Data consistency verification method and system for reliable decision-making of intelligent ship navigation in inland waterways

Abstract

The present invention relates to the field of communication data verification technology, which solves the technical problem that traditional technologies lack security in the face of data transmission and processing, and in particular to a data consistency verification method and system for trusted decision-making of intelligent ships in inland waters, which is specifically divided into five parts: zero-trust identity authentication and access control, data encryption and communication security, time synchronization and verification mechanism, redundant verification and fusion of multi-source data, and dynamic evaluation of multi-ship trust based on consistency verification results. The present invention realizes that each data interaction between ships and shore bases, ships and ships, and ships and the environment is subject to identity authentication and security review. Combined with time synchronization, multi-source data fusion, redundant verification and anomaly detection, etc., the data consistency and credibility of navigation decisions are ensured, and the navigation safety of inland ships and the system's anti-attack capability are significantly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of communication data verification, and in particular to a data consistency verification method and system for reliable decision-making of intelligent ship navigation of inland waterways. Background Art

[0002] In the intelligent navigation of inland ships controlled by shore-based control, the data transmission and decision-making process between the ship system and the shore-based control center is highly dependent on the collaborative work of various sensors and communication equipment. With the improvement of ship navigation automation and intelligence, the information exchange between ships and shore-based is frequent and complex, which puts higher requirements on the consistency and reliability of data. Especially in inland navigation, due to the influence of waterway environment, ship characteristics and external factors, the intelligent decision-making of ships faces more uncertainties. In this context, ensuring the consistency and credibility of data has become the core issue of the safety, stability and reliability of intelligent navigation systems.

[0003] Traditional data consistency verification methods usually rely on the credibility and integrity of the data source, such as by verifying the accuracy and source of sensor data, or comparing the rationality of data through redundant systems. However, these methods usually ignore the security issues that may be encountered during data transmission and processing. With the increasing complexity of communication networks and system architectures, especially when multiple participants and devices work together, security risks such as malicious attacks, false data injection, and communication tampering are gradually emerging. These problems may not only lead to data errors, but also affect the intelligent decision-making of ships, ultimately endangering navigation safety. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a data consistency verification method and system for trusted decision-making of intelligent inland waterway vessels, which solves the technical problem that traditional technologies lack security in data transmission and processing.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: a data consistency verification method for reliable decision-making of inland waterway intelligent ship, the method comprising the following process:

[0006] Establish zero-trust authentication and access control for all communication nodes to authenticate their identities before participating in data exchange or decision-making processes; the communication nodes include ships, shore-based control systems, and various sensors equipped on ships to obtain various types of ship information, including position, speed, and heading.

[0007] Establish a data communication encryption mechanism based on end-to-end encryption method between all communication nodes during data exchange or decision-making process;

[0008] Use timestamps to establish a time synchronization and verification mechanism for all data during data exchange or decision-making;

[0009] Based on the Kalman filter correction method, the multi-source data of the communication nodes in the data exchange or decision-making process are redundancy checked and integrated to obtain consistency test results;

[0010] Based on the consistency test results, a dynamic evaluation of the trust between multiple ships' collaboration is performed, including the trust based on historical behavior and the comprehensive trust based on external verification.

[0011] Further, the zero-trust authentication and access control for performing identity authentication includes zero-trust authentication, access control, and making access decisions;

[0012] The zero-trust authentication includes:

[0013] Communication nodes hold independent and unique digital certificates to verify their identities and use public key infrastructure for authentication;

[0014] The access control includes role-based access control and policy-based access control, wherein:

[0015] Role-based access control is used to dynamically control access rights according to the permissions of different roles, including ship drivers and shore-based controllers;

[0016] Policy-based access control is used to determine data access rights through access control policies, ensuring that only authorized users can access specific data or perform specific operations. Access control policies are determined by predetermined conditions and context information.

[0017] Making access decisions includes:

[0018] Dynamically verify permissions for each request, and make access decisions based on the context and role information of the current request, combining role-based access control and policy-based access control.

[0019] Furthermore, the specific process of making the access decision includes:

[0020] Use policy-based access control to establish access control policies and request context Control decisions for matching situations , the expression is:

[0021] ;

[0022] Adopting control decision Comprehensive trust in each ship Weighted and calculated final decision result , the expression is:

[0023] ;

[0024] In the formula, is the number of data sources, corresponding to Communication nodes;

[0025] Based on decision results Dynamically verify permissions for each request and make access decisions by combining role-based access control and policy-based access control. The expression is:

[0026] ;

[0027] In the formula, It is the permission verification of role-based access control; It is policy verification for policy-based access control; To express a request; Indicates communication nodes.

[0028] Furthermore, the data communication encryption mechanism includes:

[0029] After receiving the data, the recipient verifies the digital signature through the public key or compares the hash value to confirm whether the data has been tampered with, including the data confidentiality verification mechanism and the data integrity verification mechanism. The data integrity verification mechanism includes hash verification and digital signature.

[0030] Furthermore, the time synchronization and verification mechanism includes:

[0031] During data exchange, the timestamp attached to each piece of data is verified. If the timestamp of the data differs from the global standard time, or the order of the timestamps is abnormal, the data has potential problems and is marked as abnormal or invalid.

[0032] Furthermore, obtaining the consistency check result includes the following process:

[0033] Kalman filter data fusion: Use Kalman filter method to fuse multi-source data from multiple sensors to obtain the reference state of the ship ,Right now:

[0034] ;

[0035] In the formula, They are the reference position, reference speed and reference heading of the ship respectively;

[0036] Sensor data collection: Get the real status of the ship from different sensors ,Right now:

[0037] ;

[0038] In the formula, They are the true position, true speed and true heading of the ship respectively;

[0039] Calculate cosine similarity: Calculate cosine similarity for each data ,Right now:

[0040] Calculate the cosine similarity of the position data, that is:

[0041] ;

[0042] Calculate the cosine similarity of the speed data, that is:

[0043] ;

[0044] Calculate the cosine similarity of the heading data, that is:

[0045] ;

[0046] Threshold selection for consistency check: Set the cosine similarity threshold used to determine whether the data is consistent , if the cosine similarity Exceeding the cosine similarity threshold , the data is considered consistent; below the cosine similarity threshold , then it is considered that there is inconsistency, that is, outlier data;

[0047] Outlier data correction: According to the deviation of the current sensor data and the previous state prediction, the outlier data is corrected. The correction formula is:

[0048] ;

[0049] In the formula, is the state prediction of the previous moment; is the Kalman gain; is the observation data of the current sensor; is the measurement matrix, which is used to map the state into the observation space.

[0050] Furthermore, the dynamic trust evaluation is used to evaluate the credibility of each data source in real time, and dynamically adjust the influence of the data source according to the trust.

[0051] Furthermore, the calculation formula of the trust based on historical behavior is:

[0052] ;

[0053] In the formula, Is the data source Trust based on historical behavior; Is the data source the number of trustworthy behaviors; Is the data source Total communication records or data exchange times;

[0054] The calculation formula of the trust degree based on external verification is:

[0055] ;

[0056] In the formula, Is the data source Trust in external verification; Is the data source The raw data provided; It is reference data provided by other ships, shore-based control systems or third-party services.

[0057] Furthermore, the calculation formula of the comprehensive trust is:

[0058] ;

[0059] In the formula, Is the data source Overall trustworthiness; and is a weighting factor that controls the relative importance of historical behavior and external validation, and .

[0060] The technical solution also provides a system for implementing the above data consistency verification method, the system comprising:

[0061] A zero-trust authentication and access control establishment module is used to establish zero-trust authentication and access control for all communication nodes to authenticate before participating in data exchange or decision-making processes;

[0062] A data communication encryption mechanism establishment module, which establishes a data communication encryption mechanism for all communication nodes during data exchange or decision-making based on an end-to-end encryption method;

[0063] The module for establishing a time synchronization and verification mechanism uses timestamps to establish a time synchronization and verification mechanism for all data during data exchange or decision-making;

[0064] The consistency check result acquisition module performs redundancy check and fusion on the multi-source data of the communication nodes in the data exchange or decision-making process based on the Kalman filter correction method to obtain the consistency check result;

[0065] The trust dynamic evaluation module performs dynamic trust evaluation among multi-ship collaborations based on consistency verification results, including comprehensive trust based on historical behavior and trust based on external verification.

[0066] By means of the above technical solution, the present invention provides a data consistency verification method and system for reliable decision-making of intelligent inland waterway ships, which has at least the following beneficial effects:

[0067] 1. The present invention realizes that every data interaction between ships and shore bases, ships and ships, and ships and the environment is subject to identity verification and security review. Combined with time synchronization, multi-source data fusion, redundancy check and anomaly detection, it ensures the data consistency and credibility of navigation decisions, and significantly improves the navigation safety of inland ships and the system's anti-attack capability.

[0068] 2. The present invention can prevent malicious attacks and false data injection during data transmission and processing. Through multiple identity authentication, encrypted communication and data signature technology, the authenticity of all data sources is ensured to prevent malicious nodes from tampering with data or injecting false information.

[0069] 3. The present invention can ensure data consistency across devices and systems. By combining redundant data sources and intelligent data fusion algorithms, data from different sensors can be checked for consistency, ensuring that data from different sources can be effectively fused during data interaction, eliminating the impact of single sensor failure or data anomalies.

[0070] 4. The present invention can prevent tampering and data leakage during the communication process, and ensure that data is not tampered with or leaked during the transmission process through encryption protocols, digital certificates and signature technologies.

[0071] 5. The present invention can automatically detect and correct abnormal data, and through an abnormality detection and correction mechanism, discover and correct data anomalies in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0073] Figure 1 is a flow chart of the data consistency verification method in the present invention;

[0074] Figure 2It is a flowchart of zero-trust identity authentication and access control in the present invention;

[0075] Figure 3 A flowchart of data encryption and communication security in the present invention;

[0076] Figure 4 This is a flow chart of multi-node time synchronization and data consistency verification in the present invention;

[0077] Figure 5 This is a flowchart of multi-node trust evaluation and collaborative decision-making in the present invention. DETAILED DESCRIPTION

[0078] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0079] In order to meet the challenges raised by the above background technologies, Zero Trust Architecture (ZTA) has been gradually introduced into the intelligent ship system as a new network security model. The core concept of Zero Trust Architecture is "never trust, always verify", that is, strict identity authentication and permission control should be performed regardless of whether the device or user is located in the intranet. The introduction of Zero Trust Architecture can effectively deal with security threats such as external attacks, internal abuse and data leakage, thereby providing stronger security protection for the intelligent navigation of ships.

[0080] Under the zero-trust architecture, the intelligent ship system uses a dynamic and continuous verification mechanism to ensure that every data exchange and every decision-making process undergoes strict security review. This means that in the communication process between the ship and the shore-based control center, whether it is the collection and transmission of sensor data or the execution of the decision-making process, real-time identity authentication, access control and data consistency verification are required.

[0081] Please refer to Figure 1-Figure 5 This embodiment proposes a data consistency verification method for the trusted decision-making of the intelligent navigation of inland ships controlled by shore-based driving. By introducing a zero-trust architecture, each data interaction between the ship and the shore, between ships, and between ships and the environment is authenticated and reviewed for security. Ensure the data consistency and credibility of navigation decisions, and significantly improve the navigation safety of inland ships and the system's anti-attack capabilities. The method is divided into five parts: zero-trust identity authentication and access control, data encryption and communication security, time synchronization and verification mechanism, redundant verification and fusion of multi-source data, and dynamic evaluation of the trust of multiple ships based on consistency verification results, such as Figure 1 The specific implementation plan and steps are as follows:

[0082] The first step is to design zero-trust authentication and access control, such as Figure 2 As shown. All communication nodes (including ships, shore-based control systems, sensors, other ships, etc.) must undergo strict identity authentication before they can participate in data exchange or decision-making processes. Each communication node holds an independent digital certificate to verify its identity. These certificates are managed through a public key infrastructure (PKI) to ensure the authenticity of the identity during data exchange.

[0083] According to the principle of zero-trust architecture, no device or user is trusted, regardless of whether it is in the intranet. This embodiment dynamically verifies the permissions of each request based on roles and permissions. Permission control adopts an access control strategy that combines role-based access control (RBAC) and policy-based access control (PBAC), where:

[0084] Role-based access control (RBAC): Dynamically control access rights based on the permissions of different roles (such as ship drivers, shore-based controllers, etc.).

[0085] In role-based access control (RBAC), communication nodes are granted different access rights based on their roles. Each role has a specific set of permissions, and the permissions of the communication node are determined by its role. Suppose there are multiple roles , each role corresponds to a permission set , the relationship between roles and users is , that is, the communication node belongs to a certain role. Assume that the role Corresponding permission set , then the communication node Belong to the role When , the communication node will obtain the following permissions:

[0086] ;

[0087] in, For communication nodes The permission set.

[0088] Policy-based access control (PBAC): Data access permissions are determined through access control policies to ensure that only authorized users can access specific data or perform specific operations.

[0089] Policy-based access control (PBAC) uses policy rules to dynamically control access rights. Access control policies are determined by predetermined conditions and contextual information (such as time, location, request type, etc.).

[0090] Access Control Policy , each access control policy is a conditional expression:

[0091] ;

[0092] in, Is context information (such as time, request source, network status, etc.), if the condition If satisfied, access permission is granted To the requesting party. Control decisions for visits Based on access control policy and request context The matching situation is:

[0093] ;

[0094] The data consistency verification system decides whether to allow a user or device to access specific resources based on the context information of the request and the access control policy.

[0095] In the actual decision-making process, the data consistency verification system will combine the trust and credibility of the data source to weight the final decision result. For example, assuming that a decision process needs to consider data from multiple ships, the data consistency verification system will weight the trust of each ship and calculate the final decision result. data sources, corresponding to communication nodes (ships, shore-based control systems, etc.), whose trustworthiness is , and the decision result is , then the weighted decision can be expressed as:

[0096] ;

[0097] in, is the weighted coefficient of each data source, and the final weighted decision result will be the weighted synthesis of all control decisions, where the confidence This will be explained in step 5.

[0098] In a zero-trust architecture, the data consistency verification system dynamically verifies permissions for each request, and makes access decisions based on the context and role information of the current request, combined with RBAC and PBAC. By communication node Initiate, the data consistency verification system will calculate the access rights according to the following formula:

[0099] ;

[0100] In the formula, It is permission verification based on RBAC; It is a policy verification based on PBAC. The joint guarantee of RBAC and PBAC ensures the consistency of decision-making in roles and policies.

[0101] In a system based on zero-trust architecture, identity authentication and access control are the basis for ensuring data consistency and security. Therefore, in this embodiment, all communication nodes (such as ships, shore-based control systems, sensors, etc.) must undergo strict identity authentication before participating in data exchange and decision-making. Each communication node has a unique digital certificate and uses public key infrastructure (PKI) for authentication to ensure that the identity of each device is credible and legal. For users of different roles, the system dynamically controls the access rights of each user through role-based access control (RBAC) and policy-based access control (PBAC) to ensure that data and decision-making processes are only accessible to authorized personnel. This access control method effectively prevents illegal access and data tampering, and ensures the legality of each data exchange.

[0102] The second step is data encryption and communication security design, such as Figure 3 As shown in the figure, a data communication encryption mechanism is established based on an end-to-end encryption method for all communications between ships and shore-based control systems, and between ships during data exchange or decision-making.

[0103] All communications between ships and shore-based control systems, and between ships, must be end-to-end encrypted to prevent data from being intercepted or tampered with during transmission. The end-to-end encryption method used in this embodiment is AES encryption. AES encryption is commonly used for data content encryption to ensure that even if the data is intercepted, attackers cannot read it. The data communication encryption mechanism is a key measure to ensure that data is not stolen, tampered with or forged during transmission. Among them:

[0104] The data confidentiality verification mechanism uses end-to-end encryption technology to ensure that communications between ships and shore bases, and between ships, are encrypted at all times to prevent middleman attacks and data leakage. Communication encryption uses the AES encryption algorithm to ensure that data is always encrypted during transmission.

[0105] In the data integrity verification mechanism, in order to further ensure the integrity of the data and prevent the data from being tampered with during transmission, each piece of data is accompanied by a digital signature or hash value. After receiving the data, the receiver can verify the digital signature or compare the hash value with the public key to confirm whether the data has been tampered with. Through these encryption and authentication measures, the confidentiality, integrity and reliability of the data are ensured.

[0106] Each piece of transmitted data is accompanied by a digital signature or hash value to ensure that the data has not been tampered with during transmission. The data integrity verification mechanism includes hash verification and digital signature, where:

[0107] Hash verification: Hash the data content to generate a unique hash value. The receiver calculates the hash value after receiving the data to ensure data consistency.

[0108] Digital signature: Data is signed using the sender’s private key, and the recipient verifies the signature using the public key, thereby confirming the integrity and origin of the data.

[0109] The third step is to design a time synchronization and verification mechanism. Use timestamps to establish a time synchronization and verification mechanism for all data during data exchange or decision-making.

[0110] In order to ensure the timeliness and consistency of data, all transmitted data needs to be timestamped, and the time between each node needs to be synchronized. Through the NTP protocol, all equipment (ships, shore-based, sensors, etc.) are synchronized to a unified global standard time (UTC) to ensure that the timestamps of all data are consistent.

[0111] The ship is equipped with GPS equipment to ensure that the ship's real-time position and time are synchronized with the international standard time. When exchanging data, the system verifies the timestamp of the data to ensure the timeliness of the data. If the data timestamp differs too much from the system time, the system will consider the data to have potential problems and mark it as abnormal.

[0112] Time synchronization plays a vital role in ensuring data consistency and timeliness. In this embodiment, all data exchanges and data in the decision-making process need to be accompanied by accurate timestamps. To this end, the network time protocol (NTP) is used to synchronize the time of the ship, shore-based control system and other sensors to ensure that the time of all devices is consistent. If it is detected that the timestamp of the data is significantly different from the current time, or the order of the data timestamp is abnormal, the data will be marked as invalid or abnormal.

[0113] The fourth step is redundancy check and multi-source data fusion, such as Figure 4 As shown in the figure, redundancy check and fusion are performed on the multi-source data of the communication nodes in the data exchange or decision-making process to obtain the consistency check result.

[0114] In this embodiment, in order to improve the consistency and reliability of data, multiple independent data sources are used for redundancy verification. The position, speed, heading and other information of the ship are obtained by using multiple sensors such as GPS, inertial navigation system (INS), radar, etc. Each data source can provide the same or similar ship status information (such as position, speed, heading, etc.), and compare and verify each other. Reference state for consistency verification is the estimated value of the fusion sum of multi-source data.

[0115] The system estimates the state of the ship by fusing multi-source information. The result of data fusion is usually used as a unified "reference value" for consistency verification. Multi-source data fusion includes the following two parts:

[0116] Kalman filter estimate: Kalman filter calculates a weighted composite estimate by combining observations from multiple sources. This estimate is the reference standard. The basic formula of Kalman filter includes a prediction step and an update step.

[0117] Predict the state and covariance matrix of the system:

[0118] ;

[0119] ;

[0120] in, It's time Status prediction; is the state transition matrix; is the effect of the control input on the system state; is the predicted covariance matrix; is the process noise covariance matrix; is the state transition matrix The transpose of .

[0121] Update based on sensor data:

[0122] ;

[0123] ;

[0124] ;

[0125] in, is the Kalman gain matrix, used for optimization estimation; is the observation matrix; is the sensor measurement value; is the observation noise covariance matrix; is the updated state estimate; is the covariance matrix; is the identity matrix.

[0126] Prediction and measurement consistency check: Predictions are made through methods such as Kalman filtering, and then compared with actual measurements to test the reliability of the fusion estimate. The purpose of this step is to test whether the prediction results are consistent with reality and remove abnormal prediction data. The test formula is as follows:

[0127] ;

[0128] in, is the actual measured value, is the predicted value based on the previous estimate. Innovation represents the difference between the prediction and the measurement. If this value is too large, it indicates that there is data inconsistency. In Kalman filtering, Innovation usually follows a Gaussian distribution, so the standard deviation of Innovation can be used To determine the consistency of the data. If the Innovation value is greater than a certain threshold (for example, 3 times the standard deviation), it may indicate that the data is inconsistent, that is:

[0129] ;

[0130] If the Innovation exceeds 3 times the standard deviation, it is considered abnormal data.

[0131] In order to improve the data consistency of the system, the sensor consistency check is used to detect whether there is a large deviation in the same data provided by different sensors. When the difference in sensor data exceeds the preset threshold, the system will mark it as an abnormality and take corresponding processing measures, such as warnings or data corrections.

[0132] The Kalman filter is used to fuse the multi-source data of the ship's status (position, speed, heading, etc.) to obtain the estimated value of a certain time node after fusion. As a reference value. Then, the similarity between the data from multiple independent sensors and the fused data is compared, and the cosine similarity is used to measure the consistency between them. The specific algorithm is as follows:

[0133] Cosine similarity measures the angle between two vectors, reflecting whether their directions are similar. Given two vectors and , the cosine similarity calculation formula is:

[0134] ;

[0135] in, and They are two vectors, representing the data from the sensor and the reference data after Kalman filter fusion. and yes and The value of cosine similarity is between -1 and 1. The closer the value is to 1, the more similar the directions of the two vectors are. The closer the value is to -1, the opposite their directions are. 0 means no directional similarity.

[0136] In this embodiment, the specific process of obtaining the consistency check result is as follows:

[0137] Kalman filter data fusion: Use the Kalman filter method to fuse multi-source data from multiple sensors (such as GPS, INS, radar, etc.) to obtain the reference state of the ship. ,Right now:

[0138] ;

[0139] In the formula, They are the reference position, reference speed and reference heading of the ship respectively;

[0140] Sensor data collection: Get the real status of the ship from different sensors (such as GPS, radar, INS, etc.) ,Right now:

[0141] ;

[0142] In the formula, They are the true position, true speed and true heading of the ship respectively;

[0143] Calculate cosine similarity: Calculate cosine similarity for each data ,Right now:

[0144] Calculate the cosine similarity of the position data, that is:

[0145] ;

[0146] Calculate the cosine similarity of the speed data, that is:

[0147] ;

[0148] Calculate the cosine similarity of the heading data, that is:

[0149] ;

[0150] Threshold selection for consistency check: Set the cosine similarity threshold used to determine whether the data is consistent , used to determine whether the data is consistent. The specific setting needs to be based on the actual situation, and no limitation is made here. Exceeding the cosine similarity threshold , the data can be considered consistent; below the cosine similarity threshold , then it is considered that there is inconsistency, that is, outlier data;

[0151] Outlier data correction: Adjust outlier data based on the deviation of current sensor data and previous state predictions.

[0152] Kalman filtering can not only perform data fusion, but also correct outlier data through its prediction mechanism. Kalman filtering adjusts outlier data based on the deviation of current sensor data and previous state prediction. Suppose the current state is , the current observation is , the Kalman gain is , the Kalman filter correction formula is:

[0153] ;

[0154] in is the state prediction of the previous moment; is the Kalman gain; is the observation data of the current sensor; is the measurement matrix, which is used to map the state into the observation space.

[0155] In order to improve the reliability and consistency of data, this embodiment introduces redundant verification and multi-source data fusion methods. Ships are equipped with a variety of sensors (such as GPS, inertial navigation system (INS), radar, etc.) to obtain various information of the ship (position, speed, heading, etc.). Through the Kalman filter data fusion algorithm, data from different sensors can be optimized and processed to eliminate the impact of errors or failures that may occur in a single sensor. The data consistency of each sensor is monitored in real time. When it is found that the data of a certain sensor deviates greatly from the expected results of other sensors or systems, the data consistency verification system will automatically adjust or replace it. This redundancy mechanism improves the consistency of data and reduces the negative impact of sensor failure or inconsistent data on decision-making. If it is detected that the data of a certain sensor is significantly different from the expected results of other sensors, the data consistency verification system will automatically correct or replace the data to ensure the consistency of the data in the decision-making process.

[0156] The fifth step is the dynamic evaluation of multi-ship trust based on the consistency test results, e.g. Figure 5 shown.

[0157] In the intelligent ship system based on zero-trust architecture, the trust evaluation mechanism and decision weighting mechanism are important means to ensure data consistency, reliability and security. This mechanism evaluates the trust of each data source based on multiple factors. Low-trust data sources will be restricted or adjusted in their influence on decision results. The core goal of trust evaluation is to evaluate the credibility of each data source in real time and dynamically adjust the influence of the data source according to the trust. The dynamic trust evaluation is mainly based on the following two aspects:

[0158] 1. Trust based on historical behavior

[0159] The historical behavior of the data source of a ship or sensor is crucial to its trustworthiness assessment. The historical behavior mainly refers to communication records, which are used to assess whether the data source has frequent data loss, communication failures, or malicious behavior.

[0160] The trust calculation formula based on historical behavior is:

[0161] ;

[0162] in, Is the data source Trust based on historical behavior; Is the data source the number of trustworthy behaviors; Is the data source Total communication records or data exchange times. Historical behavior trust The value of is between [0,1], and the higher the value, the more credible the historical behavior.

[0163] 2. Trust based on external verification

[0164] External verification further enhances the credibility of data sources by connecting to shore-based control systems, other ships or third-party services for real-time verification. External verification mainly relies on data consistency, that is, by comparing with other trusted data sources, verifying whether the data provided by the current data source is consistent. Consistency verification can be used for verification. The calculation formula for the trustworthiness of external verification is:

[0165] ;

[0166] in, Is the data source External verification trust; Is the data source The raw data provided; It is reference data provided by other ships, shore-based control systems or third-party services.

[0167] Overall trust Trust based on historical behavior and trust based on external verification The weighted combination forms a final trust score. The calculation formula for comprehensive trust is:

[0168] ;

[0169] In the formula, Is the data source Overall trustworthiness; and is a weighting factor that controls the relative importance of historical behavior and external validation, and .

[0170] In order to further improve data consistency and system security, this embodiment introduces a multi-ship trust evaluation mechanism. In a multi-ship collaborative environment, ships share a large amount of data, including key parameters such as position, speed, and heading. These data not only need to be verified for consistency, but also need to evaluate the credibility of the data source. In this process, the trustworthiness of each ship is dynamically evaluated through consistency test results and historical interaction data.

[0171] The present invention provides a data consistency verification method and system for the trusted decision-making of intelligent ship navigation of inland waterway ships controlled by shore-based driving based on zero-trust architecture. By introducing the zero-trust architecture, each data interaction between the ship and the shore, between ships, and between ships and the environment is authenticated and reviewed for security. Combined with technologies such as time synchronization, multi-source data fusion, redundant verification, and anomaly detection, the data consistency and credibility of navigation decisions are ensured, significantly improving the navigation safety of inland waterway ships and the system's anti-attack capability.

[0172] Those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, so the present application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0173] The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A data consistency verification method for reliable decision-making of inland river ship intelligent ship operation, characterized in that: The Method The process includes: Establish zero-trust authentication and access control for all communication nodes to authenticate before participating in data exchange or decision-making processes, including zero-trust authentication, access control, and making access decisions. The specific process of making access decisions includes: Use policy-based access control to establish access control policies and request context Control decisions for matching situations , the expression is: ； Adopting control decision Comprehensive trust in each ship Weighted and calculated final decision result , the expression is: ； In the formula, is the number of data sources, corresponding to Communication nodes; Based on decision results Dynamically verify permissions for each request and make access decisions by combining role-based access control and policy-based access control. The expression is: ； In the formula, It is the permission verification of role-based access control; It is policy verification for policy-based access control; To express a request; Indicates Communication nodes; Establish data communication encryption mechanism between all communication nodes during data exchange or decision-making process; Establish time synchronization and verification mechanism for all data during data exchange or decision-making process; Based on the Kalman filter correction method, the multi-source data of the communication nodes in the data exchange or decision-making process are redundancy checked and integrated to obtain consistency test results; Based on the consistency test results, a dynamic evaluation of the trust between multiple ships' collaboration is performed, including the trust based on historical behavior and the comprehensive trust based on external verification.

2. The data consistency verification method according to claim 1, characterized in that: The zero-trust authentication includes: Communication nodes hold independent and unique digital certificates to verify their identities and use public key infrastructure for authentication; The access control includes role-based access control and policy-based access control, wherein: Role-based access control is used to dynamically control access rights according to the permissions of different roles, including ship drivers and shore-based controllers; Policy-based access control is used to determine data access rights through access control policies, ensuring that only authorized users can access specific data or perform specific operations. Access control policies are determined by predetermined conditions and context information. Making access decisions includes: Dynamically verify permissions for each request, and make access decisions based on the context and role information of the current request, combining role-based access control and policy-based access control.

3. The data consistency verification method according to claim 1, characterized in that: The data communication encryption mechanism includes: After receiving the data, the recipient verifies the digital signature through the public key or compares the hash value to confirm whether the data has been tampered with, including the data confidentiality verification mechanism and the data integrity verification mechanism. The data integrity verification mechanism includes hash verification and digital signature.

4. The data consistency verification method according to claim 1, characterized in that: The time synchronization and verification mechanism includes: During data exchange, the timestamp attached to each piece of data is verified. If the timestamp of the data differs from the global standard time, or the order of the timestamps is abnormal, the data has potential problems and is marked as abnormal or invalid.

5. The data consistency checking method according to claim 1, characterized in that: Obtaining the consistency test result includes the following process: Kalman filter data fusion: Use Kalman filter method to fuse multi-source data from multiple sensors to obtain the reference state of the ship ,Right now: ； In the formula, They are the reference position, reference speed and reference heading of the ship respectively; Sensor data collection: Get the real status of the ship from different sensors ,Right now: ； In the formula, They are the true position, true speed and true heading of the ship respectively; Calculate cosine similarity: Calculate cosine similarity for each data ,Right now: Calculate the cosine similarity of the position data, that is: ； Calculate the cosine similarity of the speed data, that is: ； Calculate the cosine similarity of the heading data, that is: ； Threshold selection for consistency check: Set the cosine similarity threshold used to determine whether the data is consistent , if the cosine similarity Exceeding the cosine similarity threshold , the data is considered consistent; below the cosine similarity threshold , then it is considered that there is inconsistency, that is, outlier data; Outlier data correction: According to the deviation of the current sensor data and the previous state prediction, the outlier data is corrected. The correction formula is: ； In the formula, is the state prediction of the previous moment; is the Kalman gain; is the observation data of the current sensor; is the measurement matrix, which is used to map the state into the observation space.

6. The data consistency checking method according to claim 1, characterized in that: The dynamic trust evaluation is used to evaluate the credibility of each data source in real time, and dynamically adjust the influence of the data source according to the trust.

7. The data consistency checking method according to claim 6, characterized in that: The calculation formula of the trust degree based on historical behavior is: ； In the formula, Is the data source Trust based on historical behavior; Is the data source the number of trustworthy behaviors; Is the data source Total communication records or data exchange times; The calculation formula of the trust degree based on external verification is: ； In the formula, Is the data source Trust in external verification; Is the data source The raw data provided; It is reference data provided by other ships, shore-based control systems or third-party services.

8. The data consistency checking method according to claim 7, characterized in that: The calculation formula of the comprehensive trust is: ； In the formula, Is the data source Overall trustworthiness; and is a weighting factor that controls the relative importance of historical behavior and external validation, and .

9. A system for implementing the data consistency verification method according to any one of claims 1 to 8, characterized in that: The system comprises: A zero-trust authentication and access control establishment module is used to establish zero-trust authentication and access control for all communication nodes to authenticate before participating in data exchange or decision-making processes; A data communication encryption mechanism establishment module, which establishes a data communication encryption mechanism for all communication nodes during data exchange or decision-making based on an end-to-end encryption method; The module for establishing a time synchronization and verification mechanism uses timestamps to establish a time synchronization and verification mechanism for all data during data exchange or decision-making; The consistency check result acquisition module performs redundancy check and fusion on the multi-source data of the communication nodes in the data exchange or decision-making process based on the Kalman filter correction method to obtain the consistency check result; The trust dynamic evaluation module performs dynamic trust evaluation among multi-ship collaborations based on consistency verification results, including comprehensive trust based on historical behavior and trust based on external verification.

Images