1309 results about "Multi source data" patented technology

The invention discloses a disease knowledge map construction method and a system, a device and a storage medium thereof, belonging to the technical field of disease knowledge maps. The disease knowledge map construction method comprises the following steps: extracting or learning entity, attributes and relationships among entities from a multi-source database to form ontological knowledge representation; B. knowledge fusion: integrate knowledge to eliminate contradictions and ambiguity; C. Knowledge processing: After quality assessment, the fused knowledge is added to the knowledge base. It also includes disease knowledge mapping platform system, equipment and storage medium. Aiming at the problems existing in the prior art, it extracts entities, attributes and their relationships from multiple data sources, and fuses and processes them, so as to quickly construct a normalized and standardized disease knowledge map.

The invention discloses a power grid multi-source data fusion method and system based on a multi-element heterogeneous model. The method comprises the following steps of multi-source data access, metadata storage, unified device modeling and data extraction, model matching degree calculation and multi-element data fusion. The system mainly comprises the five modules of multi-source data access, metadata storage, unified device modeling and data extraction, model matching degree calculation and multi-element data fusion. A unified model including multi-source system data is established by deeply analyzing the multi-source system data, automatic association is performed through model traversal comparison and model matching degree calculation according to the matching degree, automatic data integration and fusion of 90% or above is achieved, unfused data details and detailed causes are accurately analyzed, integration and fusion of various service data are achieved, and the overall fusion quality is effective managed and controlled.

The invention provides a three-dimensional building fine geometric reconstruction method integrating airborne and vehicle-mounted three-dimensional laser point clouds and streetscape images. The method comprises the following steps: (1) a quick modeling method based on airborne laser data; (2) combining the semantic segmentation framework of the vehicle-mounted point cloud and the image; and (3) amodel automatic enhancement algorithm fusing multi-source data. According to the method, airborne laser point cloud, vehicle-mounted laser point cloud and streetscape images are taken as research objects, model reconstruction, model enhancement and updating are taken as targets, joint processing of point cloud and image data of different platforms is realized, and the fusion potential of variousdata is fully mined. The final research result will perfect the fusion and fine modeling framework of vehicle-mounted-airborne data, promote the development of the point cloud data semantic segmentation technology, and serve the emerging application fields of unmanned driving and the like.

The invention discloses a traffic navigation method of a wireless ad hoc network based on multi-source data, including a sudden traffic accident prewarning process. The prewarning process includes the steps: 1, the information collected from an information collecting module is obtained; 2, the emergency degree of the accident and the region and direction where the accident information is required to be issued are all arranged according to the information acquired from the step 1; 3, a vehicle knot which collects the sudden traffic accident information adjusts the priority and issuing region of the information according to the type and emergency degree of the traffic accident and transfers the accident information according to the issuing direction of the information; 4, the vehicles knot which receives the sudden traffic accident information inform drivers and passengers of the prewarning information ahead. The invention additionally adopts the prewarning function for sudden traffic accidents to better avoid the chain collision when the accident happens.

The invention discloses a method for comprehensive monitoring and intelligent analysis of the safety state of a rail system. The method combines three sensing monitoring technologies, monitors low-frequency data such as structural temperature based on optical fiber grating technology, and uses corrected stress-strain technology to monitor the horizontal and vertical rails. High-frequency data such as axial stress, and for sensitive structures that are difficult to measure, such as switch point rails, use video perception technology to observe large deformation and surface conditions of the structure, forming an all-weather system monitoring of the railway track system from appearance to interior, from high frequency to low frequency. Through fusion and analysis of the collected multi-source data, the track status can be effectively evaluated, diagnosed and predicted, and then timely early warning of the track safety status can be realized. The invention has reasonable arrangement of measuring points, high degree of automaticity in the monitoring process, accurate evaluation of line status, timely early warning of abnormal conditions, realizes safe and controllable service of the railway track system, and provides reliable guarantee for safe and stable operation of trains.

The invention provides a time-space characteristic and cross-border mining identification method for multi-source data monitoring mining area deformation. The method comprises the following steps: firstly, obtaining and optimally processing data by using a synthetic aperture radar (SAR); fusing SAR data monitoring data of a multi-satellite platform to obtain a settlement result map; carrying out supplementary monitoring on 'a large-deformation area' or 'a de-coherence area' in a tested mining area in the fused settlement result map; unifying multi-satellite platform data monitoring result coordinates; and finally inverting time-space characteristics of surface deformation of the mining area, so as to identify a cross-border mining area. The method is simple, small in calculated quantity and high in identification efficiency, and has important theoretical value and a wide application prospect in the aspects of maintaining the mining order, ensuring the mine safety and protecting the ecological environment of the mine; and the time-space characteristics of surface deformation of the mining area can be effectively inverted.

Systems and processes for assembling de-identified patient healthcare data records in a longitudinal database are provided. The systems and processes may be implemented over multiple data suppliers and common database facilities while ensuring patient privacy. At the data supplier locations, patient-identifying attributes in the data records are placed in standard format and then doubly encrypted using a pair of encryption keys before transmission to a common database facility. The pair of encryption keys includes a key specific to the data supplier and a key specific to the common database facility. At the common database facility, the encryption specific to the data supplier is removed, so that multi-sourced data records have only the common database encryption. Without direct access to patient identifying-information, the encrypted data records are assigned dummy labels or tags by which the data records can be longitudinally linked in the database. The tags are assigned based on statistical matching of the values of a select set of encrypted data attributes with a reference database of tags and associated encrypted data attribute values.

The invention belongs to the technical field of data processing, and particularly relates to a method of a big data governance system integrating application and display of multi-source government affair data. The specific technical scheme is as follows: the method for constructing the government affair big data governance system comprises the following specific steps: 1, compiling a data resourcedirectory; 2, sharing and exchanging government affair big data; 3, carrying out government affair big data treatment; 4, gathering and integrating government affair big data; 5, mining and analyzinggovernment affair big data; 6, carrying out government affair big data application. According to the invention, multi-source government affair data such as spatial data, business data, attribute data, workflow data, essential data and the like are effectively fused; the data processing method and the application method are effectively combined and applied, intelligent information transmission integrating application and display of multi-source data after data processing and analysis is achieved, and therefore effective fusion of service data and two-dimensional and three-dimensional graphic data is achieved, and multi-dimensional three-dimensional data information presentation is achieved.

The invention discloses a multi-source data integration method based on geographic information, and belongs to the geographic information technology. The method is characterized in comprising the following steps of: 1) analysis design: investigating and surveying required data, and generating a data analysis report; 2) data arrangement processing: carrying out integration processing on the data subjected to the analysis design; 3) data storage: carrying out classification integration storage on an achievement obtained after data processing, and forming a kernel database; and 4) map service configuration: carrying out symbol rendering on spatial data, publishing the spatial data to a corresponding map server, and carrying out the integrative display of system configuration and service in an appointed system. The method has the advantages that multi-source data, including the spatial data, business data, attribute data, workflow data, element data and the like, can be effectively fused, and data processing and application methods can be effectively combined and applied.

A system and method are disclosed for compiling a database of investor-related data by gathering and linking customer-specific data records from multiple unaffiliated financial institutions, where such data records are coded in such a manner that the database compiler is enabled to link, across data providers and/or time periods, data records that pertain to the same investor without being provided any information that reveals the identity of any investor.

The invention discloses an automated supervised learning method with multi-source data supported, which comprises steps of (1) data pre-processing, (2) feature engineering, (3) model and super parameter regulation and (4) Bayesian pipeline optimization. The traditional data analysis process is automated, the process of manually regulating a machine learning pipeline is fundamentally improved, under the high coupling degree of super parameter regulation and pipeline optimization, the extensibility of the system on a supervised learning algorithm is greatly improved, a genetic algorithm is creatively put forward for regulation on the super parameters for the machine learning pipeline, and the efficiency for automated parameter regulation is greatly improved. Besides, a Bayesian optimizer is adopted for optimizing a pipeline algorithm combination, the problem of combination space explosion can be greatly solved, and finally, the accuracy and the efficiency of the automated supervised learning method are improved in the result.

The invention relates to a public transport passenger flow monitoring method and device based on multi-source data, computer equipment and a storage medium. The method comprises the steps of obtainingbus station entering and exiting data, bus IC card data, subway gate entering and exiting data and weather data of public transport; determining subway station entering data and subway station exiting data of the passengers according to the subway gate entering and exiting data; determining bus getting-on data of passengers by matching the bus IC card data with the bus station entering and exiting data; calculating bus getting-off data of the passengers according to the subway station entering data and the bus getting-on data, and determining trip chain data of the passengers; obtaining the time difference of two adjacent riding in the travel chain data, and determining the transfer data of the passenger; according to the weather data, the travel chain data of the passengers and the transfer data, obtaining passenger flow condition monitoring results of stations, lines and designated areas of public transport. According to the invention, the passenger flow monitoring results are comprehensive and have high accuracy, and the general processing method for bus and subway passenger flow data is provided for an informatization system.

The power distribution network fault information mining and diagnosing method based on the multi-source heterogeneous data comprises the steps of firstly, formulating a pre-set rule for a power distribution network fault event, carrying out data mining, and then preprocessing and fusing the multi-source heterogeneous information of the power distribution network, and finally, performing fault diagnosis on the power distribution network based on the multi-source data. According to the method, a production management system, fault repair and SCADA data are fused, SCADA system and TCM system event pre-set rules are established, the information related to the faults is extracted, and the information is stored in a big data platform; the relevance of the multi-source heterogeneous data is mined, information and attributes of events in the distribution network system are diagnosed, the auxiliary information is combined to verify the diagnosis result, and the technical support is provided forthe high-quality, safe and stable operation of the power distribution network.

The invention belongs to the technical field of agricultural flood disaster range monitoring. The invention discloses an agricultural flood disaster range monitoring system and method based on a high-resolution satellite remote sensing image. The agricultural flood disaster range monitoring system based on the high-resolution satellite remote sensing image comprises a remote sensing image acquisition module, a main control module, an image correction module, an image enhancement module, an image feature extraction module, a disaster information analysis module, an information processing moduleand a display module. Through the image enhancement module, the definition of the acquired remote sensing image can be greatly improved; meanwhile, various information data can be processed through the information processing module. The processing efficiency and utilization rate of multi-source data are improved. A model is constructed to improve the precision and accuracy of the model. The modelis used to accurately extract water body information. The flood disaster dynamic development situation of a river reach or a tributary is monitored and preliminarily evaluated, which lays a foundation for providing accurate disaster information service for river basin flood disasters.

The invention discloses an aero-engine turbine blade reliability digital twinning modeling method, relates to the technical field of aero-engines, and aims to realize high fidelity simulation and tracking of aero-engine turbine blade damage and life loss and quickly and efficiently evaluate the reliability and residual life of the aero-engine turbine blade. According to the invention, the turbineblade is taken as an object, aiming at the characteristics of multi-source and multi-time-scale use reliability related information, few fault samples and the like of the turbine blade, a physical model driving and data driving fusion method is adopted, that is, the specialty of a physical model in the aspect of explaining specific data is fully utilized, and a turbine blade digital entity model based on a high-precision physical model and multi-source data is constructed by means of the advantages of a machine learning method in the aspects of dimension reduction and multi-modal data fitting.The model can reflect the physical characteristics of the turbine blade and the variable characteristics dealing with different environments and damages, and can realize the product operation reliability dynamic evaluation and residual life prediction of multimode information fusion.

The present invention proposes a multi-source data-based crowding degree prediction method of an urban public open space. Urban multi-source data such as WeChat user number data, POI data, comment data, area attribute data, meteorological data and time attribute data are utilized to determine the spatial-temporal features of each small region in the space; the people flow indexes of a region in different historical periods are obtained from the WeChat user number chart data through using a gridding sampling adding method; the historical people flow indexes and the spatial-temporal features are inputted into a fuzzy neural network model, so that people flow index prediction can be realized; and a predicted people flow index is converted into crowding degree through using clustering and comparison. With the method of the invention adopted, the prediction of the crowding degree is successfully achieved through using the open urban multi-source data; and the technological problems of too high prediction costs caused by over-reliance on hardware equipment, and incapability of realizing accurate prediction by using a single data source of a traditional crowding degree prediction method can be solved; and prediction economic costs are decreased, and prediction accuracy is improved.

The invention discloses an urban traffic flow prediction method based on multi-source data fusion. The urban traffic flow prediction method comprises the following steps: performing a fusion algorithmoriented to structured and unstructured traffic data; to be specific, designing a wavelet neural network (WNN) containing a three-layer network topology structure to process traffic volume parametersof a multi-source detector; supposing that the traffic detector performs statistics by taking 5min as a time interval, setting an acquired traffic flow sequence to be xi (i = 1, 2, 3,..., k), and using the xi as an input traffic parameter of the wavelet neural network. According to the invention, multi-azimuth detection is carried out in combination with various sensors, comprehensive and complete traffic information is obtained, structured and unstructured data are comprehensively analyzed and fused, and the accuracy and reliability of traffic flow data are improved; and in combination witha traffic flow prediction algorithm based on a deep belief network, prediction of the traffic flow is realized, so that the traffic flow prediction precision is improved and the traffic jam is relieved.

The invention discloses a multi-source data assisted clinical decision support system and method. The system comprises a medical/pharmaceutical data storage unit, a clinical pathway/evidence storage unit, an information input unit, a comparison processor unit, a diagnosis and treatment result output unit and an early warning and operation recording unit. According to the multi-source data assisted clinical decision support system and method of the invention, feasible clinical diagnosis and treatment scheme suggestions and corresponding clinical research and real world research evidence support are provided for medical workers, the whole disease cycle of diagnosis, treatment, prognosis, out-of-hospital management, disease burden and the like is covered, and doctors are assisted to quickly improve the clinical diagnosis and treatment level; the contradiction that time and energy of medical workers are difficult to keep up with clinical research progress is solved, and medical resources are balanced. After the system is deployed to a hospital end, when a doctor makes a prescription, the system can carry out reasonable early warning on treatment and medication schemes specifically involved in a clinical path; based on individual differences of patients, the reasonability and safety of the medication schemes are ensured, and the overall medical service quality is improved.

The invention discloses a remote sensing image mangrove forest extraction method and system based on a deep convolutional neural network, and the method comprises the steps: firstly carrying out the preprocessing of a high-resolution remote sensing image, including the atmospheric correction and research region cutting of the remote sensing image, and carrying out the waveband operation of each waveband after processing, so as to extract the priori feature information; achieving multi-band and feature information fusion by applying multi-source data fusion, and constructing a data set; training and verifying a semantic classification model ME-net built by a convolutional neural network; calling an ME-net model to realize automatic classification of the mangrove forest, and outputting a mask file in a png format, namely a classification and extraction result; and performing fine adjustment on the classification result through a long-distance conditional random field. In application of the classification model, the classification precision can reach 92.3% by expanding a data set, artificial visual interpretation can be completely replaced, and auxiliary technical support is providedfor updating of a high-precision image map and protection of a coastal region ecosystem.

The invention discloses a knowledge base construction method based on multi-modal fusion, which comprises the steps of extracting basic attributes of entities based on information box information of entries in a data source to establish a binary relationship, and generating a mapping dictionary of the information box attributes and the relationship; establishing a topic entity and relationship extraction model based on a word vector space and a conditional random field, and expanding the binary relationship to generate a multivariate relationship template; constructing a feature set of entities based on the extracted names of the binary relationships, performing hierarchical clustering division on the entities, constructing a classification system, and summarizing information of the classification system; carrying out attribute normalization on data in the data source according to the inherent attributes and attribute values of the entities; determining a fused data set, identifying equivalent entities in different data sources according to an entity alignment algorithm, establishing equivalent links of the same entity in the different data sources, and performing multi-source datafusion; and correcting and expanding the knowledge graph after multi-source data fusion to realize automatic knowledge completion.