Intelligent ship integrated control system, data vertical correlation method, storage medium and electronic equipment

Abstract

This invention discloses an intelligent ship integrated control system, a data vertical correlation method, a storage medium, and electronic equipment. The intelligent ship integrated control system includes a data correlation analysis module, a data acquisition module based on data correlation preprocessing, a ship business data retrieval module, and a data sharing and storage module. The data correlation analysis module calculates correlation indicators for vertical domain data based on data similarity and / or data temporal continuity and / or data causal correlation, and establishes a data vertical correlation model accordingly. The data acquisition module pre-correlates and groups sensor data based on the data vertical correlation model. The ship business data retrieval module calculates ship business display results based on indicator data and pre-correlated grouped data. This invention solves the problems of poor timeliness in analyzing massive amounts of ship data, fragmented business modules, lack of business collaboration, and low ship intelligence levels in existing intelligent ship technologies.

Description

Technical Field

[0001] This invention belongs to the field of intelligent ship technology, and in particular relates to intelligent ship integrated control systems, data vertical correlation methods, storage media and electronic devices. Background Technology

[0002] As a core direction for the transformation and upgrading of the shipping industry in the future, intelligent ships optimize navigation efficiency, reduce energy consumption, and enhance safety through data-driven approaches, thereby promoting the rapid development of global shipping.

[0003] Current mainstream intelligent ship solutions (such as some shipborne IoT platforms or remote monitoring systems) can collect ship data and achieve intelligent monitoring functions through data models. However, they still rely on traditional database architectures and have not introduced distributed storage or edge computing technologies, resulting in significant data throughput bottlenecks. When dealing with massive amounts of data from the engine room and meteorology, real-time query responses are slow, hindering the timeliness of data analysis. At the same time, the system design has not broken down the barriers between business modules, resulting in fragmented business modules, inconsistent data standards for navigation, power, and maintenance systems, weak inter-module interactivity, and difficulty in forming global optimization decisions. In addition, existing intelligent systems often focus on local functions (such as single device status monitoring) and lack support for data integration and business collaboration, failing to fundamentally solve the problems of data silos and system fragmentation. This leads to intelligent upgrades remaining superficial and making it difficult to achieve true "ship-port-cargo" end-to-end collaboration.

[0004] To address the issues of poor timeliness in analyzing massive amounts of ship data, fragmented business modules, lack of business collaboration, and insufficient global optimization leading to low levels of ship intelligence, this paper proposes an intelligent ship integrated control system, a data vertical correlation method, storage media, and electronic equipment. Summary of the Invention

[0005] This invention proposes an intelligent ship integrated control system, a data vertical correlation method, a storage medium, and electronic equipment to at least solve the problems of poor timeliness of massive ship data analysis, fragmented business modules, lack of business collaboration, and low ship intelligence level caused by the lack of global optimization in existing intelligent ship technologies.

[0006] According to one embodiment of the present invention, an intelligent ship integrated control system is provided, comprising:

[0007] Data correlation analysis module: Identify indicator data of different functional modules of the ship, calculate the correlation index of vertical domain data based on data similarity and / or data time continuity and / or data causal correlation, and establish a data vertical correlation model accordingly;

[0008] The data acquisition module based on data correlation preprocessing: It uses heterogeneous communication network fusion technology to collect sensor data deployed on the ship, and performs pre-correlation grouping of sensor data based on the data vertical correlation model;

[0009] Ship business data retrieval module: retrieves indicator data and its pre-associated grouped data according to the ship's target function, and calculates the ship business display results based on the indicator data and pre-associated grouped data;

[0010] Data sharing and storage module: Establish a data platform shared by different functional modules of the ship, calculate the correlation index between different types of data based on the data vertical correlation model, and use knowledge graph to associate and store data with correlation index greater than the threshold.

[0011] In a preferred embodiment, the different functional modules of the ship include any one or more of the following: ship management module, electronic chart module, ship monitoring module, security early warning module, energy management module, real-time route planning module, fault early warning module, spare parts management module, communication management module, and firewall module.

[0012] In a preferred embodiment, the indicator data refers to data that has a direct causal relationship with the ship's functional modules, including any one or a combination of ship monitoring data, ship navigation data, ship engine data, ship energy data, ship fault data, ship spare parts management data, electronic chart data, fleet management data, and communication data.

[0013] In a preferred embodiment, the step of calculating the correlation index of vertical domain data based on data similarity and / or data temporal continuity and / or data causal correlation includes the following steps:

[0014] Calculate the data similarity index based on the similarity of data types and / or the similarity of data values;

[0015] Calculate the time continuity index of data based on the consistency of data generation time and / or the connection relationship of data generation time;

[0016] Calculate the causal correlation index of the data based on the causal relationship and / or the mutual influence between the data;

[0017] Calculate the correlation index of vertical domain data based on data similarity index, / or data time continuity index, and / or data causal correlation index.

[0018] In a preferred embodiment, the heterogeneous communication network includes any one or a combination of satellite communication networks, offshore base station communication networks, and port 5G communication networks.

[0019] In a preferred embodiment, the pre-association grouping of sensor data based on the data vertical correlation model includes:

[0020] The data acquired by each edge processor on the ship are grouped horizontally according to sensor type.

[0021] The correlation index between data within a type group and data within other type groups at the same time is calculated based on the data vertical correlation model.

[0022] Data with correlation indicators greater than a preset threshold are grouped as vertical correlation groups;

[0023] Pre-associated groups are obtained based on horizontal type grouping and vertical correlation grouping.

[0024] In a preferred embodiment, the calculation of the ship operation display results based on indicator data and pre-associative grouping data includes:

[0025] Preliminary results of ship operations are calculated based on the relationship between indicator data and preset indicator thresholds.

[0026] Calculate the stability of changes in ship business data based on the amount of data change within the horizontal type groups in the pre-association grouping;

[0027] Calculate the deviation of ship business data based on the deviation value of the data within the vertical association group in the pre-association group;

[0028] Calculate the ship operation correction value based on the stability of changes in ship operation data and / or the deviation of ship operation data;

[0029] The ship operation display results are calculated based on the preliminary display results and the ship operation correction values.

[0030] According to another embodiment of the present invention, a method for vertical data correlation in an intelligent ship integrated control system is provided, comprising:

[0031] Identify indicator data for different functional modules of a ship;

[0032] Calculate the correlation index of vertical domain data based on data similarity and / or data temporal continuity and / or data causal correlation, and establish a data vertical correlation model accordingly;

[0033] Based on the data vertical association model, the correlation index between different types of data is calculated, and knowledge graphs are used to associate and store data with correlation indexes greater than the threshold.

[0034] The collected data is pre-associated and grouped according to the data vertical association model;

[0035] Based on the ship's target function call indicator data and its pre-associated group data, calculate the ship's business display results.

[0036] According to another embodiment of the present invention, a computer-readable storage medium is provided that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute a method for vertical data association of an integrated control system for intelligent ships.

[0037] According to another embodiment of the present invention, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement a method for vertical data association in an intelligent ship integrated control system.

[0038] The advantages of the intelligent ship integrated control system, data vertical correlation method, storage medium, and electronic equipment of the present invention are:

[0039] (1) Calculate the correlation index of vertical domain data based on the similarity of data and / or the time continuity of data and / or the causal correlation of data, and establish a data vertical correlation model based on this. Compared with the traditional technical solution for ship data processing, it can effectively associate massive messy data according to different functional modules, which is convenient to break data silos and establish data management between different functional modules, thereby facilitating the subsequent improvement of the speed of data structured processing and reducing data processing latency.

[0040] (2) The data acquired by each edge processor of the ship are divided into horizontal type groups according to the sensor type and the correlation index is calculated according to the data vertical correlation model and then divided into vertical correlation groups. Compared with the traditional intelligent ship data acquisition technology, it can effectively improve the ship's ability and computing efficiency to process massive data, and improve the timeliness of data query and data analysis.

[0041] (3) Calculate the stability of changes in ship business data based on the horizontal type grouping in the pre-association grouping, calculate the deviation of ship business data based on the vertical association grouping in the pre-association grouping, calculate the ship business correction value based on the stability of changes in ship business data and / or the deviation of ship business data, and calculate the ship business display result based on this. Compared with the traditional intelligent ship technology solution, it can effectively reduce the amount of data calculation, improve the data processing speed, and thus improve the timeliness of data analysis and result display. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the structure of the intelligent ship integrated control system according to an embodiment of the present invention;

[0043] Figure 2This is a flowchart illustrating how to calculate the correlation index of vertical domain data based on data similarity and / or data temporal continuity and / or data causal correlation, according to an embodiment of the present invention.

[0044] Figure 3 This is a flowchart illustrating the pre-association grouping of sensor data based on a data vertical correlation model, according to an embodiment of the present invention.

[0045] Figure 4 This is a flowchart illustrating the calculation of ship operation display results based on indicator data and pre-associative grouping data according to an embodiment of the present invention;

[0046] Figure 5 This is a flowchart of a data vertical correlation method for an intelligent ship integrated control system according to an embodiment of the present invention;

[0047] Figure 6 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0048] The present invention will now be described in detail with reference to specific embodiments. These embodiments will help those skilled in the art to further understand the invention, but do not limit the invention in any way. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all fall within the protection scope of the present invention.

[0049] According to an embodiment of the present invention, an intelligent ship integrated control system is provided, the structural schematic diagram of which is shown below. Figure 1 As shown, it includes:

[0050] Data correlation analysis module: Identify indicator data of different functional modules of the ship, calculate the correlation index of vertical domain data based on data similarity and / or data time continuity and / or data causal correlation, and establish a data vertical correlation model accordingly;

[0051] The data acquisition module based on data correlation preprocessing: It uses heterogeneous communication network fusion technology to collect sensor data deployed on the ship, and performs pre-correlation grouping of sensor data based on the data vertical correlation model;

[0052] Ship business data retrieval module: retrieves indicator data and its pre-associated grouped data according to the ship's target function, and calculates the ship business display results based on the indicator data and pre-associated grouped data;

[0053] Data sharing and storage module: Establish a data platform shared by different functional modules of the ship, calculate the correlation index between different types of data based on the data vertical correlation model, and use knowledge graph to associate and store data with correlation index greater than the threshold.

[0054] In a preferred embodiment, the different functional modules of the ship include any one or more combinations of a ship management module, an electronic chart module, a ship monitoring module, a security early warning module, an energy management module, a real-time route planning module, a fault early warning module, a spare parts management module, a communication management module, and a firewall module. In this embodiment, depending on the usage scenario of the intelligent ship, the ship functional modules include, but are not limited to, a ship management module, an electronic chart module, a ship monitoring module, a security early warning module, an energy management module, a real-time route planning module, a fault early warning module, a spare parts management module, a communication management module, and a firewall module.

[0055] In a preferred embodiment, the indicator data refers to data that has a direct causal relationship with the ship's functional modules, including any one or a combination of ship monitoring data, ship navigation data, ship engine data, ship energy data, ship fault data, ship spare parts management data, electronic chart data, fleet management data, and communication data. In this embodiment, each ship functional module has indicator data that has a direct causal relationship with it. The indicator data may be one or more, and the indicator data between different functional modules may be the same or different. For example, the ship management module is a functional module that manages and monitors the ship's navigation status, navigation data, and position, with its key data including ship navigation data, ship position data, and electronic charts; the electronic chart module is a functional module that displays the ship's position and status on electronic charts, with its key data including electronic chart data and real-time ship position data; the ship monitoring module is a functional module that performs real-time monitoring of various locations in the ship's hold and analyzes personnel behavior, with its key data including CCTV monitoring data and personnel sensor data at various locations on the ship; the security early warning module is a functional module that identifies security anomalies based on ship monitoring and personnel behavior and issues early warnings, with its key data including CCTV monitoring data and personnel sensor data at various locations on the ship; and the energy management module manages the ship's energy... The system includes several functional modules: a remaining capacity management module for optimizing energy consumption, with key data including electricity consumption, fuel consumption, and other energy usage data; a real-time route planning module for calculating and displaying the ship's route, with key data including the ship's real-time position, electronic charts, and climate data; a fault warning module for identifying and issuing warnings about potential equipment malfunctions, with key data including the ship's equipment operating parameters; a spare parts management module for monitoring remaining spare parts, with key data including spare parts inventory; a communication management module for managing internet access on board, with key data including data on network traffic and satellite signals; and a firewall module for ensuring the ship's network security, with key data including data on network attacks.

[0056] In a preferred embodiment, the process of calculating the correlation index of vertical domain data based on data similarity and / or data temporal continuity and / or data causal correlation is illustrated in the flowchart below. Figure 2 As shown, the steps include:

[0057] Step S011: Calculate the data similarity index based on the similarity of data types and / or the similarity of data values;

[0058] Step S012: Calculate the time continuity index of the data based on the consistency of the data generation time and / or the connection relationship of the data generation time;

[0059] Step S013: Calculate the causal correlation index of the data based on the causal relationship of the data and / or the mutual influence between the data;

[0060] Step S014: Calculate the correlation index of vertical domain data based on the data similarity index and / or the data time continuity index and / or the data causal correlation index.

[0061] In this embodiment, the calculation of the data similarity index based on the similarity of data types and / or the similarity of data values ​​can be any one of the following: calculating the data similarity index based on the positive correlation between the similarity of data types and the data similarity index; calculating the data similarity index based on the positive correlation between the similarity of data values ​​and the data similarity index; or calculating the data similarity index based on the positive correlation between the similarity of data types and the similarity of data values ​​and the data similarity index. The data similarity index is represented by the variable x.

[0062] The calculation of the data time continuity index based on the consistency of data generation time and / or the connection relationship of data generation time can be achieved by any one of the following: calculating the data time continuity index based on the positive correlation between the consistency of data generation time (the smaller the time difference between data generation times, the greater the consistency); calculating the data time continuity index based on the positive correlation between the connection degree of data generation time (calculated based on the chronological interval of data generation time, the smaller the interval, the greater the connection) and the data time continuity index; or calculating the data time continuity index based on the positive correlation between the consistency of data generation time, the connection degree of data generation time, and the data time continuity index. The data time continuity index is represented by the variable y.

[0063] The calculation of the causal correlation index of data based on the causal relationship of data and / or the mutual influence between data can be any one of the following: calculating the causal correlation index of data based on the positive correlation between the degree of causal correlation of data (calculated from the relevant change caused by the change in a unit of data) and the causal correlation index of data; calculating the causal correlation index of data based on the positive correlation between the degree of mutual influence between data (calculated from the sum of the relevant changes between data per unit time) and the causal correlation index of data; or calculating the causal correlation index of data based on the positive correlation between the degree of causal correlation of data and the degree of mutual influence between data and the causal correlation index of data. The causal correlation index of data is represented by the variable z.

[0064] The calculation of the correlation index of vertical domain data based on the data similarity index and / or the data time continuity index and / or the data causal correlation index is obtained by calculating the positive correlation between the correlation index of vertical domain data and the data similarity index and / or the data time continuity index and / or the data causal correlation index. The correlation index of vertical domain data is represented by the variable p.

[0065] Examples A1 to A7 illustrate different implementation methods for calculating the relevance index of vertical domain data, as follows:

[0066] Example A1: Calculate the correlation index of vertical domain data based on the positive correlation between the similarity index of data and the correlation index of vertical domain data.

[0067] Specifically, a data similarity index x is calculated based on the similarity of data types and / or the similarity of data values; a correlation index p of the vertical domain data is calculated based on the positive correlation between the data similarity index x and the correlation index of the vertical domain data. In a preferred embodiment, the correlation index p of the vertical domain data is calculated as p = w1·x. w2 +w3, where w1 (w1>0), w2 (w2>0), and w3 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain instance are both CCTV data, and their data similarity is 1 (normalized). Based on the positive correlation between the data similarity index and the data similarity index, the data similarity index x=1 (the pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w1=1, w2=1, and w3=0, then the vertical domain data correlation index p=w1·x is calculated. w2 +w3=1×1+0=1.

[0068] Example A2: Calculate the correlation index of vertical domain data based on the positive correlation between the time continuity index of data and the correlation index of vertical domain data.

[0069] Specifically, a time continuity index y is calculated based on the consistency of data generation time and / or the connection relationship of data generation time; a correlation index p of vertical domain data is calculated based on the positive correlation between the time continuity index y and the correlation index of vertical domain data. In a preferred embodiment, the correlation index p of vertical domain data is calculated as p = w4·y. w5 +w6, where w4 (w4>0), w5 (w5>0), and w6 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain period have a data generation time difference of 2 seconds. Normalized according to a preset time difference threshold, the consistency of generation time is 0.9. Based on its positive correlation with the data's time continuity index, the data's time continuity index y=0.9 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w4=1, w5=1, and w6=0. Therefore, the correlation index p=w4·y for the vertical domain data is calculated. w5 +w6=1×0.9+0=0.9.

[0070] Example A3: Calculate the correlation index of vertical domain data based on the positive correlation between the causal correlation index of the data and the correlation index of the vertical domain data.

[0071] Specifically, a causal correlation index z is calculated based on the causal relationships and / or the mutual influence between data; and a correlation index p is calculated based on the positive correlation between the causal correlation index z and the correlation index of vertical domain data. In a preferred embodiment, the correlation index p of vertical domain data is calculated as p = w7·z. w8 +w9, where w7 (w7>0), w8 (w8>0), and w9 are pre-trained calculated coefficients. In this embodiment, for two sets of data collected in a certain instance, a unit change in one set of data leads to a correlation change of 0.8 in the other set of data, resulting in a causal correlation degree of 0.8. Based on its positive correlation with the causal correlation index of the data, the causal correlation index z=0.8 (the pre-trained calculated coefficient is 1) is calculated. The pre-trained calculated coefficients w7=1, w8=1, and w9=0, so the correlation index of the vertical domain data is calculated as p=w7·z. w8 +w9=1×0.8+0=0.8.

[0072] Example A4: Calculate the correlation index of vertical domain data based on the positive correlation between the data similarity index, the data time continuity index and the correlation index of vertical domain data.

[0073] Specifically, a data similarity index x is calculated based on the similarity of data types and / or the similarity of data values; a data temporal continuity index y is calculated based on the consistency of data generation time and / or the connection relationship of data generation time; and a vertical domain data correlation index p is calculated based on the positive correlation between the data similarity index x, the data temporal continuity index y, and the correlation index of vertical domain data. In a preferred embodiment, the vertical domain data correlation index p is calculated as p = w10·x. w11 +w12·y w13 +w14, where w10 (w10>0), w11 (w11>0), w12 (w12>0), w13 (w13>0), and w14 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain instance are both CCTV data, and their data similarity is 1 (normalized). Based on the positive correlation between the data similarity index and the data similarity index, the data similarity index x=1 (pre-trained calculation coefficient is 1). The data generation time difference is 2 seconds. Based on the preset time difference threshold, the generation time consistency is normalized to 0.9. Based on the positive correlation between the data and the data time continuity index, the data time continuity index y=0.9 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w10=0.6, w11=1, w12=0.4, w13=1, and w14=0, then the vertical domain data correlation index p=w10·x is calculated. w11 +w12·y w13 +w14=0.6×1+0.4×0.9+0=0.96. In another preferred embodiment, the correlation index p=w15·x for vertical domain data is calculated. w16 ·y w17 +w18, where w15 (w15>0), w16 (w16>0), w17 (w17>0), and w18 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain instance are both CCTV data, and their data similarity is 1 (normalized). Based on the positive correlation between the data similarity index and the data similarity index, the data similarity index x=1 (pre-trained calculation coefficient is 1). The data generation time difference is 2 seconds. Based on the preset time difference threshold, the generation time consistency is normalized to 0.9. Based on the positive correlation between the data and the data time continuity index, the data time continuity index y=0.9 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w15=1.06, w16=1, w17=1, and w18=0. Then, the vertical domain data correlation index p=w15·x is calculated. w16 ·y w17 +w18=1.06×1×0.9+0=0.954.

[0074] Example A5: Calculate the correlation index of vertical domain data based on the positive correlation between the data similarity index and the causal correlation index of the data and the correlation index of vertical domain data.

[0075] Specifically, a data similarity index x is calculated based on the similarity of data types and / or the similarity of data values; a causal correlation index z is calculated based on the causal relationship of the data and / or the mutual influence between the data; and a correlation index p of the vertical domain data is calculated based on the positive correlation between the data similarity index x, the data causal correlation index z, and the correlation index of the vertical domain data. In a preferred embodiment, the correlation index p of the vertical domain data is calculated as p = w19·x. w20 +w21·z w22 +w23, where w19 (w19>0), w20 (w20>0), w21 (w21>0), w22 (w22>0), and w23 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain instance are both CCTV data, and their data similarity is 1 (normalized). Based on the positive correlation between the similarity index and the data, the data similarity index x=1 (pre-trained calculation coefficient is 1). The unit change in one set of data brings a related change of 0.8 to the other set of data, resulting in a causal correlation of 0.8. Based on the positive correlation between the causal correlation index and the data, the causal correlation index z=0.8 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w19=0.6, w20=1, w21=0.4, w22=1, and w23=0, then the correlation index p of the vertical domain data is calculated as p=w19·x. w20 +w21·z w22 +w23=0.6×1+0.4×0.8+0=0.92. In another preferred embodiment, the correlation index p=w24·x for vertical domain data is calculated. w25 ·z w26+w27, where w24 (w24>0), w25 (w25>0), w26 (w26>0), and w27 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain instance are both CCTV data, and their data similarity is 1 (normalized). Based on the positive correlation between the data and the data similarity index, the data similarity index x=1 (pre-trained calculation coefficient is 1). The unit change in one set of data brings a related change of 0.8 to the other set of data, resulting in a causal correlation of 0.8. Based on the positive correlation between the data and the causal correlation index, the data causal correlation index z=0.8 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w24=1.15, w25=1, w26=1, and w27=0. Therefore, the correlation index p=w24·x for the vertical domain data is calculated. w25 ·z w26 +w27=1.15×1×0.8+0=0.92.

[0076] Example A6: Calculate the correlation index of vertical domain data based on the positive correlation between the time continuity index and the causal correlation index of the data and the correlation index of vertical domain data.

[0077] Specifically, the temporal continuity index y is calculated based on the consistency of data generation time and / or the connection between data generation times; the causal correlation index z is calculated based on the causal relationship of data and / or the mutual influence between data; and the correlation index p of vertical domain data is calculated based on the positive correlation between the temporal continuity index y, the causal correlation index z, and the correlation index of vertical domain data. In a preferred embodiment, the correlation index p of vertical domain data is calculated as p = w²⁸·y. w29 +w30·z w31+w32, where w28 (w28>0), w29 (w29>0), w30 (w30>0), w31 (w31>0), and w32 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain period have a data generation time difference of 2 seconds. Normalized according to a preset time difference threshold, the consistency of generation time is 0.9. Based on its positive correlation with the data's time continuity index, the data's time continuity index y=0.9 (pre-trained calculation coefficient is 1). The change in one set of data by a unit brings about a related change of 0.8 in the other set, resulting in a causal correlation of 0.8. Based on its positive correlation with the data's causal correlation index, the data's causal correlation index z=0.8 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w28=0.6, w29=1, w30=0.4, w31=1, and w32=0.1 are used to calculate the vertical domain data correlation index p=w28·y. w29 +w30·z w31 +w32=0.6×0.9+0.4×0.8+0.1=0.96. In another preferred embodiment, the correlation index p=w33·y for vertical domain data is calculated. w34 ·z w35 +w36, where w33 (w33>0), w34 (w34>0), w35 (w35>0), and w36 are pre-trained calculation coefficients. In this embodiment, two sets of data collected in a certain period have a data generation time difference of 2 seconds. Normalized according to a preset time difference threshold, the consistency of generation time is 0.9. Based on its positive correlation with the data's time continuity index, the data's time continuity index y=0.9 (pre-trained calculation coefficient is 1). The unit change in one set of data leads to a related change of 0.8 in the other set, resulting in a causal correlation of 0.8. Based on its positive correlation with the data's causal correlation index z=0.8 (pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w33=1.34, w34=1, w35=1, and w36=0. Therefore, the correlation index p=w33·y for the vertical domain data is calculated. w34 ·z w35 +w36=1.34×0.9×0.8+0=0.96.

[0078] Example A7: Calculate the correlation index of vertical domain data based on the positive correlation between the data similarity index, the data time continuity index, the data causal correlation index and the correlation index of vertical domain data.

[0079] Specifically, a data similarity index x is calculated based on the similarity of data types and / or the similarity of data values; a data temporal continuity index y is calculated based on the consistency of data generation time and / or the connection relationship of data generation time; a data causal correlation index z is calculated based on the causal relationship of data and / or the mutual influence between data; and a vertical domain data correlation index p is calculated based on the positive correlation between the data similarity index x, the data temporal continuity index y, the data causal correlation index z, and the correlation index of vertical domain data. In a preferred embodiment, the vertical domain data correlation index p is calculated as p = w37·x. w38 +w39·y w40 +w41·z w42 +w43, where w37 (w37>0), w38 (w38>0), w39 (w39>0), w40 (w40>0), w41 (w41>0), w42 (w42>0), and w43 are calculated coefficients obtained through prior training. In this embodiment, two sets of data collected in a certain instance are both CCTV data, with a data similarity of 1 (normalized). Based on the positive correlation between the data similarity index and the data similarity index, the data similarity index x=1 (the pre-trained calculation coefficient is 1). The time difference between the data generation is 2 seconds. Normalized according to a preset time difference threshold, the consistency of generation time is 0.9. Based on the positive correlation between the data and the data time continuity index, the data time continuity index y=0.9 (the pre-trained calculation coefficient is 1). The unit change in one set of data leads to a related change of 0.8 in the other set of data, resulting in a causal correlation of 0.8. Based on the positive correlation between the data and the data causal correlation index, the data causal correlation index z=0.8 (the pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w37=0.5, w38=1, w39=0.3, w40=1, w41=0.2, w42=1, w43=0. The vertical domain data correlation index p=w37·x is calculated. w38 +w39·y w40 +w41·z w42 +w43=0.5×1+0.3×0.9+0.2×0.8+0=0.93. In another preferred embodiment, the correlation index p=w44·x for vertical domain data is calculated. w45 ·y w46 ·z w47+w48, where w44 (w44>0), w45 (w45>0), w46 (w46>0), w47 (w47>0), and w48 are calculated coefficients obtained through prior training. In this embodiment, two sets of data collected in a certain instance are both CCTV data, with a data similarity of 1 (normalized). Based on the positive correlation between the data similarity index and the data similarity index, the data similarity index x=1 (the pre-trained calculation coefficient is 1). The time difference between the data generation is 2 seconds. Normalized according to a preset time difference threshold, the consistency of generation time is 0.9. Based on the positive correlation between the data and the data time continuity index, the data time continuity index y=0.9 (the pre-trained calculation coefficient is 1). The unit change in one set of data leads to a related change of 0.8 in the other set of data, resulting in a causal correlation of 0.8. Based on the positive correlation between the data and the data causal correlation index, the data causal correlation index z=0.8 (the pre-trained calculation coefficient is 1). The pre-trained calculation coefficients w44=1.29, w45=1, w46=1, w47=1, w48=0. The correlation index p=w44·x for the vertical domain data is calculated. w45 ·y w46 ·z w47 +w48=1.29×1×0.9×0.8+0=0.93.

[0080] The correlation index of vertical domain data for any two sets of data can be calculated according to the method described in any one of the embodiments A1 to A7.

[0081] In a preferred embodiment, the heterogeneous communication network includes any one or a combination of satellite communication networks, offshore base station communication networks, and port 5G communication networks.

[0082] In a preferred embodiment, the pre-association grouping of sensor data based on the data vertical correlation model is illustrated in the flowchart below. Figure 3 As shown, it includes:

[0083] Step S021: Divide the data acquired by each edge processor of the ship into horizontal type groups according to the sensor type;

[0084] Step S022: Calculate the correlation index between data within a type group and data within other type groups at the same time based on the data vertical correlation model;

[0085] Step S023: Data with correlation indicators greater than a preset threshold are grouped as vertical correlation groups;

[0086] Step S024: Obtain pre-associated groups based on horizontal type grouping and vertical correlation grouping.

[0087] In this embodiment, the data acquired by each edge processor of the ship are grouped horizontally according to the sensor type, such as location data type grouping, time delay data type grouping, ship operation status data type grouping, ship equipment status data grouping, etc.

[0088] According to the method for calculating the correlation index of vertical domain data (i.e., the data vertical correlation model) described in any one of embodiments A1 to A7, the correlation index of data within a type group and data within other type groups at the same time is calculated, and data with a correlation index greater than a preset threshold are taken as vertical correlation groups.

[0089] The data acquired by each edge processor of the ship are pre-associated groups in the form of vertical and horizontal grouping.

[0090] In a preferred embodiment, the process of calculating the ship business display results based on indicator data and pre-associative grouping data is illustrated in the flowchart below. Figure 4 As shown, it includes:

[0091] Step S031: Calculate the preliminary display results of ship operations based on the relationship between the indicator data and the preset indicator thresholds;

[0092] Step S032: Calculate the stability of changes in ship business data based on the data changes within the horizontal type groups in the pre-association grouping;

[0093] Step S033: Calculate the deviation degree of ship business data based on the deviation value of the data within the vertical association group in the pre-association group;

[0094] Step S034: Calculate the ship operation correction value based on the stability of changes in ship operation data and / or the deviation of ship operation data;

[0095] Step S035: Calculate the ship service display results based on the preliminary display results and the ship service correction values.

[0096] In this embodiment, the preliminary display result of ship business is calculated based on the relationship between indicator data and preset indicator thresholds. The indicator data threshold range corresponding to each ship functional module and the business result corresponding to each indicator threshold range are determined in advance, and the preliminary display result of ship business is obtained accordingly. The preliminary display result of ship business is represented by the variable m.

[0097] The step of calculating the stability of changes in ship business data based on horizontal type grouping in pre-association grouping involves obtaining the amount of data change within the same horizontal type grouping as the current business indicator data in the pre-association grouping (the amount of data change is calculated based on any one or more of the average change, data variance, or data standard deviation within a preset time period) and calculating the stability of changes in ship business data based on the negative correlation between the amount of data change within the horizontal type grouping and the stability of changes in ship business data. The stability of changes in ship business data is represented by variable a.

[0098] The process of calculating the ship business data deviation based on the deviation value of the data in the vertical association group in the pre-association group involves obtaining the data deviation value in the same vertical association group as the current business indicator data in the pre-association group (the data deviation value is calculated based on the average difference between the data and the preset data threshold within a preset time period) and calculating the ship business data deviation based on the positive correlation between the data deviation value in the vertical association group and the ship business data deviation. The ship business data deviation is represented by the variable b.

[0099] The calculation of the ship business correction value based on the stability of changes in ship business data and / or the deviation of ship business data is obtained by calculating the ship business correction value based on the correlation between the ship business correction value and the stability of changes in ship business data and / or the deviation of ship business data. The ship business correction value is represented by the variable c.

[0100] Examples B1-B3 illustrate different implementation methods for calculating ship operational correction values, as follows:

[0101] Example B1: Calculate the ship business correction value based on the negative correlation between the stability of changes in ship business data and the ship business correction value.

[0102] Specifically, the data change amount within the same horizontal type group as the current business indicator data in the pre-association group is obtained, and the change stability 'a' of the ship business data is calculated based on its negative correlation with the change stability of the ship business data; the ship business correction value 'c' is calculated based on the negative correlation between the change stability 'a' of the ship business data and the ship business correction value. In a preferred embodiment, the ship business correction value 'c' is calculated as c = u1·a. u2+u3, where u1, u2 (u1·u2<0), and u3 are pre-trained calculation coefficients. For example, if the ship operation is based on electronic charts and the indicator data is also based on electronic chart data, the data within its horizontal type grouping includes ship latitude and longitude data, satellite climate data, etc. The average change in ship latitude and longitude data within the 5 minutes before the current indicator data occurs is calculated as 0.2 (normalized according to the preset latitude and longitude data change threshold). Based on its negative correlation with the stability a of the ship operation data, the stability a of the ship operation data is calculated as a = 0.08 × 1 / 0.2 = 0.4 (the pre-trained calculation coefficient is 0.08). The pre-trained calculation coefficients u1 = 0.32, u2 = -1, and u3 = 0. Then, the ship operation correction value c = u1·a is calculated. u2 +u3=0.32×0.4 -1 +0=0.8.

[0103] Example A2: Calculate the ship business correction value based on the positive correlation between the deviation of ship business data and the ship business correction value.

[0104] Specifically, the data deviation value (calculated based on the average difference between the data and a preset data threshold within a preset time period) within the same vertical correlation group as the current business indicator data is obtained. The ship business data deviation degree b is calculated based on the positive correlation between the data deviation value within the vertical correlation group and the ship business data deviation degree. The ship business correction value c is calculated based on the positive correlation between the ship business data deviation degree b and the ship business correction value. In a preferred embodiment, the ship business correction value c = u4·b is calculated. u5 +u6, where u4 (u4>0), u5 (u5>0), and u6 are pre-trained calculation coefficients. In this embodiment, if the ship operation is electronic chart and the indicator data is electronic chart data, the data within its horizontal type group includes ship monitoring data, ship navigation data, etc. The data deviation value is calculated as 0.9 based on the average difference between the ship navigation data and the preset navigation data threshold within 5 minutes before the occurrence of the current indicator data (normalized according to the ship navigation data threshold range). Based on its positive correlation with the ship operation data deviation degree b, the ship operation data deviation degree b = 0.9 (the pre-trained calculation coefficient is 1). The pre-trained calculation coefficients u4 = 1, u5 = 1, and u6 = 0, then the ship operation correction value c = u4·b is calculated. u5 +u6=1×0.9+0=0.9.

[0105] Example A3: Calculate the ship business correction value based on the negative correlation between the stability of changes in ship business data and the ship business correction value, and the positive correlation between the deviation of ship business data and the ship business correction value.

[0106] Specifically, the data change amount within the same horizontal type group as the current business indicator data in the pre-association group is obtained, and the stability of the ship business data change is calculated based on its negative correlation with the stability of the ship business data change. The data deviation value (calculated based on the average difference between the data and a preset data threshold within a preset time period) within the same vertical association group as the current business indicator data in the pre-association group is obtained, and the ship business data deviation degree is calculated based on the positive correlation between the data deviation value within the vertical association group and the ship business data deviation degree. The ship business correction value is calculated based on the negative correlation between the stability of the ship business data change 'a' and the ship business correction value, and the positive correlation between the ship business data deviation degree 'b' and the ship business correction value. In a preferred embodiment, the ship business correction value c = u7·a is calculated. u8 +u9·b u10 +u11, where u7 (u7>0), u8 (u8<0), u9 (u9>0), u10 (u10>0), and u11 are pre-trained calculation coefficients. For example, if shipping operations are based on electronic charts and the indicator data is electronic chart data, the data within its horizontal type grouping includes ship latitude and longitude data, satellite climate data, etc. The average change in ship latitude and longitude data within the 5 minutes before the current indicator data occurs is calculated as 0.2 (normalized according to a preset latitude and longitude data change threshold). Based on its negative correlation with the stability 'a' of shipping operations data, the stability 'a' of shipping operations data is calculated as a = 0.08 × 1 / 0.2 = 0.4 (the pre-trained calculation coefficient is 0.08); the data within its horizontal type grouping... This includes ship monitoring data and ship navigation data. The data deviation value is calculated as 0.9 (normalized according to the ship navigation data threshold range) based on the average difference between the ship navigation data within 5 minutes prior to the occurrence of the current indicator data. The ship business data deviation value b is calculated as 0.9 (with a pre-trained calculation coefficient of 1) based on its positive correlation with the deviation value b. The pre-trained calculation coefficients u7=0.128, u8=-1, u9=0.6, u10=1, u11=0. Therefore, the ship business correction value c is calculated as c=u7·a. u8 +u9·b u10 +u11=0.128×0.4 -1 +0.6×0.9+0=0.86. In another preferred embodiment, the ship operation correction value c=u12·a is calculated. u13 ·b u14+u15, where u12 (u12>0), u13 (u13<0), u14 (u14>0), and u15 are pre-trained calculation coefficients. For example, if shipping operations are based on electronic charts and the indicator data is electronic chart data, the data within its horizontal type grouping includes ship latitude and longitude data, satellite climate data, etc. The average change in ship latitude and longitude data within 5 minutes before the current indicator data occurs is calculated as 0.2 (normalized according to a preset latitude and longitude data change threshold). Based on its negative correlation with the stability 'a' of shipping operations data, the stability 'a' of shipping operations data is calculated as a = 0.08 × 1 / 0.2 = 0.4 (the pre-trained calculation coefficient is 0.08); the data within its horizontal type grouping... The data includes ship monitoring data and ship navigation data. The data deviation value is calculated as 0.9 (normalized according to the ship navigation data threshold range) based on the average difference between the ship navigation data within the 5 minutes prior to the occurrence of the current indicator data. The ship operational data deviation value b is calculated as 0.9 (with a pre-trained coefficient of 1) based on its positive correlation with the deviation value b. The pre-trained coefficients u12=0.38, u13=-1, u14=1, u15=0. Therefore, the ship operational correction value c is calculated as c=u12·a. u13 ·b u14 +u15=0.38×0.4 -1 ×0.9+0=0.855.

[0107] The process of calculating the ship service display result based on the preliminary ship service display result m and the ship service correction value is to add the ship service correction value to the preliminary ship service display result m to obtain the final ship service display result, which is represented by the variable n.

[0108] If the ship service correction value c is obtained according to any one of embodiments B1 to B3, then the final ship service display result n = m + u16·c u17 Or n = u18·m·c, where u16, u17, and u18 are calculated coefficients obtained through prior training.

[0109] According to another embodiment of the present invention, a method for vertical data association in an intelligent ship integrated control system is provided, the flowchart of which is shown below. Figure 5 As shown, it includes:

[0110] Step S0: Identify the indicator data of different functional modules of the ship;

[0111] Step S1: Calculate the correlation index of vertical domain data based on the similarity of the data and / or the temporal continuity of the data and / or the causal correlation of the data, and establish a vertical data correlation model accordingly.

[0112] Step S2: Calculate the correlation index between different types of data based on the data vertical association model, and use knowledge graph to associate and store data with correlation index greater than the threshold;

[0113] Step S3: Pre-associate and group the collected data according to the data vertical association model;

[0114] Step S4: Calculate the ship's business display results based on the ship's target function call indicator data and its pre-association grouped data.

[0115] In this embodiment, indicator data of different functional modules of the ship are identified; a data vertical association model is established according to any one of embodiments A1 to A7; the correlation index between different data is calculated according to the data vertical association model, and a knowledge graph is used to associate and store data with correlation index greater than a threshold; the collected data is pre-associated and grouped according to the data vertical association model; based on the ship's target function call indicator data and its pre-associated grouped data, the preliminary display result of ship business is calculated according to the relationship between the indicator data and the preset indicator threshold; the ship business correction value is calculated according to any one of embodiments B1 to B3, and the ship business display result is calculated based on the preliminary display result of ship business and the ship business correction value.

[0116] According to another embodiment of the present invention, a computer-readable storage medium is provided that stores a computer program for electronic data exchange, wherein the computer program causes a computer to execute a method for vertical data association of an integrated control system for intelligent ships.

[0117] According to another embodiment of the present invention, an electronic device is provided, the structural schematic diagram of which is shown below. Figure 6 As shown, it includes a memory, a processor, and a computer program stored in the memory. The processor executes the computer program to implement a method for vertical data association in an intelligent ship integrated control system.

[0118] Of course, those skilled in the art should recognize that the above embodiments are only used to illustrate the present invention and are not intended to limit the present invention. Any changes or modifications to the above embodiments that are within the scope of the present invention will fall within the protection scope of the present invention.

Claims

1. An intelligent ship integrated control system, characterized by, The application relates to a ship data sharing and display method, which comprises the following steps: a data correlation analysis module: identifying indicative data of different functional modules of a ship, calculating a correlation index of vertical field data according to the similarity of the data and / or the time continuity of the data and / or the causal correlation of the data, and establishing a data vertical correlation model according to the correlation index; the indicative data refers to data having a direct causal corresponding relationship with the functional modules of the ship, and the indicative data comprises any one or a combination of ship monitoring data, ship driving data, ship engine data, ship energy data, ship fault data, ship spare part management data, electronic chart data, fleet management data and communication data; the correlation index of the vertical field data is calculated according to the similarity of the data and / or the time continuity of the data and / or the causal correlation of the data, and comprises the following steps: calculating a similarity index of the data according to the similarity of the data types and / or the similarity of the data values; calculating a time continuity index of the data according to the consistency of the data generation time and / or the connection relationship of the data generation time; calculating a causal correlation index of the data according to the causal relationship of the data and / or the mutual influence between the data; and calculating the correlation index of the vertical field data according to the similarity index of the data and / or the time continuity index of the data and / or the causal correlation index of the data; a data acquisition module based on data correlation preprocessing: sensor data deployed on the ship is acquired by adopting a heterogeneous communication network fusion technology, and the sensor data is pre-associated and grouped based on the data vertical correlation model; the pre-associated grouping of the sensor data based on the data vertical correlation model comprises the following steps: dividing the data acquired by each edge processor of the ship into horizontal type groups according to the sensor types; calculating the correlation index of the data in a type group with the data in other type groups at the same time according to the data vertical correlation model; taking the data with a correlation index greater than a preset threshold as a longitudinal correlation group; and obtaining the pre-associated groups according to the horizontal type groups and the longitudinal correlation group; a ship business data calling module: calling the indicative data and the pre-associated grouped data according to a target function of the ship, and calculating a ship business display result according to the indicative data and the pre-associated grouped data; the calculation of the ship business display result according to the indicative data and the pre-associated grouped data comprises the following steps: calculating a ship business preliminary display result according to the relationship between the indicative data and a preset indicative threshold; calculating the change stability of the ship business data according to the change amount of the data in the horizontal type groups in the pre-associated groups; calculating the deviation degree of the ship business data according to the deviation value of the data in the longitudinal correlation groups in the pre-associated groups; calculating a ship business correction value according to the change stability of the ship business data and / or the deviation degree of the ship business data; and calculating the ship business display result according to the ship business preliminary display result and the ship business correction value; a data sharing and storage module: establishing a data platform shared by different functional modules of the ship, calculating the correlation index between different types of data according to the data vertical correlation model, and correlatively storing the data with a correlation index greater than a threshold by adopting a knowledge graph.

2. The intelligent ship integrated control system of claim 1, wherein, The ship different function modules include any one or more combinations of a ship management module, an electronic chart module, a ship monitoring module, a security and early warning module, an energy management module, a real-time path planning module, a fault early warning module, a spare parts management module, a communication management module, and a firewall module.

3. The intelligent ship integrated control system of claim 1, wherein, The heterogeneous communication network includes any one or more combinations of a satellite communication network, an offshore base station communication network, and a port 5G communication network.

4. A data vertical association method for the intelligent ship integrated control system according to any one of claims 1-3, characterized in that, The method comprises: identifying the indicator data of the ship different function modules; calculating the relevance index of the vertical field data according to the similarity of the data and / or the time continuity of the data and / or the causal correlation of the data and establishing a data vertical association model therefrom; calculating the relevance index between different types of data according to the data vertical association model and storing the data with the relevance index greater than a threshold in association using a knowledge graph; pre-associating and grouping the collected data according to the data vertical association model; calculating the ship business display result based on the indicator data and / or the pre-associated and grouped data according to the ship target function and the indicator data and the pre-associated and grouped data.

5. A computer readable storage medium storing a computer program for electronic data interchange, wherein, The computer program enables a computer to execute the method of claim 4.

6. An electronic device, comprising: A computer program product comprising a memory, a processor, and a computer program stored on the memory, the processor executing the computer program to implement the method of claim 4.

Images