A navigation big data platform monitoring system and method

Abstract

The present invention proposes a navigation big data platform monitoring system and method; wherein the system includes: a plurality of sensor devices; an edge server subsystem having a plurality of computing nodes, the plurality of computing nodes being arranged in various areas of the ship, respectively connected with corresponding sensor devices, for processing and storing the monitoring data of the corresponding sensors, the plurality of computing nodes forming an edge computing cluster through information interaction, and pointing to the same heterogeneous database; and a central control subsystem storing a plurality of visualization algorithm modules and providing a plurality of application services, the plurality of application services being used to retrieve corresponding data from the heterogeneous database, and processing data according to the visualization algorithm modules loaded in the current application service; the central control subsystem and the edge server subsystem communicate through a data exchange network formed by a plurality of communication modes. The present invention can realize on-site processing, storage and analysis of data to flexibly and reliably cope with complex and changeable weather.

Description

Technical Field

[0001] The present invention relates to the fields of communications and computers, and in particular to a navigation big data platform monitoring system and method. Background Art

[0002] The safety of ship navigation is the primary issue in the design, construction and use of ships. Since the meteorological and hydrological conditions in the polar regions are quite different from those in ordinary waterways, and the typhoons, waves and ocean currents are relatively complex, there are more uncertain factors that affect the safety of scientific research ships during navigation. The intelligent monitoring system of ships can effectively reduce the occurrence of navigation accidents and improve the safety of navigation.

[0003] However, the application service functions in the existing intelligent ship monitoring system are fixed, and different application service functions have their own corresponding databases, which require professional personnel to maintain and manage the data; the fixed application service functions make it difficult for operators to cope with complex and changeable weather conditions, and it is impossible to effectively associate the stored data, making it difficult to make accurate judgments. Therefore, how to flexibly cope with complex and changeable weather conditions and make accurate judgments is urgently needed for polar navigation. Summary of the invention

[0004] In order to solve the technical problems in the background technology, in one aspect of the present invention, a navigation big data platform monitoring system is proposed, including: multiple sensor devices, an edge server subsystem and a central control subsystem; wherein the edge server subsystem has multiple computing nodes, the multiple computing nodes are arranged in various areas of the ship, and are respectively connected to corresponding sensor devices for processing and storing the monitoring data of the corresponding sensors, and the multiple computing nodes form an edge computing cluster through information interaction and point to the same heterogeneous database; the central control subsystem stores multiple visualization algorithm modules and provides multiple application services, the multiple application services are used to retrieve corresponding data from the heterogeneous database, and perform data processing according to the visualization algorithm module loaded in the current application service; the central control subsystem communicates with the edge server subsystem through a data exchange network formed by multiple communication methods.

[0005] In one or more embodiments, the multiple visualization algorithm modules are multiple API interfaces formed by encapsulating multiple algorithms based on a RESTful microservice framework, and the multiple algorithms are stored in a dedicated algorithm library of the central control subsystem.

[0006] In one or more embodiments, the various algorithms are used for data analysis and management, resource integration, and application support.

[0007] In one or more embodiments, the edge server subsystem and the central control subsystem are both managed by a mobile cloud operating system to virtualize computing resources, storage resources, and network resources.

[0008] In one or more embodiments, the edge server subsystem uses a distributed redundant storage method to store data.

[0009] In one or more embodiments, the edge server subsystem is communicatively connected to the various sensor devices via a data acquisition network, the data acquisition network has a plurality of aggregation nodes, the plurality of aggregation nodes are arranged between the sensor nodes and the server nodes, and the ZigBee protocol is used for communication between the sensor nodes and the server nodes.

[0010] In one or more embodiments, the data exchange network is composed of a wired backbone network, a satellite communication network, and a wireless coverage network.

[0011] In one or more embodiments, the multiple application services include: ship status monitoring, scientific research and teaching, and a big data website; wherein the big data website is used to share navigation data and data algorithms.

[0012] In another aspect of the present invention, a navigation big data platform monitoring method is proposed, which includes: associating and saving multiple monitoring data obtained by multiple sensor devices in the same heterogeneous database; retrieving corresponding data from the heterogeneous database through corresponding application services, and loading required visualization algorithm modules from a dedicated algorithm library for data analysis and processing; sharing the monitoring data, the visualization algorithm module and the analysis and processing results of the data through the big data website provided by the navigation big data platform.

[0013] In one or more embodiments, loading the required visualization algorithm module from the dedicated algorithm library includes: searching the required visualization algorithm module in the dedicated algorithm library; and loading the required visualization algorithm module into the algorithm area of ​​the application service by dragging and dropping.

[0014] The beneficial effects of the present invention include: the navigation big data platform monitoring system proposed in the present invention sets server nodes in various areas of the ship, and enables them to communicate with each other to form an edge computing cluster, which can process and save the real-time sensor monitoring data on-site, avoiding the occurrence of problems during data transmission; and, various data are managed through the same heterogeneous database, which facilitates data maintenance and management; and, a visualization algorithm module is designed so that operators can perform on-site modeling and on-site analysis, thereby being able to flexibly respond to complex and changeable weather. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a schematic diagram of the architecture composition of the navigation big data platform monitoring system of the present invention;

[0017] Figure 2 This is a schematic diagram of the architecture of the algorithm control part of the navigation big data platform of the present invention;

[0018] Figure 3 A schematic diagram of a visualization algorithm module KMeans according to an embodiment of the present invention;

[0019] Figure 4 A schematic diagram of a model for classification modeling in a visualization interface (algorithm area) based on a visualization algorithm module according to an embodiment of the present invention;

[0020] Figure 5 A schematic diagram of a model for linear fitting modeling in a visualization interface (algorithm area) based on a visualization algorithm module according to an embodiment of the present invention;

[0021] Figure 6 A schematic diagram of a model for model evaluation and modeling in a visualization interface (algorithm area) based on a visualization algorithm module according to an embodiment of the present invention;

[0022] Figure 7 The present invention is a workflow diagram of a navigation big data platform monitoring method. DETAILED DESCRIPTION

[0023] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings.

[0024] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are for distinguishing two non-identical entities with the same name or non-identical parameters. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. The subsequent embodiments will not explain this one by one.

[0025] See also Figure 1 , Figure 1 FIG. 1 is a schematic diagram of the architecture of the navigation big data platform monitoring system of the present invention. Figure 1The infrastructure part of the platform architecture shown in the figure, the navigation big data platform monitoring system of the present invention, includes: a variety of sensor devices, an edge server subsystem and a central control subsystem; wherein, the edge server subsystem has a plurality of computing nodes, and the plurality of computing nodes are arranged in various areas of the ship, and are respectively connected with corresponding sensor devices, for processing and storing the monitoring data of the corresponding sensors, and the plurality of computing nodes form an edge computing cluster through information interaction, and point to the same heterogeneous database; the central control subsystem stores a plurality of visualization algorithm modules and provides a plurality of application services, and the plurality of application services are used to retrieve the corresponding data from the heterogeneous database, and perform data processing according to the visualization algorithm module loaded in the current application service; the central control subsystem communicates with the edge server subsystem through a data exchange network formed by a plurality of communication modes. Among them, the plurality of application services include: ship status monitoring, scientific research and teaching, and a big data website; wherein, the big data website is used to share navigation data and data algorithms.

[0026] In one embodiment, multiple visualization algorithm modules are multiple API interfaces formed by encapsulating multiple algorithms based on the RESTful microservice framework, and multiple algorithms are stored in the dedicated algorithm library of the central control subsystem. Specifically, the algorithm control part of the navigation big data platform of the present invention adopts a layered software architecture design, which is divided into a control layer, a service layer, an algorithm layer, a data access layer and an entity layer. The control layer is responsible for routing, control and response; the service layer is responsible for service distribution, model selection and exception handling; the algorithm layer is responsible for data processing, algorithm calling and model generation; the data access layer is responsible for data connection, data access and data storage; the entity layer includes algorithm entities, tool entities, exception entities and configuration entities. The visualization algorithm module is essentially a graphical API interface for providing to upper-level business applications for calling. The architecture of the algorithm control part of the navigation big data platform of the present invention is as follows Figure 2 As shown, Figure 2 It is a schematic diagram of the architecture of the algorithm control part of the navigation big data platform of the present invention.

[0027] In a further embodiment, the various algorithms in the present invention are used for data analysis and management, resource integration and application support; specifically, the present invention not only provides common machine learning and deep learning algorithms, but also provides two types of algorithm libraries for signal processing and anomaly detection in combination with the particularity of polar navigation.

[0028] More specifically, the machine learning algorithm library provided by the present invention mainly includes four major categories of algorithms: clustering, classification, regression, and association. Cluster analysis is an analysis process that divides a set of physical or abstract objects into multiple classes composed of similar objects. It is different from classification in that the classes required for clustering are unknown. This algorithm can be used for analysis of meteorology, hydrology, ice conditions, etc.; classification analysis is to analyze a training set of known categories and discover classification rules from them to predict the category of new data. It can also be used for analysis of meteorology, hydrology, ice conditions, etc.; regression analysis is a predictive modeling technique that studies the relationship between dependent variables (targets) and independent variables (predictors). It can be used for analysis of meteorology, hydrology, etc. and navigation routes; association analysis is an algorithm that discovers associations and related connections between data item sets from a large amount of data. It can be used for correlation analysis of meteorology, hydrology, ice conditions, and navigation. The following introduces the application using cluster analysis as an example.

[0029] Cluster analysis algorithm is a statistical analysis method for studying classification problems. It is a method for grouping samples according to sample similarity without a given classification. It is an unsupervised machine learning algorithm. The clustering algorithm does not care about the causal relationship between features and variables. Its goal is to have large individual differences between different categories of classification results, while the individual differences of the same category are relatively small. The algorithm is applied in various fields and is also used in conjunction with other algorithms, such as regression analysis. The clustering algorithm is based on similarity. The patterns in a cluster have more similarities than the patterns in different clusters. The algorithm platform provides three clustering algorithms: KMeans, fuzzy C means and EM clustering. The present invention will be introduced using KMeans as an example.

[0030] See also Figure 3 , Figure 3 Schematic diagram of the visualization algorithm module KMeans of an embodiment of the present invention. In one embodiment, the process of data processing using the classification algorithm Kmeans of the present invention is as follows:

[0031] Search for data classification algorithms in a dedicated database and select the Kmeans algorithm;

[0032] Drag the visualization algorithm module corresponding to the Kmeans algorithm to the algorithm area of ​​the corresponding application service;

[0033] Set the input: the number of clusters k and a database containing n data objects; set the output: k clusters that meet the minimum variance criterion;

[0034] Call and run the Kmeans algorithm through the API interface corresponding to the Kmeans algorithm module icon, and analyze and process the corresponding data according to the preset input and output conditions.

[0035] In a more specific embodiment, the complete modeling process based on the Kmeans algorithm is as follows: Figure 4 As shown; Figure 4 This is a schematic diagram of a model for classification modeling based on a visualization algorithm module in a visualization interface (algorithm area) according to an embodiment of the present invention. MySQL is used to retrieve the corresponding database data, and then the attribute module is used to filter the data, and then the Kmeans is used to perform cluster analysis, and finally the data is output in the file system HDFS. Figure 4 It can be seen that the modeling process of the present invention can be simplified to dragging the corresponding multiple visualization algorithm modules into the algorithm area of ​​the application service, and realizing it by sequentially connecting the visualization algorithm modules. The platform framework of the present invention can greatly facilitate operators to perform on-site modeling analysis according to the situation, so as to flexibly respond to various emergencies.

[0036] In another embodiment, the present invention can also perform model training and model evaluation concurrently based on the operation of the visualization algorithm module. For details, please refer to the attached Figure 5 and attached Figure 6 . Figure 5 This is a schematic diagram of a model for linear fitting modeling based on a visualization algorithm module in a visualization interface (algorithm area) according to an embodiment of the present invention. Figure 5 The present invention can use the data in the HDFS file system as input, and pass the data to the linear fitting algorithm module and the generalized linear fitting module respectively through the multi-branch algorithm module, and output the model after setting the parameters in each algorithm module. In another embodiment, the present invention can also use the visualization algorithm module for model evaluation. Figure 6 This is a schematic diagram of a model for model evaluation and modeling based on a visualization algorithm module in a visualization interface (algorithm area) according to an embodiment of the present invention. Figure 6 In the present invention, the same data sample input is used to realize the simultaneous evaluation of the decision tree algorithm, BP neural network and Bayesian algorithm model in a parallel manner.

[0037] More specifically, the anomaly detection database provided by the present invention includes four signal processing algorithms, namely frequency domain analysis, Hilbert transform, EMD analysis and WVD distribution, to realize comprehensive processing such as signal extraction, transformation and analysis. Among them, the Empirical Mode Decomposition (EMD) method is to decompose the signal based on the time scale characteristics of the data itself, without presetting any basis function. This is essentially different from the Fourier decomposition and wavelet decomposition methods based on a priori harmonic basis functions and wavelet basis functions. It is precisely because of this feature that the EMD method can be theoretically applied to the decomposition of any type of signal, and therefore has a very obvious advantage in processing non-stationary and nonlinear data, and is suitable for analyzing non-linear and non-stationary signal sequences, with a very high signal-to-noise ratio. The EMD method can be used in aspects such as mechanical fault diagnosis during polar navigation.

[0038] Anomaly detection algorithms are algorithms that detect anomalies, such as network quality anomalies, user access behavior anomalies, server anomalies, switch anomalies, and system anomalies, all of which can be monitored through anomaly detection algorithms. Anomalies are defined as outliers that are more likely to be separated, which can be understood as points that are sparsely distributed and far away from densely populated groups. In statistical terms, in the data space, sparsely distributed areas indicate that the probability of data occurring in these areas is very low, so the data falling in these areas can be considered abnormal. The algorithm platform provides six anomaly detection algorithms: 3σ-based anomaly detection algorithm, quartile-based anomaly detection algorithm, local anomaly factor detection algorithm, isolation forest anomaly detection algorithm, SVM-based anomaly detection algorithm, and DBSCAN-based anomaly detection algorithm.

[0039] The 3σ-based anomaly detection algorithm states that an outlier is a value in a group of measured values ​​that deviates from the mean by more than two standard deviations, and a value that deviates from the mean by more than three standard deviations is called a highly abnormal outlier. Outlier detection is the process of finding data objects with behaviors that are very different from expectations in machine learning. These objects are called outliers or anomalies.

[0040] Compared with the 3σ principle, the quartile-based anomaly detection is based on actual data, truly and intuitively showing the true face of data distribution, and does not impose any restrictive requirements on the data (the 3σ principle requires that the data obey the normal distribution or approximately obey the normal distribution). The standard for judging outliers is based on quartiles and interquartile ranges. Quartiles give some indication of the center, spread, and shape of the data distribution, and have a certain robustness, that is, 25% of the data can become arbitrarily far without greatly disturbing the quartile, so outliers usually cannot affect this standard. In view of this, the results of the box plot in identifying outliers are more objective, so it has certain advantages in identifying outliers. Quartile-based anomaly detection provides a standard for identifying outliers, that is, outliers are usually defined as values ​​less than QL-1.5IQR or greater than QU+1.5IQR. Among them, QL is called the lower quartile, which means that one-quarter of all observations are smaller than it; QU is called the upper quartile, which means that one-quarter of all observations are larger than it; IQR is called the interquartile range, which is the difference between the upper quartile QU and the lower quartile QL, and contains half of all observations.

[0041] The local outlier factor detection algorithm LOF (Local Outlier Factor) is a density-based outlier detection algorithm suitable for high-dimensional data detection. Its core idea is that the density of outliers should be smaller than that of other points in the neighborhood.

[0042] In Isolation Forest, anomalies are defined as "outliers that are easily isolated", which can be understood as points that are sparsely distributed and far away from dense groups. In feature space, sparsely distributed areas indicate that the probability of an event occurring in the area is very low, so the data falling in these areas can be considered abnormal. Isolation Forest is an unsupervised anomaly detection method suitable for continuous numerical data, that is, no labeled samples are required for training, but the features need to be continuous. iForest uses a very efficient strategy for finding which points are easily isolated. In Isolation Forest, the data set is randomly split recursively until all sample points are isolated. Under this random splitting strategy, outliers usually have shorter paths. Intuitively, those clusters with high density need to be cut many times to be isolated, but those points with low density can be easily isolated.

[0043] The SVM-based anomaly detection algorithm does not tend to eliminate individual large regression errors, but considers the smoothness of the regression curve as a whole, and identifies abnormal data in the measurement data by comparing the residuals between the regression estimate and the measured value.

[0044] DBSCAN is a representative density-based clustering algorithm. It defines a cluster as the largest set of points connected by density, can divide areas with sufficiently high density into clusters, and can find clusters of any shape in "abnormal" data. At the same time, it divides "abnormal" data into a separate class.

[0045] In a further embodiment, in order to obtain better classification results, the method of the present invention also includes filtering and cleaning the monitoring data before the edge server saves the monitoring data of the corresponding sensor, and forming structured data. In addition, in order to ensure the security of the stored data, each edge server of the present invention realizes distributed redundant storage of data through data interaction. In a preferred embodiment, when the computing power of a certain edge server node is insufficient, the edge server node storing the same data with it can also complete the corresponding data processing work together through communication interaction. Among them, the edge server subsystem is connected to a variety of sensor devices through a data acquisition network communication, and the data acquisition network has multiple aggregation nodes, and the multiple aggregation nodes are arranged between the sensor nodes and the server nodes, and the ZigBee protocol is used for communication between the sensor nodes and the server nodes.

[0046] In a further embodiment, the method of the present invention further includes managing both the edge server subsystem and the central control subsystem through a mobile cloud operating system to virtualize computing resources, storage resources, and network resources. Resource virtualization not only helps in resource management, but also facilitates system expansion.

[0047] The navigation big data platform monitoring system proposed in the present invention sets server nodes in various areas of the ship and enables them to communicate with each other to form an edge computing cluster, which can process and save the real-time sensor monitoring data on-site, avoiding the occurrence of problems during data transmission; and, various data are managed through the same heterogeneous database, which facilitates data maintenance and management; and, a visualization algorithm module is designed so that operators can perform on-site modeling and on-site analysis, thereby being able to flexibly respond to complex and changeable weather.

[0048] Specifically, the present invention constructs the algorithm control part of the navigation big data platform based on virtualization, that is, Figure 1The "data service" in it includes data storage, integration and some application support (such as algorithm execution, task scheduling, etc.). Through virtualization, computing resources can be more reasonably allocated and utilized to support the various application services in the "application system" of the navigation big data platform, while realizing user visual interactive operations and professional application development. The navigation big data platform of the present invention is developed, debugged and improved based on Ambari, and has the characteristics of being easier to use, more stable and safer. In addition, the navigation big data platform monitoring system of the present invention provides a wealth of interfaces to facilitate secondary development and packaging. Each visualization algorithm module supports development in multiple languages ​​such as java and python to develop special application services to support polar navigation.

[0049] In a further embodiment, the data exchange network between the central control subsystem and the edge server subsystem is composed of a wired backbone network, a satellite communication network and a wireless coverage network. Specifically, in the present invention, the importance of data is graded, and different transmission methods are used for data of different levels. The priority of the transmission method for data with higher importance is the backbone network and the wireless coverage network in turn; wherein the satellite communication network is used for data sharing of big data website application services in the navigation big data platform.

[0050] Based on the above navigation big data platform monitoring system, the present invention also discloses a navigation big data platform monitoring method. Figure 7 , Figure 7 The flowchart of the navigation big data platform monitoring method of the present invention includes: associating and storing a variety of monitoring data obtained by a variety of sensor devices in the same heterogeneous database; retrieving corresponding data from the heterogeneous database through corresponding application services, and loading the required visualization algorithm module from the dedicated algorithm library for data analysis and processing; sharing the monitoring data, visualization algorithm module and data analysis and processing results through the big data website provided by the navigation big data platform.

[0051] In a further implementation, loading the required visualization algorithm module from the dedicated algorithm library includes: searching the required visualization algorithm module in the dedicated algorithm library; and loading the required visualization algorithm module into the algorithm area of ​​the application service by dragging and dropping.

[0052] The above are exemplary embodiments disclosed in the present invention, but it should be noted that various changes and modifications may be made without departing from the scope disclosed in the embodiments of the present invention as defined in the claims. The functions, steps and / or actions of the method claims according to the disclosed embodiments described herein do not need to be performed in any particular order. In addition, although the elements disclosed in the embodiments of the present invention may be described or required in individual form, they may also be understood as multiple unless explicitly limited to the singular.

[0053] It should be understood that, as used herein, the singular forms "a", "an" are intended to include the plural forms as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations including one or more of the associated listed items.

[0054] The serial numbers of the embodiments disclosed in the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0055] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention (including the claims) is limited to these examples; under the concept of the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the embodiments of the present invention as above, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A navigation big data platform monitoring system, characterized in that: include: A variety of sensor devices, edge server subsystems and central control subsystems; among them, The edge server subsystem has a plurality of computing nodes, which are arranged in various areas of the ship, are respectively connected to the corresponding sensor devices, and are configured to process and store the monitoring data of the corresponding sensors. The plurality of computing nodes form an edge computing cluster through information interaction and point to the same heterogeneous database; The central control subsystem stores a plurality of visualization algorithm modules and provides a plurality of application services, wherein the plurality of application services are used to retrieve corresponding data from the heterogeneous database and process the data according to the visualization algorithm modules loaded in the current application service; The central control subsystem communicates with the edge server subsystem via a data exchange network formed by multiple communication modes; Wherein, the heterogeneous database is used to associate and store a variety of monitoring data; The multiple visualization algorithm modules are multiple API interfaces formed by encapsulating multiple algorithms based on the RESTful microservice framework. The multiple algorithms are stored in a dedicated algorithm library of the central control subsystem. The dedicated algorithm library includes a signal processing algorithm library and an anomaly detection algorithm library. The signal processing algorithm library includes a machine learning algorithm library composed of four types of algorithms: clustering, classification, regression, and association. The anomaly detection algorithm library includes four signal processing algorithms: frequency domain analysis, Hilbert transform, EMD analysis, and WVD distribution. The multiple application services are built by dragging the visualization algorithm modules of the corresponding algorithms into the algorithm area of ​​the application service, setting configuration parameters and connecting them; The edge server subsystem and the central control subsystem are both managed by a mobile cloud operating system to virtualize computing resources, storage resources, and network resources to support a variety of application services.

2. A navigation big data platform monitoring system as claimed in claim 1, characterized in that: The various algorithm configurations are used for data analysis and management, resource integration, and application support.

3. A navigation big data platform monitoring system as claimed in claim 1, characterized in that: The edge server subsystem adopts a distributed redundant storage method to store data.

4. A navigation big data platform monitoring system as claimed in claim 1, characterized in that: The edge server subsystem is connected to the various sensor devices through a data acquisition network. The data acquisition network has multiple aggregation nodes, which are arranged between the sensor nodes and the server nodes, and use the ZigBee protocol to communicate between the sensor nodes and the server nodes.

5. The navigation big data platform monitoring system according to claim 1, characterized in that: The data exchange network consists of a wired backbone network, a satellite communication network and a wireless coverage network.

6. A navigation big data platform monitoring system as claimed in claim 1, characterized in that: The various application services include: Ship status monitoring, scientific research and teaching, and big data website; wherein the big data website is used to share navigation data and data algorithms.

7. A navigation big data platform monitoring method based on the navigation big data platform monitoring system according to any one of claims 1 to 6, characterized in that: The method comprises: The various monitoring data obtained by various sensor devices are associated and stored in the same heterogeneous database; Retrieving corresponding data from the heterogeneous database through corresponding application services, and loading required visualization algorithm modules from the dedicated algorithm library for data analysis and processing; The monitoring data, the visualization algorithm module, and the analysis and processing results of the data are shared through the big data website provided by the navigation big data platform.

8. A navigation big data platform monitoring method as claimed in claim 7, characterized in that: The step of loading the required visualization algorithm module from the dedicated algorithm library includes: Searching for the required visualization algorithm module in the dedicated algorithm library; Load the required visualization algorithm module into the algorithm area of ​​the application service by dragging and dropping.

Images