39 results about "Relationship mining" patented technology

The present application relates to the technical field of complex equipment component repair, in particular to a device component performance and unit body maintenance level relationship mining method capable of effectively improving the use efficiency of an aero-engine, which first carries out expansion processing of repair samples, and then selects a support vector machine regression method which is better in the condition of small sample problems to solve the mapping relationship between the component performance before repair, unit body maintenance level and component performance after repair. Since a component is generally composed of multiple unit bodies, each component has multiple maintenance levels, and the mapping relationship between the component performance before repair, unit body maintenance level and component performance after repair is a many-to-one mapping relationship. In order to improve the accuracy of support vector machine regression, a hybrid kernel function method is used to optimize it, and a particle swarm algorithm is used to optimize the related parameters.

This invention relates to the field of bioinformatics processing and discloses a method and system for mining the structure-activity relationship (SMR) of porcine neurotrophic peptides based on sequence features. The method includes constructing an original sample index table and fusing multi-source production data, extracting peptide sequence features to generate a sequence feature matrix, constructing a sequence-process joint graph containing peptide nodes and process state nodes, training a structure-activity relationship graph neural network to mine SMR relationships, and deriving a process control decision table based on a process response sample set generated by the network, thereby achieving online optimization of the porcine neurotrophic peptide preparation process. This invention solves the problem of SMR mining caused by the separation of process parameters, sequence information, and activity data, achieving accurate characterization of the synergistic effect of sequence and process and reverse optimization of process parameters, thus improving the targeted enrichment efficiency and bioactivity retention level of target neurotrophic peptides.

The application discloses a kind of based on dynamic knowledge graph's relay protection defect diagnosis method and device, belong to relay protection defect diagnosis field, the method is: real-time acquisition first data set in power system, and the first data set is standardized, generates second data set;Second data set is input to MacBERT-BiLSTM-CRF model and is extracted to entity, obtain multiple entities;According to second data set and each entity updates graph structure data, and graph structure data is input to GNN model and is mined to relationship, obtain multiple entity relations;According to each entity and each entity relation updates knowledge graph, based on knowledge graph and the real-time data of target relay protection device carries out rule reasoning, obtains first diagnostic result and is carried out probability reasoning by Bayes network, obtains second diagnostic result;Based on second diagnostic result and real-time data carries out grey correlation degree analysis, obtains consistency evaluation result, when consistency evaluation result is greater than first threshold value, generates and outputs diagnostic report.

This invention provides a semi-supervised AI prediction method and system for breast cancer based on the consistency of ranking influence. The method includes: weakly amplifying labeled samples, weakly amplifying unlabeled samples, and strongly amplifying them; inputting these three types of amplified samples into a deep model to obtain breast cancer prediction probabilities; for weakly amplified labeled samples, calculating the cross-entropy loss between the true image annotation and the predicted probability; for weakly amplified unlabeled samples, if their predicted probability in a certain category exceeds a threshold, using the predicted category label as a pseudo-label and calculating the consistency loss between it and the predicted probability of strongly amplified samples; performing relationship mining between labeled and unlabeled samples based on an influence function, dynamically selecting representative labeled samples and constructing a ranking probability distribution, and calculating the consistency loss of ranking influence; jointly optimizing the overall loss function and training the deep model; and using the trained deep model to output the AI ​​prediction result. This invention can be used for AI prediction of breast cancer.

This invention discloses an intelligent biological reaction monitoring system and method, belonging to the field of intelligent monitoring. The system includes: a reaction stage segmentation unit for segmenting and determining multiple reaction stages; a variable relationship mining unit for determining dominant and auxiliary variables, mining linear relationships between variables, coordinating insensitive loss functions, and supervising the training of a soft monitoring module; a continuous monitoring and acquisition unit for configuring monitoring equipment groups, performing continuous monitoring, and determining reaction monitoring data; a data analysis and screening unit for preprocessing data, performing linear analysis and abnormal reaction localization, and determining valid monitoring data; a game equilibrium decision-making unit for performing game equilibrium decisions on abnormal reaction identifiers and determining reaction regulation strategies; and a reaction monitoring management unit for responding to regulation strategies, performing feedback monitoring analysis and reaction monitoring management, improving the accuracy of biological reaction monitoring, achieving real-time online monitoring, and intelligently regulating abnormal situations.

The application discloses an intelligent user behavior anomaly detection method and system based on big data analysis, and relates to the technical field of big data analysis. The method comprises the following steps: establishing a dimension description graph of access system data; analyzing user access multi-dimensional features based on big data to construct an access description feature graph; performing preset shallow and deep feature analysis by using the graph to obtain a shallow and deep anomaly feature set; performing anomaly association mining on the dimension graph according to the two sets to generate a candidate anomaly association chain and verify the anomaly association chain to identify and verify anomaly features; and performing risk probability mapping according to the anomaly features to generate an anomaly detection result. The technical problem that it is difficult to effectively identify potential user behavior anomalies through the implicit association between data in the prior art, resulting in risk misreporting and low detection accuracy, is solved, the technical effect that explicit risks and potential risks are intelligently identified through multi-dimensional data relationship mining and anomaly association analysis, and the anomaly detection accuracy and risk prediction capability are improved is achieved.

The application relates to a retrieval enhanced generation technology, aiming at the problem that current mainstream RAG methods are difficult to efficiently realize keyword mining and inter-word relationship in the financial field to improve the performance of the RAG method, and a financial field RAG keyword retrieval method based on inter-word relationship mining is provided, which comprises the following steps: collecting and counting a large number of vertical field documents and common questions, calculating the term (A+B) point mutual information of two adjacent words termA and termB, and storing all possible term combinations by using a prefix tree dictionary; simultaneously calling two fine-tuning BERT models, a word importance model and an abstract model, to respectively execute the functions of keyword discovery, i.e. word importance, and inter-word relationship mining, i.e. word closeness, construct a word segmenter enhanced for financial vocabulary, and obtain candidate combined keywords; calculating the comprehensive score of the multi-word combination, verifying the feasibility of the triple combination and the binary combination, and integrating the keywords with high importance and the mined binary or triple word groups or short sentences. The application significantly enhances the new information recognition capability in the financial field.

This invention discloses a method and apparatus for context optimization of a large-scale language model in the urban rail transit vertical domain based on dynamic cognitive graph construction and compression. The method first extracts a set of cognitive atoms from the urban rail transit domain text input in each round using the urban rail transit vertical domain large-scale language model. Then, based on the cognitive graph of the previous round and combined with the cognitive atom set of the current round, it completes node updates, relationship mining, and node cognitive activation strength calculation to obtain the current round's cognitive graph. Next, it calculates the cognitive saliency of each node, dynamically compresses the cognitive graph to obtain a compressed subgraph, compresses it into graph-aware prompt text containing node content and semantic relationships, and inputs it into the urban rail transit large-scale language model to generate a response. Finally, it extracts new cognitive atoms from the response to generate a supplementary atom set, analyzes the dependence of the response on nodes, and updates the model's attention. Both the supplementary atom set and the updated model attention provide support for the next round of cognitive graph updates. This invention solves the problems of invalid token accumulation and the inability of static context to dynamically focus and evolve in existing technologies.

The application discloses a kind of comprehensive energy load aggregate short-term probability prediction model establishing method and device.The method includes: the historical data of comprehensive energy load aggregate collected is preprocessed and dimensionality reduction;Grouping is carried out to the data after dimensionality reduction using affinity propagation clustering algorithm based on comprehensive similarity, and the centroid feature of each group is extracted as representative load feature input prediction model;The short-term probability prediction model of comprehensive energy load aggregate that fusion Copula self-adapting correlation analysis, cross feature-time graph neural network and mixed density network is constructed.The precision of short-term probability prediction of comprehensive energy load aggregate is effectively improved by dynamic coupling relationship mining and spatiotemporal feature joint learning mechanism.

This application relates to the field of commercial data processing, providing a method and corresponding products for enterprise data identification in industry graphs. The method includes: asynchronously collecting multi-source, heterogeneous raw enterprise data from the internet and big data resource services, generating a standardized enterprise data set, and storing it in a cloud database; generating a basic entity set based on a pre-built industry knowledge ontology model, and labeling each entity with structured attribute information; analyzing the basic entity set using an enterprise relationship mining model to mine direct and implicit relationships between entities; fusing, deduplicating, and weighting the mined direct and implicit relationships, and dynamically constructing and updating an industry knowledge graph with entities as nodes and weighted relationships as edges; and responding to query requests for a target industry by intelligently retrieving and performing multi-dimensional analysis of the industry knowledge graph, outputting enterprise identification results that meet the criteria.

The application discloses an anesthesia hypotension prediction method and system based on FMD data mining of a grey system, and belongs to the field of electric digital data processing. The application carries out preprocessing, interval grey number conversion and dimension standardization processing on brachial artery blood flow mediated vasodilation function data and clinical baseline data, generates a standardized interval grey number feature set, completes feature screening and coupling relationship mining through grey nonlinear correlation analysis, completes risk simulation calculation through a non-equidistant metabolism GM(1, N) power model, and divides and outputs a hypotension risk level after anesthesia induction relying on grey clustering evaluation. The system is electrically connected by multiple functional modules in sequence, and can realize missing data completion, model precision verification and feature contribution output. The application is suitable for a poor information small sample scene, reduces the interference of data uncertainty and dimension difference, improves the reliability and interpretability of risk prediction, and provides evaluation support for perioperative hemodynamic management.

This invention discloses a sensitive data identification method based on graph retrieval enhancement, belonging to the fields of data security and artificial intelligence. The main steps of this method are: collecting sensitive data identification rules and specifications, and obtaining structured rule data through preprocessing; constructing a sensitive data identification rule knowledge graph, forming a structured association network through entity extraction and relationship mining; mining the core entity association information of the samples to be identified, and enhancing the context by combining vector retrieval and graph feature filtering; combining sensitive rules and historical cases, injecting them into a large model for classification to obtain whether it is sensitive, the sensitive type, and the judgment criteria; integrating the output results of the large model, and visually presenting the logic and graph of sensitive data determination; and manually updating the graph and the large model through closed-loop feedback. This invention combines knowledge graphs and retrieval enhancement generation capabilities to identify implicit sensitive information, and the basis for the judgment results is traceable, making it suitable for assisting in the security management of sensitive data in multiple fields.

This invention discloses a product service entity association mining method based on spectrum decoupling, belonging to the field of product service modeling and relationship mining. The method includes: First, collecting multiple product services and constructing a historical call matrix and a product service set; second, encoding the functional text and categories in the product service metadata, calculating the similarity between product services, and forming product service pairs based on the similarity scores to construct a modal feature isomorphism graph; next, further calculating a collaborative feature isomorphism graph by combining the adjusted historical call matrix, and extracting low-frequency and mid-frequency representations of the "ugly skin" (a term referring to a specific product or service) using low-pass and mid-pass frequency domain filters, further fusing features using a pairwise attention mechanism to obtain a low-dimensional representation; finally, updating parameters through a loss function and generating a product service feature retrieval table. This invention can effectively improve the accuracy and conversion rate of product service recommendations.

This invention proposes a system for the operation and maintenance management of secondary equipment in distribution networks. The system includes an equipment access layer, a data fusion layer, a knowledge graph layer, an intelligent analysis layer, and a visualization interaction layer. The equipment access layer includes a unified data access gateway and a primary-secondary relationship mining engine connected to the unified data access gateway. The knowledge graph layer includes a knowledge graph of power grid topology and equipment associations, and a graph query and reasoning engine. The intelligent analysis layer includes an equipment health evaluation model, an operation and maintenance knowledge base, a case reasoning engine, and a fault impact range analysis module. The visualization interaction layer includes an operation and maintenance situation awareness dashboard, which is connected to the equipment health evaluation model and the fault impact range analysis module. This invention enables distribution network operation and maintenance management to shift from passive response, experience-based reliance, and professional segmentation to proactive prevention, data-driven, and collaborative integration, effectively supporting the improvement of distribution automation levels and the enhancement of power supply reliability.

This invention discloses a knowledge graph-based method for mining and risk warning of relationships among construction enterprises, belonging to the field of enterprise relationship analysis and risk warning technology. The method includes the following steps: S1, collecting enterprise business registration, bidding, contract, performance, judicial, and penalty data to form knowledge graph clues; S2, determining co-occurrence relationships within the same record based on the knowledge graph clues, forming a pre- and post-record segment; S3, determining the subject identifier based on the pre- and post-record segments, and forming an association chain; S4, receiving new records and forming a change chain; S5, extracting aggregation clues, diffusion clues, and recurring clues based on the change chain, determining the risk outcome, and updating subsequent knowledge graph clues. This invention, through the setting of pending grouping, change chain, state conflict position, backtracking position, and splitting position, enables new records to perform merge updates, independent retention, or split updates on the relationship paths in the knowledge graph.

The new energy ship fault causal relationship construction method provided in the application comprises the following steps: when a fault occurs, multi-modal heterogeneous data is fused and a core feature set is obtained through screening; an environment-invariant feature matrix is obtained through invariant risk minimization learning; the causal edge strength between each variable feature is evaluated based on mutual information to obtain a causal edge strength matrix; a core fault causal skeleton is mined by combining the causal edge strength threshold and conditional independence test; based on the skeleton and the hierarchical node system, an initial hierarchical fault causal graph is constructed, the initial causal edge weight is determined by fusing the causal edge strength matrix, and the target hierarchical fault causal graph is obtained by dynamically updating the meta-learning model; after the target hierarchical fault causal graph is corrected and optimized by counterfactual samples, the reasoning path is optimized, then the implicit causal relationship is mined by combining the structured reasoning and the large language model, and the fault causal relationship of the new energy ship is obtained. Thus, stable and self-adaptive fault causal relationship mining is realized under complex dynamic working conditions.

This application discloses a method, apparatus, device, and medium for mining and dynamically monitoring website association relationships based on network identifiers, relating to the field of computer technology. The method includes: acquiring webpage information from several web pages and updating a target website association graph based on the identifier information and website domain names contained therein; if a target monitoring task corresponding to a target identifier is received from a browser client, the newly acquired webpage information is matched with the target identifier; if the match is successful, the newly acquired webpage information is determined to be a false alarm based on the historical and current list of associated websites corresponding to the target identifier, determined through the target website association graph; if it is not a false alarm, an association website intelligence event is generated and pushed to the browser client. Thus, associated websites corresponding to identifiers can be identified, and the number of websites corresponding to identifiers can be monitored in real time through intelligence event pushes.

This invention relates to the field of advertising technology, and discloses a method, system, terminal, and storage medium for generating narrative advertising videos. The method includes: acquiring the target user's native interaction data and performing cross-modal semantic fusion to obtain a user cognitive profile; using classic narrative texts, commercial advertising scripts, and multimodal materials as basic data, employing deep semantic analysis and relationship mining as construction methods, using user behavior feedback streams and external cultural semantic streams as evolutionary basis, and using incremental associative learning as an evolutionary mechanism to obtain a narrative knowledge graph; driving the narrative knowledge graph to deduce the plot, obtaining a preliminary narrative script; using brand tone constraints and key information points as optimization targets to strengthen plot anchors, obtaining a branded narrative script; performing multimodal consistency arrangement of narrative nodes and emotional logic relationships to obtain an executable narrative blueprint; and automatically rendering materials to obtain a narrative advertising video. This invention can improve the generation efficiency of narrative advertising videos.

This invention relates to the field of dynamic prediction technology, specifically to a dynamic prediction method for slope stability based on heterogeneous Transformer integration and grey clustering association. This invention solves the technical problems of single-model feature expression, gradient vanishing in traditional recurrent networks, and insufficient capture of long-range dependence and causal relationship of slope parameters by integrating the global coupling feature capture capability of BERT, the causal relationship mining capability of GPT2, and the basic nonlinear fitting capability of MLP.

This invention discloses an online method and apparatus for estimating the weighted reachability of vertex pairs in a temporal interaction graph based on edge similarity decay. By introducing a time decay factor and an edge feature similarity modeling mechanism, a continuous calculation method for reachability strength is established, and an incremental propagation strategy is combined to achieve online updates. Simultaneously, under memory-constrained conditions, a collaborative mechanism of sliding window, Top-tracking, and minimum-count sketching is employed to prioritize the retention of highly reachable states and compress the estimation of long-tailed states, thus forming a unified weighted reachability query method supporting both exact and approximate modes. This invention significantly reduces storage overhead and query latency while ensuring estimation accuracy, possesses good scalability and high throughput adaptability, and can be widely applied to scenarios such as network security monitoring, risk propagation analysis, abnormal behavior identification, and complex interaction relationship mining.

The present application belongs to the technical field of e-commerce user behavior prediction, and particularly relates to a purchase behavior linkage prediction method and system based on e-commerce user social relationship mining. The method acquires user social data, user purchase data and commodity metadata information, constructs a user social network into a weighted directed graph structure, and calculates the influence parameter of each user node. Then, the purchase behavior trajectory vector is constructed according to the purchase data, the user is clustered and divided, and the linkage factor is determined according to the purchase time difference, the commodity price interval and the purchase frequency. Further, the linkage prediction model is constructed by combining the social influence, the linkage factor and the user consumption characteristics, the probability of the target user occurring the same purchase behavior after being influenced by the social circle is output, the fitting deviation of the prediction result is evaluated, and the model parameters are updated based on the feedback data. The scheme can improve the recognition and prediction accuracy of the social driving purchase behavior.

The application belongs to the field of information technology and intelligent recommendation technology, and particularly relates to a knowledge recommendation method and system based on content semantics and graph relationship double-path retrieval, which can deeply integrate the retrieval and recommendation method of semantic content understanding and graph structure association, ensure high retrieval accuracy, return systematized and associated knowledge results, and provide natural and convenient intelligent interaction experience, so as to truly release the application potential of the building field knowledge graph, and organically integrate deep semantic understanding and graph relationship mining through the double-path retrieval collaborative mechanism. The application not only utilizes the high accuracy of semantic vector retrieval in content correlation, but also introduces rich context association knowledge through graph path retrieval, so as to maintain high precision while significantly improving the systematization and correlation of the results, overcome the defects of the single retrieval mode, and provide a more comprehensive and systematic knowledge view for users.

The application discloses a kind of segmentation assisted radar multi-frame target detection methods, applied to radar target detection and deep learning technical field, for the global feature extraction capability insufficient, adjacent target distinguishing ability insufficient, segmentation and detection task mutual relationship is not sufficient for the problem of mining;The application first obtains range-azimuth two-dimensional data according to simulated and measured radar original echo data, establishes data set, and trains multi-frame target detection network MFDet according to the established data set, then utilizes the trained target detection network and outputs multi-frame detection results in parallel;The application uses region-level detection head, effectively solves the problem that pure semantic segmentation task cannot distinguish adjacent targets;By exploring the mutual relationship between semantic segmentation and target detection, the confidence of the segmentation result is used to assist the fine boundary box, effectively reducing the false alarm rate of target detection, and improving the target detection performance in clutter interference and adjacent target scene.

The application discloses a multi-modal-based video structured label construction method and device and medium, and relates to the technical field of computer vision and artificial intelligence. The method comprises the following steps: acquiring a visual frame sequence, an audio stream and text information in a video to be labeled, and extracting features of the visual frame sequence, the audio stream and the text information to obtain multi-modal video features; performing cross-modal time sequence alignment on the multi-modal video features to obtain standard multi-modal video features, and performing deep semantic fusion on the standard multi-modal video features to generate a unified joint semantic representation; constructing a structured label knowledge graph with hierarchical semantic relationships by using unsupervised clustering and relationship mining, and matching the joint semantic representation corresponding to the video to be labeled with the structured label knowledge graph to output a pathized label set reflecting semantic levels. The application significantly improves the label construction accuracy by cross-modal time sequence alignment, deep semantic fusion and construction of a label knowledge graph.

This application relates to a data governance method, apparatus, computer equipment, storage medium, and computer program product. The method relates to the field of big data and cloud technology, and includes: parsing the table creation statements of the business data table to be governed to obtain various data table information contained in the business data table; then, treating the business data table to be governed as an entity, performing database table relationship mining based on the data table information to obtain data table relationships; subsequently, based on the partitioned business data tables and data table relationships, performing business theme merging processing on each partitioned business data table to obtain business data tables under each business theme, providing data support for business theme merging through business data relationships; and finally, performing data normalization governance on the business data tables under each business theme to obtain data governance results, thereby realizing metadata governance and normalization processing between different business modules.

This invention provides a method, apparatus, device, and medium for mining knowledge point relationships. The method includes: acquiring a dataset of exercises; acquiring all knowledge point labels in the dataset and establishing a mapping dictionary between knowledge point labels and corresponding indices; slicing the standardized text in the data using a preset sliding window and a preset sliding step size to obtain a text sequence consisting of at least one slice; predicting the knowledge point label and confidence level corresponding to each slice; determining the weight of each position in a global matrix based on the knowledge point labels and confidence levels of each slice text for each data point, combined with the positions of any two knowledge point labels in the sequence; solving for the weight value corresponding to each data point in the dataset, and accumulating the weight values ​​at the same position in the global matrix to obtain a multi-order relationship matrix reflecting the association patterns of knowledge points in the dataset. This invention solves the technical problems of coarse granularity and insufficient accuracy in existing knowledge point relationship mining results.

This invention discloses a method and system for predicting multi-source signal coupling in hydropower systems, comprising: performing a signal component decomposition process and obtaining different intrinsic mode components; constructing a multi-source cross-coupling prediction task and predicting related coupling characteristics; constructing a multi-source cross-mixed basis model and obtaining related prediction results; constructing a residual correction model and obtaining coupling prediction results; performing a mutual information analysis process and a transfer entropy calculation process, and quantifying and analyzing the correlation strength and dynamic transfer relationship. This invention solves the problems of low prediction accuracy and poor signal coupling relationship mining in traditional single-model systems, achieving high-precision coupling prediction and intrinsic correlation analysis of hydropower signals, providing reliable technical support for the condition monitoring of hydropower station equipment.

The present application relates to a kind of rehabilitation training data explainable evaluation method based on double passage causal framework, belong to medical health informatics and medical artificial intelligence technical field.The method obtains patient-related training data, reference task data and historical evaluation label, constructs three-domain nine-item structured feature, generates training stage evaluation result, rule path and double passage mechanism profile by teacher model training, rule tree distillation and causal relationship mining, and further outputs training suggestion information, for patient-related rehabilitation training data The structured processing of training stage evaluation and training management support.