality of document logic units in the bid invitation demand document; analyzing each document logic unit to determine a key semantic entity, and analyzing the key semantic entity to determine a core demand of each document logic unit; retrieving a template knowledge framework matched with the core demand from a preset knowledge database based on the core demand, and constructing a retrieval data set based on the template knowledge framework and the core demand; the retrieval data set is input into a preset language large model for text output, and an initial bid invitation file is obtained; and verifying and optimizing the content of the generated initial bid invitation file to obtain a formal bid invitation file. According to the method, the big language model serves as an intelligent brain and is combined with a professional bid invitation knowledge base and a rule engine, the intention of a user can be accurately understood, high-quality and compliant texts are generated, and professionals are liberated from tedious and repeated document work.

The application discloses an AI-assisted experimental teaching system, which organically integrates a teaching process with artificial intelligence technology, constructs a whole-process intelligentized auxiliary teaching of 'pre-class preparation-in-class operation-post-class review', and preliminarily constructs a knowledge framework for students through man-machine intelligent interaction and virtual two-dimensional simulation experiment operation, and completes intelligent preparation; the system realizes auxiliary guidance and error avoidance in the operation process through real-time monitoring and intelligent judgment; the system provides post-class homework correction assistance for teachers through a photographing automatic evaluation system, and reduces single repetitive work; the system provides accurate weakness evaluation and improvement suggestions for students through dynamic review question generation and individualized evaluation reports, and is characterized by AI assistance as a core, full-fledged teaching, teaching individualization, high efficiency and intelligence.

This invention discloses a concept graph-based method for enhancing astronomical computational reasoning instructions, comprising the following steps: obtaining seed problems labeled with subdomains and topics as basic input; extracting knowledge points from the seed problems using a large language model to establish a knowledge framework covering subdomains, topics, and knowledge points; and transforming problem instances into conceptual representations; constructing a concept graph based on the knowledge framework; executing a dynamic random walk algorithm on the concept graph to output a complete concept combination; and using the complete concept combination to guide the large language model in generating astronomical computational problems and corresponding reasoning processes through example matching, data deduplication, and thought chain distillation. This invention, by constructing a concept graph and employing a random walk strategy, improves the diversity and logical rigor of the generated data, providing a new path for optimizing astronomical computational reasoning instructions.

The invention discloses a spacecraft intention reasoning optimization method based on a multi-hop knowledge chain, and the method comprises the steps: firstly constructing a hierarchical knowledge framework containing spacecraft information, subsystems, components, behaviors and possible intentions, and extracting a dynamic sub-graph which fuses time sequence dependence and is associated with inherent semantics through a sliding window; the orbit dynamics constraint is embedded to ensure logic self-consistency; a hierarchical reasoning framework with rule guidance and graph neural network cooperation is adopted, an upper layer rapidly screens a high-confidence-coefficient intention candidate set based on predefined behavior pattern rules and orbital constraints, and a lower layer aggregates multi-hop semantic information along a knowledge chain through a lightweight graph neural network to generate fine-grained intention probability distribution; and finally, matching a historical behavior template through a dynamic time warping algorithm, and combining sequential logic constraint verification to realize intention dual verification. According to the method, the accuracy, the real-time performance and the engineering realizability of spacecraft behavior intention reasoning in a complex scene can be remarkably improved.

The application relates to the technical field of natural language processing, and discloses a method, equipment and medium for constructing a domain knowledge framework in a human-computer dialogue scenario. The method comprises the following steps: receiving a multi-round dialogue between a user and a natural language model, identifying a theme and a named entity of the multi-round dialogue through the natural language model, and generating a knowledge framework construction instruction; based on the knowledge framework construction instruction, constructing and initializing a structured domain knowledge framework according to a pre-constructed domain knowledge graph; in subsequent dialogue rounds, continuously identifying newly added themes or named entities, and dynamically expanding or associating the constructed domain knowledge framework; before the natural language model generates a reply, performing knowledge reasoning based on the currently constructed domain knowledge framework, verifying the named entities and their relationships involved in the reply, and feeding back the verified reply to the user. The method improves the accuracy and depth of the natural language model in understanding human intentions in a professional field.

Current generative AI systems using large language models (LLMs) face challenges including non-deterministic outputs, hallucinations, outdated information, and resource-intensive training. This disclosure introduces topic maps for constrained retrieval augmented generation to address these issues. The technique leverages existing LLMs while constraining outputs to specific, user-defined content domains. Topic maps, composed of topic names, descriptions, and relevant resource references, create a curated knowledge base that guides agent responses. This approach reduces hallucinations, improves consistency, and allows for dynamic updates without model retraining. The method involves receiving a query, identifying relevant topic maps, transmitting the query and references to an AI agent, and generating constrained responses. By providing a structured, updatable knowledge framework, this method enhances the accuracy, reliability, and adaptability of generative AI systems.

The invention relates to the technical field of financial informatization, and particularly discloses an automatic classification and input method for intelligently identifying accounting original certificates. The method comprises the following steps: extracting semantic features and context features in a voucher to form multi-dimensional feature information; inputting the multi-dimensional feature information into a business scene inference model, performing inference and constraint screening based on a pre-constructed accounting business knowledge framework, and outputting a target business scene identifier and an accounting processing rule; and automatically generating and entering an accounting entry according to the rule and the voucher value. The invention further relates to a feedback updating mechanism of the model, and self-adaptive learning is achieved by recording user correction and adjusting model parameters. And realizing hierarchical automatic processing based on a flow routing mechanism of confidence score. The method can deeply understand voucher business semantics, is adaptive to enterprise specific rules, and intelligently cooperates with manual operation, thereby improving the accuracy, efficiency and automation level of accounting voucher processing.

The invention discloses an APT attack detection method and device based on traceability graph subgraph division of mutual information approximation, equipment and a medium, and relates to the technical field of network security, and the method comprises the steps: constructing an original traceability graph comprising node attributes and edge attributes; performing representation learning by using a graph convolutional neural network model to generate a low-dimensional node embedding vector; on the basis of a conditional scoring function model, a node embedding vector is used as input, and in combination with context conditions, conditional mutual information between nodes is approximately calculated; the context condition is determined according to the edge attribute; based on the condition mutual information between the nodes, an optimization objective function model is constructed, and sub-graph division of the original traceability graph is completed; sub-graphs obtained through division are mapped to an existing attack knowledge framework to be labeled, key nodes are recognized by calculating the contribution degree of nodes to mutual information in the sub-graphs, a path formed by the key nodes is recognized as a key attack chain, and a visualization result and alarm information are generated. According to the method, the calculation efficiency, the robustness and the interpretability are improved.

The application discloses a kind of implicit knowledge explicitization method for tobacco enterprise production scheduling, comprising the following steps: step S1: extraction and pre-processing scheduling knowledge;Step S2: build implicit and explicit scheduling knowledge classification word library;Step S3: key word extraction is carried out to implicit knowledge and explicit knowledge, the similarity of key word of the two is compared using n-gram matching algorithm, if the similarity m of the two is greater than or equal to the set threshold n, then according to the explicit knowledge, construct scheduling knowledge framework, combine scheduling knowledge framework to carry out knowledge integration to implicit knowledge key word set, complete implicit knowledge explicitization;Step S4: integrate implicit and explicit scheduling knowledge;Based on explicit knowledge, directly adopt OWL language and with the aid of Protege ontology development tool, top-down scheduling ontology is built;Through ontology mapping and ontology fusion method, the semantic integration between scheduling IS semantic model and scheduling ontology is realized, and the integration of implicit and explicit scheduling knowledge is completed.

This invention provides a biological pre-learning guidance method and device based on an anchor-point retrospective intelligent agent, relating to the field of educational informatization technology. The method includes: constructing a target biological knowledge dependency graph to provide a structured knowledge framework for the entire guidance process; synchronously collecting gaze data streams and platform interaction event data streams, fusing them into a semantic viewing knowledge point sequence based on a biological video-knowledge mapping library, and then combining this with the anchor blink count through an interest-based joint evidence module for comprehensive analysis; analyzing the anchor interaction behavior sequence and the currently viewed biological knowledge sequence using a pre-set anchor-point retrospective guidance network model, and outputting a mastery scalar; and integrating the anchor state containing the intervention level as short-term memory and the historical knowledge sequence as long-term memory through a planner, driving the intelligent agent to generate the final strategic response based on the target biological knowledge dependency graph.

This invention discloses a method and system for constructing a knowledge graph. It extracts features from acquired multi-source operation and maintenance text data to generate context vector features, static word vector features, and statistical text features. These three types of features are then weighted and fused to generate a text representation. Temporal and causal ontology serve as the basis for weight adjustment; the greater the similarity between the multi-source operation and maintenance text data and this ontology, the greater the weight coefficient corresponding to the context vector feature. Temporal and causal ontology is a structured knowledge framework about temporal patterns and causal mechanisms. Based on the generated text representation, entities and entity relationships are identified, and then entity alignment and information fusion processing are used to generate the target result. Finally, a knowledge graph is constructed based on the target result. This invention, through multi-dimensional feature extraction combined with a weighted fusion strategy guided by temporal and causal ontology, achieves accurate identification of entities and entity relationships, thereby improving the accuracy of knowledge graph construction.

The application discloses an industry chain design method and device and a computer storage medium, relates to the technical field of industry chain management, and comprises the following steps: firstly, collecting multi-source industry data legally and preprocessing and storing the multi-source industry data; then, determining candidate nodes through knowledge framework construction, entity relationship extraction, score calculation and screening verification; setting a multi-task optimization target value strategy or an ideal value strategy function; training a learning model or screening potential chain nodes through multi-target optimization; then, constructing an initial knowledge graph, complementing missing correlations and optimizing the structure through a clustering algorithm; finally, constructing an evaluation system and forming a complete industry chain design process. Through the fusion of multi-source heterogeneous data processing, knowledge graph construction, reinforcement learning screening and whole life cycle analysis technology, the application solves the problems of insufficient data processing, inaccurate node screening, poor graph quality, incomplete chain and unstable generated quality in traditional industry chain design.

The application relates to the technical field of criminal conviction abnormality early warning, and particularly provides a criminal conviction abnormality early warning method based on a legal knowledge framework and a star graph neural network. The method comprises the following steps: obtaining criminal conviction abnormality data through judgment documents; obtaining normal criminal conviction data through a legal data set; constructing two types of legal knowledge frameworks, namely, crime name exclusive and cross-crime name general; constructing a structured legal element data set through a Qwen3-14B model; embedding legal elements into dense vectors through a bert-base-chinese model to construct a star graph neural network criminal conviction model; performing criminal conviction abnormality early warning based on two criminal conviction abnormality early warning mechanisms to obtain a criminal conviction abnormality early warning model; and deploying the criminal conviction abnormality early warning model to perform criminal conviction abnormality early warning testing. The method solves the problems existing in the crime name misrepresentation identification of the existing AI-assisted legal application technology, and improves the identification accuracy of crime name application errors in the judicial field.

The invention discloses an AI knowledge management software and hardware all-in-one machine, which relates to the field of knowledge management and comprises a hardware micro server and a software function module, the software function module comprises an AI intelligent question and answer module; each software function module corresponds to one or more micro-service components in the micro-service architecture based on the container; wherein the software function module adopts DevOps knowledge framework energizing research and development, and the AI intelligent question and answer module performs fine tuning acquisition on an AI model based on a private knowledge base. And a micro-service architecture is adopted to integrate software function modules, so that modular extension and high efficiency of the system are realized. Besides, the micro-service architecture is combined with a containerization technology and DevOps practice, so that efficient and flexible deployment is realized in an environment with limited resources, and the cost is effectively controlled. And finally, fine tuning is performed on the AI model in combination with the private knowledge base, and the enterprise or the organization is helped to maximally precipitate and utilize internal data, so that efficient business decision support is provided, and data privacy and security are ensured.