83 results about "Information mining" patented technology

The invention discloses a multi-modal data retrieval method and device, a storage medium and computer equipment. The method comprises the following steps: collecting multi-modal original data; on the basis of description information of metadata of original data, all metadata belonging to the same associated items and logic relations among all the metadata are obtained, a metadata chain is constructed, a distributed graph database is constructed on the basis of the metadata chain, the metadata chain is expressed in the distributed graph database in the form of a graph, the graph comprises nodes and edges, the nodes represent the metadata, and the edges represent the metadata. The edge represents a logical relationship between the metadata; and when a data retrieval instruction is received, traversing each node in the metadata chain along the logical relationship of the metadata chain in the distributed graph database, obtaining a target node matched with a data retrieval requirement corresponding to the data retrieval instruction, and returning original data corresponding to metadata represented by the target node. Multi-modal data dynamic association retrieval can be realized, and cross-modal information mining efficiency and accuracy are improved.

The invention relates to the technical field of data processing, and discloses a gait rehabilitation evaluation method and system based on spatial-temporal characteristics of multi-modal data, a terminal and a storage medium, and the method comprises the steps: synchronously collecting myoelectricity, electroencephalogram and exoskeleton robot IMU signals of a dyskinesia crowd in a certain motion normal form in a specific period interval; a motion function scoring result of a doctor on a patient according to a scale is synchronously recorded, data preprocessing, channel selection and feature extraction are performed on myoelectricity, electroencephalogram and exoskeleton robot IMU signals, a model is established based on a neural network, motion evaluation is performed according to a fused feature array, and a motion function quantitative score is obtained; and the motion function state of the evaluated person is graded according to the score. According to the method, the multi-modal synchronous data rehabilitation evaluation model of the movement function of the dyskinesia crowd is constructed according to multiple information mining, and the movement function state of the evaluated person is rapidly evaluated, predicted and graded.

The invention relates to a GIS (Gas Insulated Switchgear) equipment mechanical defect diagnosis method based on a Gramb angle field and a dual-channel PCNN-Attention neural network, and belongs to the technical field of gas insulated switchgear mechanical vibration defect diagnosis. The method solves the problems that traditional diagnosis depends on artificial feature extraction, so that subjectivity is high, information mining is insufficient, and defect severity evaluation is missing. According to the technical scheme, the method comprises the steps that a one-dimensional vibration signal is converted into a GASF two-dimensional image and a GADF two-dimensional image through a GASF field so as to completely reserve time sequence topological features; carrying out data enhancement by adopting an image geometric transformation technology so as to improve the generalization ability of the model; and a dual-channel PCNN-Attention model is constructed, and synchronous intelligent identification of defect types and severity is realized through parallel feature extraction and dynamic weight optimization of an attention mechanism. According to the method, the diagnosis accuracy, reliability and adaptive capacity are improved, and support is provided for equipment state operation and maintenance.

The invention discloses an innovative resource collaborative matching method and system oriented to distributed operation, and relates to the field of data processing recommendation, and the method comprises the steps: carrying out the standardization processing of a heterogeneous resource portrait description text through a large language model, constructing and forming a resource attribute knowledge graph, generating extension description information of the resources in the target industrial chain through the large language model, and constructing and forming an industrial chain knowledge graph; performing semantic alignment and hidden associated information mining on the fused graph by using a pre-trained SACN model, and constructing a resource collaborative knowledge graph representing resource attributes and collaborative logic in an industrial chain; and performing semantic fusion on the original description text representation of the resource and the resource collaborative knowledge graph representation based on a large language model, generating comprehensive vector representation through multi-modal fusion, and outputting a resource matching recommendation result by adopting a collaborative filtering recommendation model. According to the method, the cross-organization and cross-industry-chain innovative resource collaborative knowledge graph is constructed, instant and clear demands of users are accurately responded, and the resource allocation efficiency is improved.

The invention provides a hotspot technology mining method and system based on scientific and technological literature data, and relates to the technical field of scientific and technological information mining, and the method comprises the steps: firstly obtaining a scientific and technological literature data set containing papers and patent literatures, and constructing a current technical element network through technical phrase extraction and semantic normalization processing; dividing the technical element network segment into a time-serialized technical element network segment set according to time slices, calculating nodes and edge time sequence importance indexes to judge an emerging technical cluster, carrying out dynamic graph representation learning and future associated edge prediction on the set, generating a potential technical combination prediction set, and evaluating the potential technical combination prediction set; and finally, generating an emerging technology theme list and a technology fusion direction list in combination with an emerging technology cluster node growth trend and a prediction association edge evaluation result, thereby improving the accuracy, comprehensiveness and foresight of hotspot technology mining.

The invention provides a multi-view space transcriptomics clustering method based on sharing-specific information mining. The technical problems that in an existing space domain recognition method, robustness of a single view is insufficient, multi-view information fusion is insufficient, and description of data statistical characteristics is not accurate are solved. According to the technical scheme, the method comprises the following steps: S1, acquiring and preprocessing original data of a spatial transcriptome; s2, constructing a sharing-specific decomposition coding network; s3, using a ZINB expression decoder, a structure decoder and a Student's t distribution clustering module to construct a multi-task loss function; and S4, outputting a spatial domain division result based on the trained network. According to the method, the spatial domain recognition precision and robustness are remarkably superior to those of an existing method, the data statistical characteristics and biological significance can be accurately described, stable support is provided for tissue function analysis and tumor microenvironment research, and the analysis quality and application value of spatial transcriptomics data are effectively improved.

This invention discloses a method for mining alumni information based on a large-scale model, comprising the following steps: 1) acquiring raw alumni-related data; 2) preprocessing the acquired data; 3) performing natural language processing on the acquired data; 4) semantic parsing and information extraction using a large-scale model; 5) constructing a knowledge graph; storing the extracted alumni information and relationships in a graph database; and constructing a visualized alumni knowledge graph; 6) updating the knowledge graph data; and 7) providing intelligent retrieval and question-answering services for alumni information based on the knowledge graph data. This invention uses a large-scale model to perform deep semantic understanding and information extraction from unstructured text. Compared to traditional keyword-based or small-scale model-based methods, it can more accurately identify alumni identities, professional experiences, and social relationships, while reducing the false matching rate.

The application provides an atoll vegetation index prediction method, which can be applied to the technical fields of geographic information and deep learning. The method comprises the following steps: obtaining monthly normalized vegetation index data of a target atoll, corresponding marine environment data and meteorological data, and constructing a vegetation growth dataset; calculating the partial correlation of the marine environment data, the meteorological data and the normalized vegetation index change, so as to determine the key environmental data affecting the normalized vegetation index change; determining the lag response period of the normalized vegetation index to each key marine environment data; based on the lag response period, combining attention mechanism and double-time-scale information mining, constructing a double-time-phase convolution long short-term memory neural network model considering the climate time lag effect of the atoll, wherein the neural network model cell structure comprises convolution operation; training the model by using the vegetation growth dataset to obtain a trained model; and predicting the future short-term atoll vegetation normalized vegetation index change by using the trained model.

The invention discloses an unsupervised domain adaptation method for a remote sensing time sequence with phonological feature alignment, which mainly solves the problem of poor generalization performance caused by difficulty in coping with time migration and distribution migration in a cross-domain task due to neglect of phonological information in time sequence data in the prior art. According to the scheme, the method comprises the following steps: constructing a self-adaptive phenological segmentation module based on time constraint, extracting a representative phenological stage from a satellite image time sequence, and accurately capturing key time sequence characteristics of a crop growth cycle; a comparison learning module based on phenological difference is introduced, stage-level positive and negative sample pairs are established, double loss optimization is carried out, and fine alignment of cross-regional phenological features is realized. Through phenological information mining and stage-level comparison and alignment, the precision and robustness of cross-regional crop semantic segmentation under an unsupervised condition are significantly improved, and the generalization ability of a remote sensing deep learning model in an unknown target region is effectively improved.

The invention discloses a consumer complaint information mining method, device and equipment based on a large language model, and relates to the field of product defect risk assessment and recall management. Constructing a standardized product security data set according to the multi-modal data, and performing semantic recognition and labeling on multi-modal complaint information in the data set to obtain a structured product security event information flow; in response to expiration of a preset update period, analyzing the product security event information stream and the current latest product security dynamic knowledge graph to obtain a product security event; the current latest product security dynamic knowledge graph is generated by fusing newly added product security event information flow on the basis of a historical knowledge graph; and carrying out situation awareness, risk early warning and defect correlation analysis on the product security event to finally obtain a product defect assessment result. The result is fed back to the current latest product safety dynamic knowledge graph to be optimized and updated; according to the method, semantic recognition and understanding capability can be realized, and dynamic association analysis capability is improved.

The application discloses a kind of digital archives intelligent information mining method, it is related to file information processing technical field, the present application is evaluated data quality by a series of quantitative indicators including consistency index, integrity index, importance index and comprehensive importance index, which effectively reduces subjective judgment when manual screening, make data screening process more objective, reliable and scientific, simultaneously, by combining quantitative indicators with comprehensive weight, to automatically generate weighted threshold based on data-driven, the application of this weighted threshold not only can quickly process large-scale data set, to reduce the demand for a large number of manual annotation of manpower, and can effectively filter out high-quality data set, and be applied to subsequent deep learning model training, to significantly improve the output accuracy and stability of model, ensure that more accurate prediction results can be obtained, and based on this more accurate prediction results, more scientific and reasonable business decisions can be made.

The application discloses a market supervision internet information monitoring and analysis system, which comprises a CNN model construction module, an internet information collection module, an information preprocessing module and an information mining module; the application uses a CNN model algorithm to model sample data marked by artificial marking, and uses a model to determine illegal behaviors; through continuously accumulating sample data, repeatedly training and achieving the purpose of machine learning, the determination accuracy is gradually improved.

The invention relates to the technical field of intelligent monitoring, and discloses a system operation state monitoring method based on multi-source information mining and organic fusion, which comprises the following steps: acquiring internal operation state data and external operation state data, calibrating the internal operation state data and the external operation state data by using a sensor calibration algorithm based on artificial intelligence; the method comprises the following steps: extracting internal operation state data and external operation state data, performing organic fusion to form a comprehensive data set, performing correlation analysis on the comprehensive data set, mining a correlation relationship between the internal operation state data and the external operation state data, and deriving key variables influencing the operation state of a monitoring target system; and comparing the real-time data of the key variables with a preset normal operation range to obtain a comparison result, evaluating the current operation state of the monitoring target system based on the comparison result, obtaining an evaluation result, and when the evaluation result exceeds a preset standard value, triggering an early warning mechanism to prompt a user to take corresponding measures. According to the invention, the monitoring precision of the monitoring target can be improved.

The invention belongs to the technical field of alloy fatigue life prediction, and discloses an alloy fatigue life prediction method fused with an information mining technology, which comprises the following steps: introducing key physical quantities into a feature set by combining a fatigue theory; mining inherent information in the data by adopting a symbolic regression algorithm driven by genetic programming, and adding the inherent information into a feature set as derivative features so as to construct a fatigue life prediction model of the alloy; a prediction model without derivative features is constructed for performance comparison, so that the improvement effect of fusion information mining technology aided modeling on prediction precision is evaluated; derivative feature expansion is applied to fatigue life prediction of a multi-component alloy system, and the universality of mined information is verified. According to the method, the information mining technology is adopted, hidden information in the data is extracted to assist modeling, and compared with a traditional machine learning method, more universal and high-precision fatigue life prediction is achieved, so that more reliable prediction support is provided for risk assessment of structural components.

The present disclosure provides a method and device for information mining, electronic equipment and storage medium, relates to the technical field of data processing, and particularly relates to the technical field of big data. The specific implementation scheme is as follows: obtaining user basic information and behavior related information of each user from log information; generating a graph database based on the user basic information and the behavior related information, the graph database comprising a plurality of nodes and connection relationships between the nodes, the plurality of nodes comprising a to-be-reviewed node and an abnormal node; dividing the nodes included in the graph database into a plurality of communities based on a community discovery algorithm; and for each to-be-reviewed node in the graph database, if the closeness of the to-be-reviewed node to abnormal nodes in the community to which the to-be-reviewed node belongs is greater than a preset threshold, determining that the to-be-reviewed node is an abnormal node. In this way, potential abnormal users can be identified.

The present disclosure provides an advertisement business information mining method and device, an electronic device and a storage medium, and relates to the technical field of artificial intelligence, specifically to the technical field of data mining, and can be applied to scenarios such as advertisement business information mining. The specific implementation scheme is: at least one first candidate business point matched with the semantics of the target description content is selected from a business point set, and the business points in the business point set represent the business scope of the advertisement; attribute comparison results of each first candidate business point and the attribute information of the corresponding target description content are obtained; and according to the attribute comparison results corresponding to each first candidate business point, a target business point set is determined from the at least one first candidate business point. The above method can automatically determine the actual business point of the advertisement from the business point set based on the description content of the advertisement, and can reduce the labor cost and time cost consumed for business mining of the advertisement.

The invention provides a passive sonar target space-time frequency feature intelligent mining and fusion identification method, which comprises the following steps: firstly, designing a data preprocessing method, and generating a space domain sample, a time domain sample and a frequency domain sample through space-time frequency feature analysis; secondly, constructing a spatial domain feature extraction module, a frequency domain feature extraction module and a time domain feature extraction module which are parallel, constructing a serial cross-domain dynamic attention fusion module and a feature secondary fusion and classifier module on the basis, and combining to form a complete space-time-frequency feature mining and fusion recognition network model; designing a loss function and configuring an optimizer, and completing space-time frequency feature mining and fusion identification network model training based on the labeled sample; and finally, processing the unknown target space-time frequency data based on the designed preprocessing method and the well-trained space-time frequency feature mining and fusion recognition network model to obtain a target classification recognition result. Compared with an existing passive sonar target classification and recognition method, the method provided by the invention is richer in target useful feature information mining, deeper in fusion and utilization, and higher in classification and recognition confidence.

This invention discloses a method and device for optimizing prostate MRI images for clinical surgery, belonging to the field of prostate MRI image processing technology. The optimization method includes: retrieving an initial MRI image; retrieving a trained data fitting network; and adjusting the initial MRI image using the data fitting network to generate an optimized, improved MRI image. The data fitting network includes an information mining module and an enhancement residual module. The information mining module is used to mine image features from the initial MRI image, and the enhancement residual module processes the feature map preceding the information mining module to generate a residual feature map. Then, the residual feature map is used to register the feature map following the information mining module. This invention uses the enhancement residual module to perform dual-domain constrained enhancement adjustment on the preceding feature data to generate a residual feature map, which can greatly enhance the network's targeted optimization effect on the target region and avoid the distortion of image detail information.

The application provides a multi-source context-aware information mining method and system, wherein the method comprises the following steps: acquiring a technical point input by a user, constructing multi-source context information including a same-industry subject patent map according to the technical point, performing entity linking on the multi-source context information to obtain preprocessed information; extracting a user intention vector based on the technical point, extracting a feature vector based on the preprocessed information, taking the user intention vector as a query and taking the feature vector as storage information, adjusting an attention weight to obtain a fusion vector; generating a candidate research direction corresponding to each technical subclass area according to a self-defined area type based on the same-industry subject patent map in the preprocessed information, performing feasibility filtering on the candidate research direction to obtain a mining result, and evaluating the mining result; and arranging the mining result to form a structured output, wherein a suggestion classification number in the structured output is predicted by a classifier adopting hierarchical consistency judgment based on the fusion vector.

The invention belongs to the technical field of data processing, and particularly relates to an open source data information mining method and system. The open source data information mining method comprises the steps that multi-modal data of an open source scene are obtained, and the multi-modal data comprise texts, images and time sequence data; performing association confidence coefficient cleaning processing on the data of the open source scene to obtain multi-modal cleaning data; extracting each modal feature from the multi-modal cleaning data, and combining and embedding spatial mapping to obtain a multi-modal semantic vector; according to an attention weight mechanism, performing dynamic feature fusion on the multi-modal semantic vector to obtain a multi-modal fusion feature; and filtering conflict modal information in the multi-modal fusion features, and storing complementary modal information to obtain open source data information mining data.

The application provides a micro-map personalized layout information mining method, relates to the related professional knowledge of image processing and cartography, and solves the problem of difficult mapping caused by the lack of professional map knowledge of ordinary people; the method comprises the following steps: obtaining the combination characteristics and position characteristics of map layout elements, obtaining the relationship characteristic information between the layout elements, and constructing a micro-map layout knowledge base; the map component personalized layout information mining method can effectively obtain the distribution characteristics of the map components in the map, provide help for the ordinary people who lack mapping basis, and improve the map production efficiency and map quality.

The application discloses a multi-language common attention topic detection method based on mT5 and word frequency information entropy, and belongs to the technical field of social media information mining.The method adopts a statistical method of multi-language word frequency information entropy, fully considers the feature that a common attention topic is evenly distributed in multiple languages, and realizes extraction of theme words commonly attended by different cultures; synonymous words are aggregated by using mBERT, redundancy of output words is reduced by realizing identification of redundant words in the process of constructing a word table; by improving a theme word extraction algorithm in BERTopic, a single document is subjected to theme word extraction by using a fine-tuned mT5, and the method is improved from a traditional single-language topic detection to a multi-language mode, so that the problem of missing potential value theme words is avoided to a certain extent.The application is suitable for the technical field of social media information mining, improves the detection and recognition capability of common attention topics, and improves the output quality of theme words.

The invention belongs to the technical field of environmental monitoring, and particularly relates to a seasonal river water ecological risk early warning method based on environmental monitoring instrument data. Comprising the following steps: step 1, arranging an ultraviolet visible spectrum probe on a monitoring section of a target seasonal river to form a spectrum feature vector of each monitoring section; 2, constructing a maximum entropy habitat model by taking the spectral feature vector as an environment variable to obtain an aquatic organism suitability field; and step 3, dividing hydrological seasons according to the hydrological characteristics of the target seasonal river, setting an ecological risk level judgment threshold for different hydrological seasons, determining an ecological risk level, and generating and pushing early warning information when the ecological risk level reaches a preset trigger level. According to the invention, deep information mining of spectral data, quantitative characterization of an upstream and downstream pollution transmission relationship and differential response of seasonal hydrological characteristics are realized, and the accuracy, timeliness and interpretability of seasonal river water ecological risk early warning are improved.

The invention relates to the technical field of network security detection, in particular to a JS vulnerability detection and sensitive information mining method and system for an intranet scene. The method comprises the following steps: in a resource collection stage, dynamically rendering a page based on an extensible crawler framework and extracting JS resources; in the analysis stage, the JS resources are analyzed in a double-engine mode of AST static analysis and sandbox dynamic execution; in the detection stage, vulnerability verification and sensitive data identification are carried out based on the multi-dimensional joint judgment model. According to the method, the three-layer architecture of hierarchical analysis, dynamic verification and intelligent mining is adopted, the limitation of a traditional tool in the aspects of dynamic content capture, code semantic analysis and intranet adaptability can be broken through, the coverage rate and accuracy rate of intranet JS vulnerability detection are remarkably increased, and more reliable guarantee is provided for enterprise intranet security.

The application discloses a kind of key information mining multi-modal enterprise knowledge graph completion method and device, comprising: embedding representation is carried out to the enterprise knowledge graph created in advance using graph attention network GATs, to obtain enterprise knowledge graph feature embedding;Extract the key object information contained in public opinion image to obtain visual feature embedding;Text embedding model is used to carry out embedding representation to public opinion text, to obtain text feature embedding;Fusion enterprise knowledge graph embedding feature, visual embedding feature and text embedding feature, to obtain multi-modal fusion embedding feature;For any two candidate entities, based on the corresponding multi-modal fusion embedding feature, key information mining is carried out to determine the contact between two candidate entities;Based on the contact between the two candidate entities determined, the enterprise knowledge graph is completed.The application can complete multi-modal knowledge graph, can more comprehensively and timely grasp enterprise information, improve the accuracy of information analysis and mining.

The present application relates to the technical field of signal processing, and particularly relates to a photoelectric plethysmogram signal quality evaluation method and device, computer equipment and storage medium, template construction is carried out based on the photoelectric plethysmogram signals of multiple wavelengths of a user to be detected, and a photoelectric plethysmogram template signal is obtained; signal division and quality detection index extraction are carried out by using the photoelectric plethysmogram template signal, multi-level information mining is carried out on the photoelectric plethysmogram signal, more sufficient and rich feature information is obtained, more comprehensive and sufficient signal quality evaluation is realized, the extracted quality detection index is used to extract target signal extraction results from the photoelectric plethysmogram signals of multiple wavelengths, the accuracy of photoelectric plethysmogram signal extraction is improved, and comprehensive and sufficient quality control is effectively carried out on the photoelectric plethysmogram signal.

The application is suitable for the technical field of information mining, and provides a false comment detection method based on federated learning, comprising: obtaining a false comment detection model through a federated learning system; using the false comment detection model to perform false detection on text comment data to be detected; a first round of federated learning process of the federated learning system is: respectively for each client participating in federated learning, obtaining an importance vector of the client; based on the importance vectors of all clients participating in federated learning, dividing model parameters into key layer parameters and non-key layer parameters; based on the key layer parameters of all clients participating in federated learning, determining from all clients participating in federated learning a client for global aggregation; performing global aggregation on the key layer parameters and the non-key layer parameters of the client, to obtain model parameters of the first round of federated learning. The application can improve the accuracy of cross-platform false comment detection.

The application relates to the technical field of image processing, in particular to a video super-resolution reconstruction system and method based on space-time cooperative enhancement, wherein a feature and an optical flow extraction unit extracts initial features from two adjacent low-resolution videos respectively, extracts forward and backward optical flows in time sequence synchronously, and generates two groups of optical flow features based on optical flow transformation; an intermediate frame generation unit sends the two groups of initial features into a Mamba module to complete intermediate frame modeling, fuses the modeling features and the optical flow features, and obtains intermediate frame features; an information mining and aggregation unit integrates three adjacent frame features to complete sorting fusion, performs attention operation on the sorted features, generates reconstruction features after superimposing weights, and finally decodes and restores the three frames of high-definition video images. The application can effectively fuse space-time information with a smaller model, thereby realizing high-quality space-time super-resolution reconstruction.

The application provides an active power distribution network operation state information mining and prediction system and method, at least comprising: a collection module: based on a distributed measurement principle, collecting power distribution network different node electronic equipment operation state information and collecting static information including power grid topology and line impedance; a processing module: for processing the operation state information, including effective data extraction and bad data identification and cleaning; finding key features of static information and updating the state; a prediction module: for state prediction through the operation state information obtained by the processing module, the state prediction at least including one of load prediction, new energy output prediction and power distribution network operation state prediction. The optimal state of the distributed power supply access in the power distribution network can be predicted according to the analysis result.

The application discloses a marine target recognition method and device based on multi-view joint, which comprises the following steps: using a three-dimensional sampling strategy to sample the view sequence as a whole and adding position embedding to generate visible blocks and mask blocks; using an encoder to encode the visible blocks to obtain visible marks, and generating a shared learnable vector for all mask blocks as mask marks; a decoder reconstructs the input view sequence according to the visible marks and the mask marks, calculates the mean square error of the reconstructed mask blocks and the original mask blocks in the pixel space to obtain the view reconstruction loss; a dynamic updating long storage queue is used to construct a marine target visible mark set containing the current batch data, and a graph-based non-parametric method is used for instance-level association information mining to learn the association information between similar marine targets and obtain a similar model loss; the sum of the view reconstruction loss and the similar model loss is used as the target function of the network for iterative optimization, and finally the encoder is used as a marine target feature extractor for multi-view marine target recognition.