Ship-shore cooperative communication method and device, electronic equipment and storage medium

Abstract

The invention relates to the technical field of communication, in particular to a ship-shore cooperative communication method and device, electronic equipment and a storage medium. According to the scheme, the defect that a traditional system is single in monitoring index is overcome by obtaining the basic index and the business customization index data, comprehensive monitoring of the operation state of the shipborne platform is achieved, and the monitoring precision is remarkably improved; potential fault information is predicted based on two types of index data, passive warning is changed into active warning, and the problem that fault warning is not timely is solved. The shore-based equipment communicates with other shipborne platforms, a target repair strategy is obtained, a cooperative control instruction is generated, a cross-platform cooperative mechanism is constructed, the limitation of isolated operation of a traditional system is broken through, and the shore-based cooperative capability is enhanced; for the condition of no matching self-repairing strategy, external strategy resources can be dynamically called, a single fault recovery mode is changed, the fault recovery efficiency is effectively improved, and stable operation of the shipborne platform is guaranteed.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of communication technology, in particular to a ship-shore cooperative communication method and device, electronic equipment and storage medium. BACKGROUND

[0002] In the field of intelligent ship, the health monitoring system of traditional shipborne platform mainly relies on local sensors to collect basic indicators such as CPU, memory and disk, and triggers local alarm through simple threshold judgment. However, such system has significant technical defects: on the one hand, it lacks real-time data interaction and cooperative analysis capability with shore-based system, and cannot transmit key operation data to shore-based system for deep mining, resulting in delayed fault warning; on the other hand, the monitoring indicators are limited to general hardware parameters, without designing customized indicators (such as positioning signal strength, ship-shore transmission link stability, etc.) for ship business scenarios, making it difficult to accurately reflect the navigation state; at the same time, the fault recovery strategy is single, and can only perform basic operations such as service restart, and cannot dynamically adapt to diversified repair schemes according to business needs. SUMMARY

[0003] Therefore, the embodiments of the present application provide a ship-shore cooperative communication method and device, electronic equipment and storage medium to solve the problems of traditional shipborne health monitoring system, such as lack of shore-based cooperative capability, business customized monitoring indicators and dynamic fault recovery strategy, resulting in delayed fault warning, insufficient monitoring accuracy and low repair efficiency.

[0004] In a first aspect, the embodiments of the present application provide a ship-shore cooperative communication method applied to a shore-based device, the method comprising:

[0005] obtaining first indicator data corresponding to basic indicators of main services in a shipborne platform, and second indicator data corresponding to business customized indicators associated with the shipborne platform;

[0006] predicting potential fault information of the shipborne platform based on the first indicator data and the second indicator data;

[0007] querying whether there is a self-repair strategy in the shipborne platform that matches the potential fault information;

[0008] if there is no self-repair strategy in the shipborne platform that matches the potential fault information, obtaining a target repair strategy that matches the potential fault information from fault repair strategies of other shipborne platforms communicated by the shore-based device, generating a cooperative control instruction based on the target repair strategy, and sending the cooperative control instruction to the shipborne platform.

[0009] Further, the step of predicting the potential fault information of the shipborne platform based on the first indicator data and the second indicator data comprises:

[0010] analyzing time sequence characteristics of the first index data to obtain time sequence fluctuation rules of the basic index;

[0011] identifying causal coupling characteristics between second index data of different business customization indexes to obtain a correlation between the business customization indexes;

[0012] generating a composite feature vector based on the time sequence fluctuation rules and the correlation;

[0013] performing similarity matching between abnormal features in a historical fault case library and the composite feature vector;

[0014] if the historical fault case library contains abnormal features matching the composite feature vector, taking fault information corresponding to the abnormal features as the potential fault information.

[0015] Further, the method further comprises:

[0016] if the historical fault case library does not contain abnormal features matching the composite feature vector, sending the first index data, the second index data and the composite feature vector to a control terminal, wherein the control terminal is configured to generate a repair strategy according to the first index data, the second index data and the composite feature vector;

[0017] receiving the repair strategy sent by the control terminal, generating a cooperative control instruction based on the repair strategy, and sending the cooperative control instruction to the shipboard platform, wherein the shipboard platform repairs the potential fault information according to the repair strategy and stores the repair strategy.

[0018] Further, the target repair strategy matching the potential fault information is obtained from the fault repair strategies of other shipboard platforms based on the shore-based equipment communication, comprising:

[0019] building a repair strategy graph using the fault repair strategies of other shipboard platforms and attributes of other shipboard platforms;

[0020] extracting semantic content of the fault information and detecting a first candidate repair strategy matching the semantic content from the repair strategy graph;

[0021] obtaining a spatio-temporal correlation feature corresponding to the fault information, and detecting a second candidate repair strategy matching the spatio-temporal correlation feature from the repair strategy graph;

[0022] determining the target repair strategy based on candidate repair strategies that overlap in the first candidate repair strategy and the second candidate repair strategy.

[0023] Further, the method further comprises:

[0024] If there is no coincident candidate repair strategy in the first candidate repair strategy and the second candidate repair strategy, respectively acquire the repair success rate of the first candidate repair strategy and the second candidate repair strategy;

[0025] The first candidate repair strategy and the candidate repair strategy with the highest repair success rate among the second candidate repair strategy are taken as the target repair strategy.

[0026] Further, the target repair strategy is determined based on the coincident candidate repair strategy among the first candidate repair strategy and the second candidate repair strategy, comprising:

[0027] Simulate the first repair effect of the ship-borne platform repairing the potential fault information according to the first candidate repair strategy; and simulate the second repair effect of the ship-borne platform repairing the potential fault information according to the second candidate repair strategy;

[0028] Based on the first repair effect and the second repair effect, the first candidate repair strategy and the second candidate repair strategy are combined to obtain the target repair strategy.

[0029] Further, the method further comprises:

[0030] If the ship-borne platform has a self-repair strategy matching the potential fault information, monitor the fault repair situation of the ship-borne platform;

[0031] If the fault repair situation of the ship-borne platform is repair failure, analyze the self-repair strategy to determine the cause of the repair failure;

[0032] Based on the cause, generate update content of the self-repair strategy, and send the update content to the ship-borne platform, so that the ship-borne platform updates the self-repair strategy based on the update content, and repairs the potential fault information by using the updated self-repair strategy.

[0033] In a second aspect, an embodiment of the present application provides a ship-shore cooperative communication device, the device comprising:

[0034] An acquisition module is configured to acquire first index data corresponding to a basic index of main service in a ship-borne platform, and second index data corresponding to a business customization index associated with the ship-borne platform;

[0035] A prediction module is configured to predict potential fault information of the ship-borne platform based on the first index data and the second index data;

[0036] The query module is configured to query whether a self-repair strategy matching the potential fault information exists in the shipboard platform.

[0037] The processing module is configured to, if no self-repair strategy matching the potential fault information exists in the shipboard platform, acquire a target repair strategy matching the potential fault information from fault repair strategies of other shipboard platforms communicated by the shore-based device, generate a cooperative control instruction based on the target repair strategy, and send the cooperative control instruction to the shipboard platform.

[0038] In a third aspect, an electronic device is provided, which includes a memory and a processor in communication connection with each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the method of the first aspect or any of the corresponding embodiments thereof.

[0039] In a fourth aspect, a computer readable storage medium is provided, which stores computer instructions for causing a computer to perform the method of the first aspect or any of the corresponding embodiments thereof.

[0040] The scheme of the present application compensates for the defect of single monitoring index of the traditional system by acquiring the basic index and the business customization index data, realizes comprehensive monitoring of the running state of the shipboard platform, and significantly improves the monitoring accuracy. The potential fault information is predicted based on the two types of index data, which changes passive alarm to active early warning, and solves the problem of untimely fault early warning. The shore-based device communicates with other shipboard platforms to acquire the target repair strategy and generate the cooperative control instruction, builds a cross-platform cooperative mechanism, breaks the limitation of isolated operation of the traditional system, and enhances the shore-based cooperative capability. In the case of no matching self-repair strategy, external strategy resources can be dynamically called, the single fault recovery mode is changed, the fault repair efficiency is effectively improved, and the stable operation of the shipboard platform is ensured. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings needed to be used in the specific embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0042] Figure 1 is a flowchart of a ship-shore cooperative communication method according to some embodiments of the present application;

[0043] Figure 2 is a flowchart of another ship-shore cooperative communication method according to some embodiments of the present application;

[0044] Figure 3 is a flowchart of still (further) XX method according to some embodiments of the present application;

[0045] Figure 4 is a structural block diagram of XX apparatus according to embodiments of the present application;

[0046] Figure 5 is a hardware structural schematic diagram of electronic equipment according to embodiments of the present application. DETAILED DESCRIPTION

[0047] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present application.

[0048] According to the embodiments of the present application, a ship-shore cooperative communication method and device, electronic equipment and storage medium are provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a group of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that here.

[0049] In the present embodiment, a ship-shore cooperative communication method is provided, which is applied to a shore-based device, Figure 1 is a flowchart of a ship-shore cooperative communication method according to an embodiment of the present application, as Figure 1 shown, the flowchart includes the following steps:

[0050] In step S101, first index data corresponding to a basic index of a main service in a shipboard platform and second index data corresponding to a business customization index associated with the shipboard platform are acquired.

[0051] In the embodiment of the present application, two types of index data are obtained through the BITE module integrated in the back-end main service of the shipboard platform: one type is first index data corresponding to basic indexes of the main service in the shipboard platform, and the other type is second index data corresponding to business customized indexes associated with the shipboard platform. The shipboard platform is a collection of hardware and software systems on a ship, including main services and various business modules; the main service is a core functional module of the shipboard platform, such as power control, navigation system, etc.; the basic indexes include CPU usage, memory occupancy, disk space, network port status, middleware (MySQL / Redis, etc.) process status, and other basic parameters reflecting the running state of the main service; and the first index data is real-time or historical data of the above-mentioned basic indexes. The business customized indexes are specific indexes customized according to the specific business needs of the ship, such as data acquisition link integrity (communication status between acquisition program and sensor), ship positioning signal strength (GPS / Beidou signal quality), ship-shore transmission link stability (transmission delay / packet loss rate), etc.; and the second index data is real-time or historical data corresponding to these customized indexes.

[0052] In the implementation, the BITE module obtains the first index data in the following manner: using the data acquisition module deployed in the hardware devices (such as sensors, controllers) of the main service, real-time reading of CPU, memory, and other basic indexes through Modbus, TCP / IP, and other network protocols; regularly capturing historical data from the system logs and monitoring databases of the main service; and obtaining real-time data from the running state monitoring module of the main service through the API interface, such as middleware process status. For the acquisition of the second index data, the BITE module can interface with the business system database to query the business data tables related to the customized indexes (such as the positioning signal strength table); collect data through special business terminal devices (such as data acquisition link monitoring terminals) and transmit them to the shipboard platform through 4G, Wi-Fi, and other wireless methods; and use customized script programs to parse and extract index data from the business system data stream, such as delay data packets of the ship-shore transmission link. In the data acquisition process, regular polling (such as collecting data every 5 minutes), event triggering (such as real-time collection when the link is interrupted), and other methods are used, and temporary data is temporarily stored through the data caching mechanism of the BITE module, to ensure the integrity and timeliness of the two types of data and avoid data loss caused by transmission interruption.

[0053] Step S102, based on the first index data and the second index data, predicting potential fault information of the shipboard platform.

[0054] In the embodiment of the present application, based on the first index data and the second index data, the potential fault information of the shipboard platform is predicted, including the following steps A1-A5:

[0055] Step A1, analyzing the time sequence characteristics of the first index data to obtain the time sequence fluctuation rule of the basic indexes.

[0056] It should be noted that the timing feature refers to the periodicity, trend, volatility, seasonality, etc. dynamic change characteristics of the first index data on the time axis; the basic index is the core parameter reflecting the running state of the main service of the ship-borne platform; and the timing fluctuation law is the change mode and internal law of the basic index on the time sequence obtained by analysis.

[0057] Specifically, first, the first index data is preprocessed, and methods such as sliding window filtering and outlier elimination are used to eliminate noise interference and ensure the accuracy of the data; then statistical analysis methods (such as calculating mean, variance, and standard deviation) are used to quantify the fluctuation range of the data, and the change trend of the data over time is intuitively presented by drawing a timing curve; then time series analysis algorithms (such as ARIMA model, Fourier transform, and wavelet transform) are used to extract periodic characteristics, such as identifying the periodic fluctuation law of CPU usage rate in the daily peak period; at the same time, the moving average method is used to detect the trend item of the data (such as the continuous downward trend of disk space over time), and the difference method is used to eliminate the trend item to highlight the periodic fluctuation; in addition, LSTM, Prophet, etc. models in machine learning can be used to identify the pattern of timing data, automatically fit the fluctuation law of the data, such as determining the fluctuation period and amplitude of memory occupancy rate under different business loads by training the model. The BITE module integrates the above analysis results to form a regular description of the basic index in the time dimension, such as "CPU usage rate presents a daily 8:00-22:00 periodic fluctuation, and the peak value exceeds 80% in the period of 14:00-16:00" and other specific fluctuation laws.

[0058] Step A2, identify the causal coupling characteristics between the second index data of different business customization indexes, and obtain the association relationship between the business customization indexes.

[0059] It should be noted that the causal coupling feature refers to the dynamic coupling characteristics of the causal relationship or mutual influence between the index data; and the association relationship is the dependency relationship, influence path or cooperative change mode between the indexes determined by analysis.

[0060] Specifically, first, the second index data is preprocessed, data cleaning techniques such as missing value filling and outlier filtering are used to ensure data quality, and time alignment processing is used to make different index data synchronous; then, a causal relationship analysis algorithm such as Granger causality test is used to quantify the causal influence strength between indexes, for example, to test whether “ship-shore transmission link delay increases” is the Granger cause of “data acquisition link interruption”; at the same time, an association rule mining method such as Apriori algorithm is used to extract frequent co-occurrence patterns between index data, generating an association rule “low positioning signal strength < threshold value → ship-shore transmission packet loss rate increases”; a Bayesian network model can also be built to describe the causal dependence relationship between indexes in terms of conditional probability, for example, to establish a probability conduction path “data acquisition link anomaly → ship-shore transmission stability decreases”; in addition, a graph neural network (GNN) in machine learning is used to model the index data, each business customization index is taken as a node, and the coupling relationship between indexes is taken as an edge. Through training the model to learn the dynamic association characteristics between indexes. After integrating the above analysis results, the BITE module forms the association relationship description between business customization indexes, such as “the probability of ship positioning signal strength decrease leading to ship-shore transmission link delay increase increases by 40%” and other specific association conclusions.

[0061] Step A3, based on the time series fluctuation rule and the association relationship, a composite feature vector is generated.

[0062] Specifically, first, the time series fluctuation rule is quantitatively extracted, and methods such as Fourier transform and wavelet analysis are used to convert periodic characteristics into frequency domain parameters (such as main frequency and harmonic component), and statistical characteristics such as mean, variance and peak interval of time series data are calculated through sliding window, for example, “CPU usage rate exceeds 80% from 14:00 to 16:00 every day” is converted into “peak period proportion” and “peak amplitude” and other numerical characteristics; at the same time, the association relationship is mathematically modeled, and indexes such as Granger causality test coefficient, Bayesian network conditional probability value and association rule confidence are used to quantify the influence strength between indexes, for example, “the probability of positioning signal strength decrease leading to ship-shore transmission delay increase increases by 40%” is converted into a causal association weight value. Subsequently, the time series quantitative characteristics and the association weight characteristics are standardized (such as Z-Score normalization), and are spliced into a multi-dimensional vector according to the pre-set dimension order; for high-dimensional feature space, dimension reduction algorithms such as principal component analysis (PCA) and automatic encoder (Auto encoder) can be used to compress the feature dimension and retain the key feature components. The finally generated composite feature vector contains the fusion information of the basic index time series characteristics and the business index association characteristics, for example, the numerical vector form of “[CPU fluctuation period, memory trend slope, positioning-transmission association weight, link interruption probability...]”, which provides standardized feature input for subsequent fault case matching.

[0063] Step A4, similarity matching is performed between the abnormal feature and the composite feature vector in the historical fault case library.

[0064] It should be noted that the historical fault case library is a database for storing historical fault events of the shipborne platform, containing abnormal feature vectors and corresponding fault information at the time of failure; the abnormal feature is a feature vector composed of the time series fluctuation rule of the basic index and the association relationship of the business customized index at the time of historical failure; the composite feature vector is a multi-dimensional numerical representation of the current running state of the shipborne platform, which integrates the time series features of the basic index and the association features of the business index.

[0065] Specifically, first, the abnormal features in the historical fault case library are standardized for preprocessing to ensure consistency in dimensions and units with the composite feature vector; then, a similarity calculation algorithm (such as cosine similarity, Euclidean distance, Manhattan distance) is used to quantify the difference between the composite feature vector and each historical abnormal feature, for example, the cosine value of the vector angle is calculated to measure the directional similarity; at the same time, the K nearest neighbor (KNN) algorithm can be combined to select the K historical abnormal features with the highest similarity as candidate matching items; to improve matching efficiency, a local sensitive hash (LSH) index or KD tree index structure can be constructed to map high-dimensional feature vectors into hash buckets and quickly locate similar feature subsets. In addition, weighted similarity calculation can also be introduced, with different weights given to the importance of basic indexes and business indexes (such as higher weight for CPU fluctuation features than for general business indexes), so that the matching results are more consistent with the fault diagnosis logic. During the matching process, the BITE module will calculate the composite feature vector with each abnormal feature in the case library one by one or use batch matrix operations to speed up the processing, and finally output a list of historical abnormal features sorted by similarity, providing a basis for subsequent fault information determination.

[0066] Step A5, if there is an abnormal feature in the historical fault case library that matches the composite feature vector, the fault information corresponding to the abnormal feature is taken as the potential fault information.

[0067] Specifically, the BITE module first sets a similarity threshold (such as cosine similarity greater than 0.8) based on the similarity matching results, and filters out abnormal features that exceed the threshold. For each abnormal feature that meets the conditions, the corresponding fault information is queried from the historical fault case library, including basic information such as fault name (such as "data acquisition link interruption"), fault cause (such as "sensor communication interface abnormality"), fault impact (such as "real-time uploading of shipborne data is not possible"), and historical processing records (such as the repair strategies used). If there are multiple matching abnormal features, the BITE module will sort them from high to low according to the similarity, and preferentially select the fault information corresponding to the abnormal feature with the highest similarity as the potential fault information; if multiple abnormal features correspond to the same type of fault information, the BITE module will confirm that the type of fault is the potential fault.

[0068] Finally, the BITE module structures the extracted potential fault information into a standardized data structure containing elements such as fault type, possible causes, and impact scope, for subsequent query of self-repair strategies. Throughout the process, the BITE module quickly locates the fault information corresponding to the abnormal characteristics through database indexing technology, ensuring the real-time and accuracy of the matching results.

[0069] The embodiment of the application changes the traditional system which only relies on simple threshold alarm by analyzing the time sequence characteristics of the first index data to obtain the time sequence fluctuation rule of the basic index, and identifying the causal coupling characteristics between the second index data to clarify the correlation of the business customized index, improves the monitoring depth from the time dimension and the index correlation dimension, and solves the problem of insufficient monitoring accuracy; generates a composite feature vector based on the time sequence fluctuation rule and the correlation, and performs similarity matching with the abnormal characteristics in the historical fault case library to predict potential faults, changes the defect of the traditional system lacking depth analysis, realizes active prediction of potential faults, and effectively solves the problem of untimely fault warning; uses the historical fault case library for matching analysis to provide data support for fault prediction, to some extent, makes up for the deficiency of the traditional system lacking dynamic strategy, and provides a more targeted basis for subsequent fault repair.

[0070] In the embodiment of the application, the method further includes the following steps B1-B2:

[0071] Step B1, if there is no abnormal characteristic in the historical fault case library that matches the composite feature vector, the first index data, the second index data, and the composite feature vector are sent to a control terminal, wherein the control terminal is used to generate a repair strategy according to the first index data, the second index data, and the composite feature vector.

[0072] Specifically, first, the three types of data (first index data, second index data, and composite feature vector) are structured and packaged, and are encapsulated in JSON or Protobuf format to ensure data compatibility; then a secure transmission channel is established through a ship-shore communication link (such as 4G, satellite communication), data is encrypted using SSL / TLS protocol to prevent data leakage or tampering during transmission; a breakpoint resume mechanism is used during transmission, if the communication is interrupted, the data is cached, and when the link is restored, the data is automatically retransmitted to ensure data integrity.

[0073] Before the control terminal receives the data, identity authentication and data verification are performed, the data integrity is verified through a message digest algorithm (such as MD5), and after confirmation, the data is stored in the database and the strategy generation process is triggered. In addition, the BITE module can dynamically adjust the transmission mode according to the data size, uses streaming transmission for scenes with high real-time requirements, and uses block compression transmission for large data volume scenes to optimize bandwidth utilization.

[0074] Step B2, receive the repair strategy sent by the control terminal, generate a cooperative control instruction based on the repair strategy, and send the cooperative control instruction to the shipboard platform, wherein the shipboard platform repairs the potential fault information according to the repair strategy, and stores the repair strategy.

[0075] Specifically, first, the repair strategy sent by the control terminal is received through the ship-shore communication link (such as 4G, satellite communication), the strategy content is parsed in JSON / Protobuf format, and the message integrity is verified by the HMAC algorithm to prevent tampering. Then, according to the strategy type (such as "restart collection program" "switch to backup sensor"), the corresponding cooperative control instruction is generated, and the instruction format follows the shipboard platform API interface specification, for example, the "restart service" strategy is converted into a binary instruction package containing service identification and restart parameters. When sending the instruction, a reliable connection is established through the TCP / IP protocol, and the SSL / TLS encryption transmission is used, and if the communication link quality is poor, the adaptive retransmission mechanism (such as dynamically adjusting the retransmission interval based on RTT) is enabled. After the shipboard platform receives the instruction, the BITE module parses and executes it, for example, calls the system API to restart the specified service, modifies the resource allocation configuration file, or triggers the backup link switching logic. At the same time, the BITE module stores the repair strategy to the local SQLite database, and updates it to the shore-based system through the incremental synchronization mechanism, and the storage content includes strategy version number, execution parameter, generation time, etc. Metadata, facilitating subsequent traceability and strategy optimization.

[0076] Step S103, query whether there is a self-repair strategy in the shipboard platform that matches the potential fault information;

[0077] In the embodiments of the present application, first, the key features (such as fault type, affected component, abnormal index) are extracted from the potential fault information to generate a query condition, for example, the query keywords corresponding to the "data acquisition link interruption" fault are "link interruption" and "sensor communication". Then, the self-repair strategy library stored locally in the shipboard platform is accessed, and the library usually adopts a relational database (such as SQLite) or a key-value pair storage structure, each strategy is associated with fault feature labels (such as "CPU overload" "weak positioning signal") and scene description. In order to improve the query efficiency, the strategy library will establish an inverted index or a full-text retrieval index, and the fault feature keywords are associated with the strategy ID, for example, the "link switching" strategy corresponds to the "data acquisition link" "backup sensor" and other index items.

[0078] When querying, the BITE module filters through keyword matching, semantic analysis (such as TF-IDF algorithm to calculate the similarity of the fault description and the policy label) or rule engine (such as conditional matching based on decision tree), for example, when the potential fault information contains "data acquisition link interruption", the policy with the label containing "link interruption" and the operation type of "switching standby link" in the policy library is retrieved. If a policy with a matching degree exceeding a preset threshold (such as 80%) is found, it is determined that there is a matching self-repairing policy; if no policy meeting the condition is found, the repair strategy is obtained from the outside. During the whole process, the BITE module records the query log, including the query condition, the matching policy ID, the similarity score, etc.

[0079] In step S104, if there is no self-repairing policy matching the potential fault information in the ship-borne platform, a target repair strategy matching the potential fault information is obtained from the fault repair strategies of other ship-borne platforms based on the communication of the shore-based device, a cooperative control instruction is generated based on the target repair strategy, and the cooperative control instruction is sent to the ship-borne platform.

[0080] It should be noted that the shore-based system is a remote management system that receives and analyzes data of the ship-borne platform; the other ship-borne platform refers to a platform on another ship interconnected with the current ship-borne platform through the shore-based system; the fault repair strategy is an effective solution used by the other ship-borne platform in historical faults; the target repair strategy is a strategy suitable for the current potential fault selected from the strategies of other platforms; and the cooperative control instruction is a set of instructions converted from the target repair strategy and executable by the ship-borne platform.

[0081] In the embodiments of the present application, obtaining the target repair strategy matching the potential fault information from the fault repair strategies of other ship-borne platforms based on the communication of the shore-based device includes the following steps C1-C4:

[0082] In step C1, a repair strategy graph is built using the fault repair strategies of other ship-borne platforms and the attributes of other ship-borne platforms.

[0083] Specifically, as Figure 2As shown, other shipboard platforms refer to monitoring systems on other vessels interconnected with the current platform through the shore-based system; failure repair strategies are effective solutions verified in historical failures (such as "switching to backup sensors" and "adjusting network transmission parameters"); platform attributes include environmental characteristics such as ship type, navigation area, hardware configuration, etc. In the implementation, first, the shore-based system collects strategy data and attribute information of each interconnected platform, and uses knowledge graph technology to structure the data - taking repair strategies (such as "switching to backup sensors when data acquisition link is interrupted") and platform attributes (such as "ocean-going cargo ship" and "navigation in North Latitude 30° sea area") as nodes, and "applicable to" and "associated with" as edges, and builds a network structure through a graph database (such as Neo4j). For example, the record of "a certain strategy successfully repaired a link failure on a cargo ship in the Bohai Sea" is converted into an associated edge in the graph "strategy node → navigation area node → ship type node", and finally a repair strategy graph containing strategy-attribute association relationships is formed.

[0084] Step C2, extract the semantic content of the failure information, and detect the first candidate repair strategy matching the semantic content from the repair strategy graph.

[0085] Specifically, the semantic content of the failure information is the text description of the potential failure (such as "high delay of ship-shore transmission link"), and the first candidate repair strategy is a set of strategies related to the semantic content in the graph. In implementation, first, natural language processing (NLP) technology is used to perform word segmentation and keyword extraction on the failure description (such as "transmission link" and "delay"), and then a semantic similarity algorithm (such as the BERT model) is used to calculate the matching degree of the keywords and the strategy labels in the graph (such as "link optimization" and "transmission delay handling"). For example, when the failure information is "abnormal positioning signal strength", the system extracts keywords such as "positioning signal" and "abnormal", retrieves strategies whose labels contain "positioning signal repair" and "signal enhancement strategy" in the graph, and generates a first candidate repair strategy list according to the similarity, ensuring that the strategy semantics are highly related to the failure description.

[0086] Step C3, obtain the spatio-temporal association features corresponding to the failure information, and detect the second candidate repair strategy matching the spatio-temporal association features from the repair strategy graph.

[0087] Specifically, the spatio-temporal correlation feature includes the time (e.g., "2 a.m.") and space (e.g., "120° east longitude and 25° north latitude") information of the fault occurrence, and the second candidate repair strategy is a set of strategies in the graph that match the spatio-temporal feature. In implementation, first, the current position is obtained through the shipborne GPS or Beidou system, and the timestamp (e.g., system log record) of the fault occurrence is combined to form spatio-temporal data (e.g., "30° north latitude and 120° east longitude on June 30, 2025"). Then, the spatio-temporal index (e.g., R-tree) is used to search for strategies with similar spatio-temporal labels in the graph, for example, to find "link repair strategies effective in the night period in the Pacific Ocean", and by comparing the overlap degree (e.g., area coincidence degree, time window matching degree) of the fault spatio-temporal and the spatio-temporal of the historical application of the strategy, the second candidate repair strategy that adapts to the current spatio-temporal environment is screened out, ensuring the spatio-temporal applicability of the strategy.

[0088] Step C4, determining the target repair strategy based on the candidate repair strategies that overlap in the first candidate repair strategy and the second candidate repair strategy.

[0089] Specifically, if there are overlapping strategies, the repair effect of the strategy is simulated through the digital twin model: for example, the first repair effect (e.g., link recovery time, resource occupancy rate) and the second repair effect of the overlapping strategy "switching to the standby link" on the current platform are simulated respectively, and combined with the historical success rate data, the target repair strategy (e.g., "switching to the standby sensor first, and then restarting the acquisition program") is combined according to the rule of "first executing the strategy with the highest success rate, and then supplementing auxiliary strategies". If there are no overlapping strategies, the system statistics the historical repair success rates (e.g., obtaining the success times of each strategy in similar faults from the shore-based system) of the two types of candidate strategies, and selects the strategy with the highest success rate as the target repair strategy. For example, the success rate of the first candidate strategy is 60%, and the success rate of the second candidate strategy is 75%, then the second candidate strategy is determined as the target strategy, ensuring the repair effectiveness. Finally, the target repair strategy will be converted into a cooperative control instruction executable by the shipborne platform, and executed through the shore-based system.

[0090] In the embodiments of the present application, the target repair strategy is determined based on the candidate repair strategies that overlap in the first candidate repair strategy and the second candidate repair strategy, including: simulating the first repair effect of the shipborne platform repairing the potential fault information according to the first candidate repair strategy; and simulating the second repair effect of the shipborne platform repairing the potential fault information according to the second candidate repair strategy; combining the first candidate repair strategy and the second candidate repair strategy based on the first repair effect and the second repair effect to obtain the target repair strategy.

[0091] Specifically, the first repair effect and the second repair effect are respectively simulation execution results of two types of strategies in a virtual environment, and the target repair strategy is an integrated optimal strategy combination. First, a digital twin model of the ship-borne platform is constructed by using tools such as Unity or ANSYS, which includes mathematical modeling of hardware components (such as sensors, communication modules) and business processes (such as communication protocols of data acquisition links). For the first candidate strategy, its parameters (such as backup sensor ID, switching timing) are input into the model, and the index change data (such as link recovery time, CPU load fluctuation) are collected after simulation execution, forming the quantitative results of the first repair effect (such as “switching time 200 ms, CPU instantaneous occupancy rate increases by 15% ”); Similarly, when the second candidate strategy (such as “adjusting the bandwidth allocation of ship-shore transmission”) is input with space-time parameters (such as current latitude and longitude, timestamp), the execution process in a specific environment is simulated, and the second repair effect such as transmission delay reduction amplitude and packet loss rate change is recorded.

[0092] Subsequently, the strategy combination is performed based on the two types of simulation effects: if the first strategy quickly recovers the link but consumes more resources, and the second strategy optimizes the transmission efficiency but takes longer to recover, then the combination is performed in the order of “first, execute the first strategy to restore the basic function, and then execute the second strategy to optimize the performance”; if there is a parameter conflict between the two (such as resource preemption between bandwidth allocation strategy and sensor switching), then the strategy parameters are adjusted (such as reducing the bandwidth threshold during switching) by using genetic algorithms or reinforcement learning models to generate compatible target repair strategies. During the combination process, the strategy combination effects of similar scenarios in the historical fault case library (such as the success rate of “switching + bandwidth adjustment”) are referred to to ensure the feasibility of the combined strategy, and finally a standardized instruction package containing the execution order, parameter configuration, and emergency fallback mechanism is formed.

[0093] Embodiments of the present application build a repair strategy graph by using the fault repair strategies and attributes of other ship-borne platforms, break the traditional system running limit in isolation, and enhance the shore-based collaboration capability; extract the fault information semantic content to match the first candidate strategy, combine the space-time correlation features to match the second candidate strategy, change the traditional single threshold alarm mode, incorporate the business scenario and space-time dimension analysis, and improve the monitoring accuracy; simulate the repair effects of different candidate strategies and generate the target strategy by combination, change the limitations of the traditional single restart strategy, form a dynamically adapted repair scheme, and solve the problem of low repair efficiency.

[0094] In the embodiments of the present application, the method further includes steps D1-D2:

[0095] Step D1, if there is no overlapping candidate repair strategy in the first candidate repair strategy and the second candidate repair strategy, the repair success rates of the first candidate repair strategy and the second candidate repair strategy are obtained respectively.

[0096] Specifically, the repair success rate refers to the probability of the strategy successfully repairing in the history similar fault. The shore-based system queries the historical execution record of the repair strategy atlas, and calculates the ratio of the success times to the total execution times of each type of strategy in similar fault scenarios (such as "strategy A succeeds 8 times in 10 similar faults, and the success rate is 80%"). For strategies lacking sufficient historical data, the system will combine a machine learning model (such as random forest) to predict the success rate, input parameters including strategy type, fault characteristics, platform attributes, etc., and finally generate a quantitative success rate value (such as 0.75), providing data support for subsequent strategy selection.

[0097] Step D2, the candidate repair strategy with the highest repair success rate in the first candidate repair strategy and the second candidate repair strategy is selected as the target repair strategy.

[0098] Specifically, first, compare the success rate values of the two types of strategies (such as the first candidate strategy success rate 65%, the second candidate strategy success rate 78%), and select the strategy with a higher value as the target strategy. If there are multiple strategies with the same success rate, further reference to auxiliary indicators such as strategy execution efficiency (such as repair time consumption), resource occupancy rate (such as CPU consumption) is made for screening (such as selecting the strategy with shorter time consumption). After determining the target strategy, the system converts it into a cooperative control instruction executable by the shipborne platform, the instruction contains strategy ID, execution parameters (such as backup link ID, resource adjustment threshold) and timing requirements, and is encrypted and issued to the shipborne BITE module by the shore-based system, to ensure the effectiveness and priority of fault repair.

[0099] Figure 3 is a flowchart of a ship-shore cooperative communication method according to an embodiment of the present application, as shown in Figure 3 , the flowchart includes the following steps:

[0100] Step S201, if the shipborne platform has a self-repair strategy matching the potential fault information, monitor the fault repair situation of the shipborne platform.

[0101] In the embodiment of the present application, when the ship-borne platform has a self-repair strategy matching the potential fault information, the strategy execution engine is first triggered to call the corresponding repair module (such as service restart, parameter adjustment), and a multi-dimensional monitoring mechanism is started at the same time: a fluctuation curve of basic indicators such as CPU and memory is collected in real time, and a repair effect evaluation matrix is constructed in combination with business customized indicators (such as data acquisition link recovery state); the whole process call chain of strategy execution is tracked by using distributed tracking technology (such as OpenTelemetry), and the execution time and return state of key nodes are recorded; the repair process data is synchronized to the shore-based system by the edge computing node at a second-level frequency, forming a three-dimensional monitoring data stream containing time stamp, indicator change and strategy execution log, and the fault repair progress (such as process survival state after service restart, performance indicator recovery trend after parameter adjustment) is judged in real time.

[0102] In step S202, if the fault repair of the ship-borne platform fails, the self-repair strategy is analyzed to determine the cause of the repair failure.

[0103] In the embodiment of the present application, if the monitoring data indicates that the fault repair fails (such as the key indicators not restored to within the threshold value, the business function continuously abnormal), a hierarchical diagnosis mechanism is started: first, the execution log of the self-repair strategy is analyzed to check whether there is an instruction execution error (such as insufficient permission leading to restart failure) or parameter configuration deviation (such as the memory threshold value set too low);

[0104] Secondly, by comparing the indicator feature vectors before and after repair, the abnormal detection algorithm (such as Isolation Forest) is used to locate the key indicator combination leading to failure (such as CPU usage rate not decreasing but rising accompanied by disk IO blocking); and then the strategy execution process is simulated in combination with the digital twin system to verify whether the strategy is invalid due to the current running condition of the ship-borne platform (such as high load concurrent business), and finally a three-dimensional failure cause analysis situation including strategy execution defects, environmental factor influence and indicator correlation anomaly is formed.

[0105] In step S203, the update content of the self-repair strategy is generated based on the cause, and the update content is sent to the ship-borne platform, so that the ship-borne platform updates the self-repair strategy based on the update content, and repairs the potential fault information by using the updated self-repair strategy.

[0106] In the embodiment of the present application, if the strategy parameter configuration is improper, the Bayesian optimization algorithm is used to search for the optimal parameter combination (such as adjusting the memory threshold value from 80% to 75%); if there is a defect in the execution process, the state machine model is used to reconstruct the execution logic (such as adding a pre-resource checking step);

[0107] If failure is caused by environmental factors, condition-triggered strategy variants (such as preferentially executing lightweight repair under high load) are generated in combination with real-time working condition data of the ship-borne platform (such as current business load and sea environment parameters). The updated content is sent to the ship-borne platform through an encrypted communication link, and the platform automatically injects the updated content into the strategy engine, completes the strategy version iteration, and immediately enables the updated strategy to re-execute the repair, while feeding back the update effect data to the shore-based platform for continuous optimization of the strategy.

[0108] When there is a matching strategy, the multi-dimensional real-time monitoring of the embodiments of the present application ensures that the repair process is traceable and avoids formality in strategy execution; when repair fails, the hierarchical diagnosis mechanism combines log analysis, index correlation mining and digital twin simulation to accurately locate the strategy defects and environmental impact factors, breaking the blindness of traditional "one-size-fits-all" repair; the cause-based strategy update supports parameter optimization, logic reconstruction and working condition adaptation, so that the self-repairing strategy can dynamically evolve with the running state of the ship-borne platform, and finally form a virtuous cycle of continuous optimization of the strategy, significantly improving the fault repair

[0109] In the embodiments, a ship-shore cooperative communication device is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and contemplated.

[0110] The embodiments provide a ship-shore cooperative communication device, as shown in Figure 4 The device includes:

[0111] The acquisition module 401 is configured to acquire first index data corresponding to basic indexes of main services in the ship-borne platform and second index data corresponding to business customization indexes associated with the ship-borne platform.

[0112] The prediction module 402 is configured to predict potential fault information of the ship-borne platform based on the first index data and the second index data.

[0113] The query module 403 is configured to query whether there is a self-repairing strategy matching the potential fault information in the ship-borne platform.

[0114] The processing module 404 is configured to, if there is no self-repairing strategy matching the potential fault information in the ship-borne platform, acquire a target repair strategy matching the potential fault information from fault repair strategies of other ship-borne platforms communicated by the shore-based device, generate a cooperative control instruction based on the target repair strategy, and send the cooperative control instruction to the ship-borne platform.

[0115] Further, the prediction module 402 is configured to analyze time sequence characteristics of the first index data to obtain time sequence fluctuation rules of the basic index; identify causal coupling characteristics between the second index data of different service customization indexes to obtain correlation relationships between the service customization indexes; generate a composite feature vector based on the time sequence fluctuation rules and the correlation relationships; perform similarity matching between abnormal features in the historical fault case library and the composite feature vector; and if the historical fault case library contains abnormal features matching the composite feature vector, take fault information corresponding to the abnormal features as the potential fault information.

[0116] Further, the apparatus further includes a sending module configured to send the first index data, the second index data, and the composite feature vector to a control terminal if the historical fault case library does not contain abnormal features matching the composite feature vector, where the control terminal is configured to generate a repair strategy based on the first index data, the second index data, and the composite feature vector; receive the repair strategy sent by the control terminal, generate a cooperative control instruction based on the repair strategy, and send the cooperative control instruction to the shipboard platform, where the shipboard platform repairs the potential fault information according to the repair strategy and stores the repair strategy.

[0117] Further, the processing module 404 is configured to build a repair strategy atlas using fault repair strategies of other shipboard platforms and attributes of the other shipboard platforms; extract semantic content of the fault information, and detect a first candidate repair strategy matching the semantic content from the repair strategy atlas; obtain time-space correlation features corresponding to the fault information, and detect a second candidate repair strategy matching the time-space correlation features from the repair strategy atlas; and determine a target repair strategy based on candidate repair strategies that overlap in the first candidate repair strategy and the second candidate repair strategy.

[0118] Further, the apparatus further includes a determination module configured to obtain repair success rates of the first candidate repair strategy and the second candidate repair strategy, respectively, if there is no candidate repair strategy that overlaps in the first candidate repair strategy and the second candidate repair strategy; and take a candidate repair strategy with the highest repair success rate in the first candidate repair strategy and the second candidate repair strategy as the target repair strategy.

[0119] Further, the processing module 404 further includes an analog sub-module configured to simulate a first repair effect of the shipboard platform repairing the potential fault information according to the first candidate repair strategy, and simulate a second repair effect of the shipboard platform repairing the potential fault information according to the second candidate repair strategy; and combine the first candidate repair strategy and the second candidate repair strategy based on the first repair effect and the second repair effect to obtain the target repair strategy.

[0120] In the embodiment of the present application, the device further comprises an updating module configured to monitor the fault repair of the shipboard platform if the shipboard platform has a self-repair strategy matching the potential fault information; analyze the self-repair strategy if the fault repair of the shipboard platform fails, and determine the cause of the repair failure; generate an update content of the self-repair strategy based on the cause, and send the update content to the shipboard platform, so that the shipboard platform updates the self-repair strategy based on the update content, and repairs the potential fault information by using the updated self-repair strategy.

[0121] Referring to Figure 5 , Figure 5 is a structural schematic diagram of an electronic device provided by an optional embodiment of the present application, as shown in Figure 5 , the electronic device comprises one or more processors 10, a memory 20, and an interface for connecting various components, including a high-speed interface and a low-speed interface. Various components are communicatively connected to each other by using different buses, and can be installed on a common mainboard or in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in the memory or on the memory to display graphical information of a GUI on an external input / output device, such as a display device coupled to the interface. In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memories, if necessary. Similarly, multiple electronic devices can be connected, each device providing part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system).

[0122] The processor 10 can be a central processor, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application-specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a generic array logic, or any combination thereof.

[0123] The memory 20 stores instructions executable by the at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0124] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system and applications required by at least one function. The data storage area can store data created by the use of the electronic device according to the presentation of a small program landing page, and the like. In addition, the memory 20 can include a high-speed random access memory, and can further include a non-transitory memory such as at least one of a magnetic disk storage device, a flash memory device, or other non-transitory solid state memory device. In some alternative embodiments, the memory 20 can optionally include a memory that is remotely located with respect to the processor 10, and these remote memories can be connected to the electronic device through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0125] The memory 20 can include a volatile memory such as a random access memory, and can further include a non-volatile memory such as a flash memory, a hard disk, or a solid state disk. The memory 20 can also include a combination of the above-mentioned types of memories.

[0126] The electronic device further includes a communication interface 30 for communication of the electronic device with other devices or communication networks.

[0127] The embodiments of the present application also provide a computer readable storage medium. The above-mentioned method according to the embodiments of the present application can be implemented in hardware, firmware, or as computer code recorded on a storage medium, or stored in a remote storage medium or a non-transitory machine readable storage medium and downloaded to a local storage medium through a network, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, or a solid state disk, and the like. Further, the storage medium can also include a combination of the above-mentioned types of memories. It can be understood that the computer, processor, microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the method shown in the above-mentioned embodiments.

[0128] Although the embodiments of the present application have been described with reference to the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present application, and such modifications and changes are intended to fall within the scope of the appended claims.

Claims

1. A ship-shore cooperative communication method, characterized in that, Applied to shore-based equipment, the method includes: Obtain the first indicator data corresponding to the basic indicators of the main service in the shipborne platform, and the second indicator data corresponding to the business-customized indicators associated with the shipborne platform; Based on the first indicator data and the second indicator data, predict the potential fault information of the shipborne platform; Check whether there is a self-healing strategy in the shipborne platform that matches the potential fault information; If there is no self-repair strategy in the shipborne platform that matches the potential fault information, then a target repair strategy that matches the potential fault information is obtained from the fault repair strategies of other shipborne platforms based on the shore-based equipment communication, a cooperative control command is generated based on the target repair strategy, and the cooperative control command is sent to the shipborne platform.

2. The method according to claim 1, characterized in that, The prediction of potential fault information of the shipborne platform based on the first indicator data and the second indicator data includes: By analyzing the time-series characteristics of the first indicator data, the time-series fluctuation pattern of the basic indicator is obtained; Identify the causal coupling characteristics between the second indicator data of different business customization indicators to obtain the correlation between the business customization indicators; Based on the aforementioned temporal fluctuation patterns and correlations, a composite feature vector is generated; Similarity matching is performed between the abnormal features in the historical fault case database and the composite feature vector; If there is an abnormal feature in the historical fault case library that matches the composite feature vector, then the fault information corresponding to the abnormal feature is taken as the potential fault information.

3. The method according to claim 2, characterized in that, The method further includes: If there is no abnormal feature in the historical fault case database that matches the composite feature vector, then the first indicator data, the second indicator data, and the composite feature vector are sent to the control terminal, wherein the control terminal is used to generate a repair strategy based on the first indicator data, the second indicator data, and the composite feature vector; The system receives a repair strategy sent by the control terminal, generates a collaborative control command based on the repair strategy, and sends the collaborative control command to the shipborne platform. The shipborne platform repairs potential fault information according to the repair strategy and stores the repair strategy.

4. The method according to claim 1, characterized in that, The target repair strategy for obtaining the potential fault information matching the fault repair strategy of other shipborne platforms based on the shore-based equipment communication includes: A repair strategy map is constructed by utilizing the fault repair strategies of other shipborne platforms and the attributes of other shipborne platforms; Extract the semantic content of the fault information, and detect a first candidate repair strategy that matches the semantic content from the repair strategy graph; Obtain the spatiotemporal correlation features corresponding to the fault information, and detect a second candidate repair strategy that matches the spatiotemporal correlation features from the repair strategy map; The target repair strategy is determined based on the candidate repair strategies that overlap between the first and second candidate repair strategies.

5. The method according to claim 4, characterized in that, The method further includes: If there is no overlap between the first candidate repair strategy and the second candidate repair strategy, then the repair success rate of the first candidate repair strategy and the second candidate repair strategy are obtained respectively. The candidate repair strategy with the highest repair success rate among the first candidate repair strategy and the second candidate repair strategy is selected as the target repair strategy.

6. The method according to claim 1, characterized in that, The step of determining the target repair strategy based on the overlapping candidate repair strategies in the first and second candidate repair strategies includes: Simulate the first repair effect of the shipborne platform repairing potential fault information according to the first candidate repair strategy; and simulate the second repair effect of the shipborne platform repairing potential fault information according to the second candidate repair strategy; Based on the first repair effect and the second repair effect, the first candidate repair strategy and the second candidate repair strategy are combined to obtain the target repair strategy.

7. The method according to claim 1, characterized in that, The method further includes: If the shipborne platform has a self-healing strategy that matches the potential fault information, then monitor the fault repair status of the shipborne platform. If the fault repair status of the shipborne platform is repair failure, then analyze the self-repair strategy to determine the cause of the repair failure; Based on the aforementioned reasons, an updated version of the self-healing strategy is generated and sent to the shipboard platform, so that the shipboard platform updates the self-healing strategy based on the updated version and uses the updated self-healing strategy to repair potential fault information.

8. A ship-shore collaborative communication device, characterized in that, The device includes: The acquisition module is used to acquire the first indicator data corresponding to the basic indicators of the main service in the shipborne platform, and the second indicator data corresponding to the business-customized indicators associated with the shipborne platform. The prediction module is used to predict potential fault information of the shipborne platform based on the first indicator data and the second indicator data. The query module is used to query whether there is a self-healing strategy in the shipborne platform that matches the potential fault information; The processing module is configured to, if there is no self-repair strategy in the shipborne platform that matches the potential fault information, obtain a target repair strategy that matches the potential fault information from the fault repair strategies of other shipborne platforms based on the shore-based equipment communication, generate a cooperative control command based on the target repair strategy, and send the cooperative control command to the shipborne platform.

9. An electronic device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to perform the method of any one of claims 1 to 7.

Images