Method, device and readable storage medium for determining sensitive ship

Abstract

The application provides a sensitive ship determination method, device and readable storage medium. The method comprises the following steps: in response to a search instruction of a sensitive ship, acquiring sensitive words and spelling variants of the sensitive words according to a preset sensitive word library; constructing an initial sensitive dictionary tree according to the sensitive words and the spelling variants; acquiring ship navigation data of each of a plurality of to-be-detected ships; acquiring to-be-detected sensitive ship data matched with the initial sensitive dictionary tree according to the plurality of ship navigation data and the initial sensitive dictionary tree; constructing a sensitive ship dictionary tree according to the to-be-detected sensitive ship data and the initial sensitive dictionary tree; acquiring target ship navigation data associated with a target search condition carried by the search instruction according to the target search condition and the sensitive ship dictionary tree; and determining a target sensitive ship according to the target ship navigation data. The application realizes the search and screening of the sensitive ship by constructing the sensitive ship dictionary tree and combining spatial features.

Description

Technical Field

[0001] This invention relates to the field of shipping and maritime monitoring technology, and more specifically, to a method, apparatus, and readable storage medium for identifying sensitive vessels. Background Technology

[0002] In the field of maritime data monitoring and network information content security, the supervision of sensitive ship name information typically relies on two main methods: manual inspection and basic keyword filtering. Manual inspection is highly dependent on manpower, and when faced with massive amounts of real-time updated ship data, it suffers from low efficiency, insufficient coverage, and delayed response, easily missing illegal ship names. The basic keyword filtering model has limitations; it cannot address situations where virtual AIS devices use sensitive ship names to commit illegal activities in localized sea areas, and it is difficult to detect sensitive and illegal information that evades routine inspections in a real-time, accurate, and automated manner. Summary of the Invention

[0003] The present invention aims to solve at least one of the technical problems existing in the prior art or related art.

[0004] Therefore, a first aspect of the present invention provides a method for identifying sensitive ships.

[0005] A second aspect of the invention provides a device for identifying sensitive ships.

[0006] A third aspect of the invention provides another device for identifying sensitive ships.

[0007] The fourth aspect of this application proposes a readable storage medium.

[0008] In view of the above, a first aspect of the present invention provides a method for determining sensitive vessels, comprising: responding to a retrieval instruction for a sensitive vessel, acquiring sensitive words and spelling variations of sensitive words according to a preset sensitive word library; constructing an initial sensitive dictionary tree according to the sensitive words and spelling variations; acquiring navigation data of each of a plurality of vessels to be detected; acquiring data of sensitive vessels to be detected that match the initial sensitive dictionary tree according to the plurality of vessel navigation data and the initial sensitive dictionary tree; constructing a sensitive vessel dictionary tree according to the sensitive vessel data to be detected and the initial sensitive dictionary tree; acquiring target vessel navigation data associated with the target retrieval conditions according to the target retrieval conditions carried in the retrieval instruction and the sensitive vessel dictionary tree; and determining the target sensitive vessel according to the target vessel navigation data.

[0009] The search command in this application is initiated by maritime regulatory personnel based on the needs of maritime data monitoring and sensitive information supervision. It is an operational command used to request the system to identify and determine sensitive vessels. It is the starting signal that triggers the entire sensitive vessel determination process and can carry the target search conditions required for subsequent searches.

[0010] The preset sensitive word database is a database that is pre-configured and stored in the system in the field of maritime supervision. It contains various illegal, irregular, sensitive and inappropriate words and serves as the basic data source for obtaining sensitive words and spelling variations.

[0011] Sensitive words are the core, unmodified illegal, irregular, sensitive and inappropriate basic words in the pre-set sensitive word database. They are the core identifiers related to ship names that need to be identified in maritime supervision.

[0012] Spelling variants are various irregular spellings produced in a pre-defined sensitive word database to circumvent regular sensitive word detection. They are variations of sensitive words.

[0013] The initial sensitive dictionary is a multi-branch tree data structure built on sensitive words and their spelling variants. It is designed for fast string retrieval and is the basic data structure for achieving efficient matching of ship names with sensitive words.

[0014] The vessels to be inspected are all vessels within the system that require sensitive information screening and are the targets of maritime supervision.

[0015] Ship navigation data is a collection of various data that characterizes the identity, navigation status, and location information of a ship to be detected. It is the core data basis for identifying sensitive ships.

[0016] The sensitive vessel data to be detected consists of all the navigation data of the vessels whose navigation data matches the initial sensitive dictionary tree. It is the sensitive vessel-related data obtained through preliminary screening.

[0017] The sensitive vessel trie is a specialized trie built upon the initial sensitive trie and the data of sensitive vessels to be detected. It incorporates actual vessel data and is the core data structure for achieving accurate retrieval of target sensitive vessels.

[0018] The target search criteria are the screening conditions set by maritime regulators based on specific regulatory needs and carried in the search instructions. They serve as the specific basis for screening target sensitive vessels.

[0019] The target vessel navigation data is the vessel navigation data associated with the target search conditions in the sensitive vessel dictionary tree, and is the direct data source for identifying the target sensitive vessel.

[0020] The target sensitive vessel is a sensitive vessel that meets the target retrieval criteria and is finally determined through a complete systematic screening process. It is the final result of the entire method.

[0021] The sensitive vessel identification method described in this application solves the core technical problems of how to ensure the accuracy of supervision while avoiding inefficiency, insufficient coverage, and delayed response, as well as the inability of basic keyword filtering mode to accurately identify evasive sensitive vessel names and the difficulty in achieving accurate screening under multiple conditions. It realizes the automation, real-time, accuracy, and efficiency of sensitive vessel identification and determination in maritime supervision.

[0022] This application achieves deep integration of sensitive word matching and ship data retrieval, from a basic sensitive word database to an initial dictionary tree, and then to a sensitive ship dictionary tree incorporating ship data. This significantly improves the efficiency and accuracy of maritime supervision in screening sensitive ships, adapting to the needs of global, massive, and real-time updated ship data supervision, and meeting the requirements of efficient and intelligent modern maritime supervision. Furthermore, this application triggers the entire process through search commands, supports customizable target search conditions, and possesses strong flexibility and practicality, adapting to various practical screening scenarios in maritime supervision.

[0023] In some technical solutions of this application, spelling variations include at least one of character substitution, homophonic rewriting, separator insertion, and abbreviated spelling with missing characters; character substitution includes the form of alternating between numbers and letters, and alternating between special symbols and characters.

[0024] In the above technical solutions, character substitution is a specific form of spelling variation, referring to a variation in which the original characters in sensitive words are replaced with other types of characters. This is a common method used by violators to circumvent sensitive word detection. Homophonic rewriting is a specific form of spelling variation, referring to a variation in which the original characters in sensitive words are replaced with homophones or near-homophones. Separator insertion is a specific form of spelling variation, referring to a variation in which meaningless separators are inserted between characters in sensitive words. Abbreviation and omission is a specific form of spelling variation, referring to a variation in which sensitive words are abbreviated or some characters are omitted. Number and letter substitution is a specific form of character substitution, referring to a substitution method in which letters in sensitive words are replaced with numbers of corresponding shapes or pronunciations, or numbers are replaced with letters. Special symbol and character substitution is a specific form of character substitution, referring to a substitution method in which ordinary characters in sensitive words are replaced with special symbols, or special symbols are replaced with ordinary characters.

[0025] This application further refines the screening scope for sensitive words by clearly defining the specific types of spelling variants and the specific forms of character replacements. This ensures that the system can effectively identify all common circumvention methods used by violators to circumvent sensitive word variations, fundamentally solving the problem of missed detection of variant sensitive words in traditional keyword filtering models from a data perspective. This significantly improves the comprehensiveness and accuracy of sensitive word identification. Simultaneously, the clear definition of spelling variant types provides specific processing objects and directions for subsequent standardization processing, making it more targeted and operable, and laying a data foundation for accurate matching of the subsequent trie.

[0026] In some technical solutions of this application, an initial sensitive dictionary tree is constructed based on sensitive words and spelling variants, including: processing the sensitive words and spelling variants, the processing including at least one of lowercase conversion, avoidance character restoration, and delimiter removal; constructing an initial sensitive dictionary tree with a multi-branch tree structure with a single character as a node based on the processed sensitive words and spelling variants; configuring a status flag bit for the terminal node corresponding to each sensitive word and spelling variant in the initial sensitive dictionary tree; sensitive words and spelling variants with a common prefix share the corresponding node of the initial sensitive dictionary tree, and the status flag bit is used to mark whether the character path from the root node to the corresponding node constitutes a complete sensitive word.

[0027] In the above technical solutions, lowercase conversion is a specific method for processing sensitive words and spelling variants, referring to a standardized processing method that uniformly converts all uppercase characters in sensitive words and spelling variants to lowercase characters. Avoidance character restoration is a specific method for processing sensitive words and spelling variants, referring to a standardized processing method that restores avoidance characters transformed by character substitution or other methods in spelling variants to the original characters of the sensitive words. Separator removal is a specific method for processing sensitive words and spelling variants, referring to a standardized processing method that deletes meaningless separators inserted into sensitive words and spelling variants. A single character, after standardization, constitutes the smallest symbolic unit of sensitive words and spelling variants, and is the node foundation for constructing the initial sensitive dictionary tree, including letters, Chinese characters, numbers, symbols, etc. A multi-branch tree structure is the tree-like data structure adopted by the initial sensitive dictionary tree, referring to a structure where each node in the tree can have multiple child nodes, adapting to the needs of multi-branch string retrieval. The terminating node is the node in the initial sensitive dictionary tree corresponding to the last character of the complete sensitive word or spelling variant, and is the key node identifying the complete sensitive word. The status flag is an identifier configured on the terminal node of the initial sensitive dictionary tree, used to mark whether the character path from the root node to that node constitutes a complete sensitive word. A common prefix is ​​a sequence of characters that share the same starting part among multiple sensitive words or spelling variations. The root node is the starting node of the initial sensitive dictionary tree and is the starting point of all character paths.

[0028] In some technical solutions of this application, the ship navigation data is Automatic Identification System (AIS) data, which includes at least one of the following: the name of the ship to be detected, the Maritime Mobile Service Identifier (MMSI), the call sign, and the real-time location information; the AIS data is the basic data characterizing the identity and navigation status of the ship to be detected.

[0029] In the above technical solution, Automatic Identification System (AIS) data refers to all types of data collected and transmitted by the AIS regarding a vessel's identity, navigation status, location information, etc., and is the specific form of vessel navigation data. Name data is the specific data representing the vessel's name within the AIS data and is a core retrieval field for identifying sensitive vessels. The Maritime Mobile Service Identifier (MMSI) is a digital code used to uniquely identify a vessel within the AIS data, serving as the vessel's exclusive identifier. The call sign is the exclusive identifier used by the vessel in radio communication within the AIS data, and is another important identifier for the vessel. Real-time location information is the information representing the vessel's real-time geographical location within the AIS data and is the core data for spatial range filtering.

[0030] In some technical solutions of this application, sensitive ship data to be detected is obtained based on multiple ship navigation data and an initial sensitive dictionary, including: extracting the name data of each ship to be detected from the Automatic Identification System (AIS) data; performing character-by-character traversal matching based on the name data and the initial sensitive dictionary, and determining the AIS data of the ships to be detected that match the sensitive words as the sensitive ship data to be detected.

[0031] In the above technical solution, character-by-character traversal matching is a specific method for matching the processed ship name data with the initial sensitive dictionary. It refers to starting from the first character of the ship name data and the root node of the initial sensitive dictionary, and sequentially matching each character of the ship name with the corresponding node of the dictionary, traversing the entire character sequence and the dictionary.

[0032] In some technical solutions of this application, a sensitive ship dictionary is constructed based on the sensitive ship data to be detected and an initial sensitive dictionary, including: attaching the pointer of the sensitive ship data to be detected to the corresponding terminal node in the initial sensitive dictionary; adding an invalid marker to the nodes in the initial sensitive dictionary that do not have the pointer of the sensitive ship data to be detected attached, the invalid marker being used to terminate the retrieval of invalid branches during traversal matching; adding skip character and fault tolerance rules to the character matching logic of the initial sensitive dictionary, the skip character and fault tolerance rules including skipping non-key characters and equivalent character matching; and determining the initial sensitive dictionary after adding invalid markers and skip character and fault tolerance rules as the sensitive ship dictionary.

[0033] In the above technical solution, the data pointer is an identifier pointing to the data storage address of the sensitive vessel to be detected. The data pointer allows for quick retrieval of the corresponding sensitive vessel data and is the core identifier for associating the trie with the vessel data. The invalidity marker is an identifier added to nodes in the initial sensitive trie that do not have a data pointer attached. It marks that the node has no corresponding sensitive vessel data and is the core identifier for quickly terminating invalid branches. The character matching logic is the rule and algorithm in the initial sensitive trie used to match vessel name data with trie nodes, and is the core basis of the matching process. The skip character and error tolerance rules are supplementary matching rules added to the character matching logic, including skipping non-key characters and equivalent character matching. These are core rules for improving the ability to identify evasive sensitive words. Skipping non-key characters is a specific form of the skip character and error tolerance rules, referring to the rule of skipping meaningless non-key characters inserted in the vessel name data during the matching process and continuing with subsequent character matching. Equivalent character matching is a specific form of the skip character and error tolerance rules, referring to the rule of matching some characters in the vessel name data with the node characters in the initial sensitive trie according to equivalence relationships during the matching process.

[0034] In some technical solutions of this application, the target retrieval conditions are the maritime regulatory screening conditions carried in the retrieval instructions, including at least one of the following: a single sensitive word, a logical AND condition of multiple sensitive words, a logical OR condition of multiple sensitive words, and a combination of a logical AND or OR condition of multiple sensitive words with a spatial range threshold; the spatial range threshold is the ship spatial coverage range or ship-to-ship distance threshold set in maritime regulation.

[0035] In the above technical solutions, maritime regulatory screening conditions are set by maritime regulators based on specific maritime regulatory needs, such as screening for specific sensitive words, screening for multiple sensitive words, and screening for regionally sensitive vessels. These conditions are used to screen target sensitive vessels. A single sensitive word condition is a specific form of target retrieval condition, referring to a condition that uses only one sensitive word as the screening basis. A logical AND condition for multiple sensitive words is a specific form of target retrieval condition, referring to a condition where multiple sensitive words are simultaneously satisfied as the screening basis; that is, the vessel name must contain all specified sensitive words. A logical OR condition for multiple sensitive words is a specific form of target retrieval condition, referring to a condition where any one of multiple sensitive words is satisfied as the screening basis; that is, the vessel name only needs to contain one of the specified sensitive words. The spatial range threshold is a numerical standard set by maritime regulators based on specific regulatory needs, used to determine whether the spatial location of a vessel meets the requirements, and is the core basis for achieving regionally sensitive vessel screening. The vessel spatial coverage range is the geographical area covered by the real-time location information of multiple vessels, and is a specific form of spatial parameter calculation. The distance threshold between vessels is a value set by maritime regulators to determine whether the distance between two or more vessels meets the sensitive screening criteria. It is a specific form of spatial range threshold.

[0036] A second aspect of this application provides an apparatus for determining sensitive vessels, comprising: a first acquisition module, a first construction module, a second acquisition module, a third acquisition module, a second construction module, a fourth acquisition module, and a first determination module. The first acquisition module is used to, in response to a retrieval instruction for a sensitive vessel, acquire sensitive words and spelling variations of those words according to a preset sensitive word library. The first construction module is used to construct an initial sensitive dictionary tree based on the sensitive words and spelling variations. The second acquisition module is used to acquire navigation data for each of a plurality of vessels to be detected. The third acquisition module is used to acquire data of sensitive vessels to be detected that matches the initial sensitive dictionary tree based on the navigation data of the plurality of vessels and the initial sensitive dictionary tree. The second construction module is used to construct a sensitive vessel dictionary tree based on the data of sensitive vessels to be detected and the initial sensitive dictionary tree. The fourth acquisition module is used to acquire navigation data of a target vessel associated with the target retrieval conditions carried in the retrieval instruction and the sensitive vessel dictionary tree. The first determination module is used to determine a target sensitive vessel based on the navigation data of the target vessel.

[0037] A third aspect of the present invention provides an apparatus for determining a sensitive vessel, comprising: a processor and a memory, wherein the memory stores a program or instructions, and the processor, when executing the program or instructions in the memory, implements the steps of the method for determining a sensitive vessel as described in any of the above-described technical solutions. Therefore, the apparatus for determining a sensitive vessel possesses all the beneficial effects of the method for determining a sensitive vessel as described in any of the above-described technical solutions.

[0038] A fourth aspect of the present invention provides a readable storage medium storing a program or instructions, which, when executed by a processor, implement the steps of the method for determining a sensitive vessel as described in any of the above-described technical solutions. Therefore, the readable storage medium possesses all the beneficial effects of the method for determining a sensitive vessel as described in any of the above-described technical solutions.

[0039] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0040] The above and / or additional aspects and advantages of the present invention will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which:

[0041] Figure 1 This is a flowchart illustrating a method for determining sensitive vessels according to an embodiment of the present invention.

[0042] Figure 2 This is an overall architecture diagram of a sensitive ship detection system corresponding to a sensitive name with spatial characteristics and a ship detection method according to an embodiment of the present invention;

[0043] Figure 3 This is a schematic diagram of ship navigation status and sensitive target monitoring according to an embodiment of the present invention;

[0044] Figure 4 One of the schematic block diagrams of a sensitive vessel determination device according to an embodiment of the present invention;

[0045] Figure 5 This is a second schematic block diagram of a sensitive vessel identification device according to an embodiment of the present invention. Detailed Implementation

[0046] To better understand the above-mentioned objectives, features, and advantages of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0047] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and therefore the scope of protection of the invention is not limited to the specific embodiments disclosed below.

[0048] The following reference Figures 1 to 5 Methods, apparatus, and readable storage media for identifying sensitive ships according to some embodiments of the present invention are described.

[0049] like Figure 1 As shown, this application provides a method for determining sensitive vessels, the steps of which include:

[0050] Step 102: In response to the search command for sensitive ships, obtain sensitive words and their spelling variations according to the preset sensitive word database;

[0051] Step 104: Construct an initial sensitive dictionary tree based on sensitive words and spelling variations;

[0052] Step 106: Obtain the navigation data of each of the multiple vessels to be inspected;

[0053] Step 108: Based on multiple ship navigation data and the initial sensitive dictionary, obtain the sensitive ship data to be detected that matches the initial sensitive dictionary;

[0054] Step 110: Construct a sensitive vessel trie based on the sensitive vessel data to be detected and the initial sensitive trie;

[0055] Step 112: Based on the target search conditions and sensitive vessel dictionary carried by the search instruction, obtain the target vessel navigation data associated with the target search conditions;

[0056] Step 114: Identify the target sensitive vessel based on the target vessel's navigation data.

[0057] The search command in this application is initiated by maritime regulatory personnel based on the needs of maritime data monitoring and sensitive information supervision. It is an operational command used to request the system to identify and determine sensitive vessels. It is the starting signal that triggers the entire sensitive vessel determination process and can carry the target search conditions required for subsequent searches.

[0058] The preset sensitive word database is a database that is pre-configured and stored in the system in the field of maritime supervision. It contains various illegal, irregular, sensitive and inappropriate words and serves as the basic data source for obtaining sensitive words and spelling variations.

[0059] Sensitive words are the core, unmodified illegal, irregular, sensitive and inappropriate basic words in the pre-set sensitive word database. They are the core identifiers related to ship names that need to be identified in maritime supervision.

[0060] Spelling variants are various irregular spellings produced in a pre-defined sensitive word database to circumvent regular sensitive word detection. They are variations of sensitive words.

[0061] The initial sensitive dictionary is a multi-branch tree data structure built on sensitive words and their spelling variants. It is designed for fast string retrieval and is the basic data structure for achieving efficient matching of ship names with sensitive words.

[0062] The vessels to be inspected are all vessels within the system that require sensitive information screening and are the targets of maritime supervision.

[0063] Ship navigation data is a collection of various data that characterizes the identity, navigation status, and location information of a ship to be detected. It is the core data basis for identifying sensitive ships.

[0064] The sensitive vessel data to be detected consists of all the navigation data of the vessels whose navigation data matches the initial sensitive dictionary tree. It is the sensitive vessel-related data obtained through preliminary screening.

[0065] The sensitive vessel trie is a specialized trie built upon the initial sensitive trie and the data of sensitive vessels to be detected. It incorporates actual vessel data and is the core data structure for achieving accurate retrieval of target sensitive vessels.

[0066] The target search criteria are the screening conditions set by maritime regulators based on specific regulatory needs and carried in the search instructions. They serve as the specific basis for screening target sensitive vessels.

[0067] The target vessel navigation data is the vessel navigation data associated with the target search conditions in the sensitive vessel dictionary tree, and is the direct data source for identifying the target sensitive vessel.

[0068] The target sensitive vessel is a sensitive vessel that meets the target retrieval criteria and is finally determined through a complete systematic screening process. It is the final result of the entire method.

[0069] The sensitive vessel identification method described in this application solves the core technical problems of how to ensure the accuracy of supervision while avoiding inefficiency, insufficient coverage, and delayed response, as well as the inability of basic keyword filtering mode to accurately identify evasive sensitive vessel names and the difficulty in achieving accurate screening under multiple conditions. It realizes the automation, real-time, accuracy, and efficiency of sensitive vessel identification and determination in maritime supervision.

[0070] This application achieves deep integration of sensitive word matching and ship data retrieval, from a basic sensitive word database to an initial dictionary tree, and then to a sensitive ship dictionary tree incorporating ship data. This significantly improves the efficiency and accuracy of maritime supervision in screening sensitive ships, adapting to the needs of global, massive, and real-time updated ship data supervision, and meeting the requirements of efficient and intelligent modern maritime supervision. Furthermore, this application triggers the entire process through search commands, supports customizable target search conditions, and possesses strong flexibility and practicality, adapting to various practical screening scenarios in maritime supervision.

[0071] First, the system responds to sensitive vessel search commands initiated by maritime regulators. Using a pre-configured sensitive word database as its data foundation, it extracts core sensitive words and their corresponding spelling variations, providing a complete sensitive word data system for subsequent trie construction. This ensures the screening scope covers both the original sensitive words and various circumventing variations, addressing the issue of missed detections at its source. Second, based on the extracted sensitive words and their spelling variations, an initial sensitive trie is constructed. Leveraging the structural advantages of tries, specifically designed for fast string retrieval, it replaces the traditional keyword list, laying the structural foundation for rapid matching of massive amounts of vessel data. Next, the system acquires the navigation data of all vessels to be detected within the scope, gathering the core data of all screening targets to ensure comprehensiveness. Then, the navigation data of all vessels to be detected is matched against the initial sensitive trie. This initial screening yields sensitive vessel data matching the initial sensitive trie, completing the initial filtering from a massive vessel database to a candidate set of sensitive vessels, significantly reducing the dataset size for subsequent searches. Subsequently, based on the preliminary screening data of sensitive vessels to be detected and the initial sensitive vessel dictionary, a sensitive vessel dictionary integrating actual vessel data is constructed. This deeply integrates the sensitive word matching structure with the actual vessel data, enabling subsequent searches to directly retrieve vessel data quickly based on this dedicated dictionary, solving the efficiency problem of the separation of retrieval and matching in the traditional model. Next, the target search conditions carried in the search instructions are extracted and matched against the sensitive vessel dictionary. The navigation data of the target vessel associated with the target search conditions is obtained from the sensitive vessel dictionary, achieving precise filtering based on custom conditions. Finally, based on the obtained target vessel navigation data, the final target sensitive vessel is determined, completing the entire process of sensitive vessel identification and determination, providing maritime regulators with accurate regulatory targets. This application utilizes the structural advantages of the dictionary to achieve rapid processing of massive amounts of data, achieves deep integration of sensitive word matching and vessel data through two dictionary constructions, and achieves precise filtering through custom search conditions. It solves the shortcomings of the traditional regulatory model from both a process and structural perspective, ultimately achieving automation, real-time processing, accuracy, and efficiency in the determination of sensitive vessels.

[0072] In some embodiments of this application, spelling variations include at least one of character substitution, homophonic rewriting, separator insertion, and abbreviated spelling with missing characters; character substitution includes the form of alternating between numbers and letters, and alternating between special symbols and characters.

[0073] In the above embodiments, character substitution is a specific form of spelling variation, referring to a variation in which the original characters in sensitive words are replaced with other types of characters. This is a common method used by violators to circumvent sensitive word detection. Homophonic rewriting is a specific form of spelling variation, referring to a variation in which the original characters in sensitive words are replaced with homophones or near-homophones. Separator insertion is a specific form of spelling variation, referring to a variation in which meaningless separators are inserted between characters in sensitive words. Abbreviation and omission is a specific form of spelling variation, referring to a variation in which sensitive words are abbreviated or some characters are omitted. Number and letter substitution is a specific form of character substitution, referring to a substitution method in which letters in sensitive words are replaced with numbers of corresponding shapes or pronunciations, or numbers are replaced with letters. Special symbol and character substitution is a specific form of character substitution, referring to a substitution method in which ordinary characters in sensitive words are replaced with special symbols, or special symbols are replaced with ordinary characters.

[0074] This application further refines the screening scope for sensitive words by clearly defining the specific types of spelling variants and the specific forms of character replacements. This ensures that the system can effectively identify all common circumvention methods used by violators to circumvent sensitive word variations, fundamentally solving the problem of missed detection of variant sensitive words in traditional keyword filtering models from a data perspective. This significantly improves the comprehensiveness and accuracy of sensitive word identification. Simultaneously, the clear definition of spelling variant types provides specific processing objects and directions for subsequent standardization processing, making it more targeted and operable, and laying a data foundation for accurate matching of the subsequent trie.

[0075] When retrieving spelling variants from a pre-defined sensitive word database, the system explicitly includes character substitution, homophonic rewriting, separator insertion, and abbreviation / omission within the scope of spelling variants. It also specifies the substitution of numbers and letters, and special symbols and characters, as concrete forms of character substitution. This ensures that the acquired spelling variants comprehensively cover various sensitive word transformations commonly used by violators in maritime supervision, guaranteeing the integrity of the sensitive word data system. During subsequent standardization of spelling variants, the system can employ corresponding processing methods based on the specific form of each variant. For example, it can restore characters after substitution, remove separators after insertion, and correct homophonic rewriting. This ensures that all transformed sensitive words can be restored to standard core sensitive words, guaranteeing accurate identification of various transformed sensitive words in the subsequent matching process based on the initial sensitive word dictionary, avoiding missed detections due to sensitive word transformation. By clearly defining the specific types of spelling variants, the system achieves comprehensive coverage and accurate restoration of various circumvention-style sensitive words, ensuring the comprehensiveness of sensitive word identification from the data source, thereby improving the screening accuracy of the entire sensitive vessel identification process.

[0076] In one embodiment, in a real-world maritime regulatory scenario, if the sensitive word is "QB", its homophonic spelling variant can be "QB", the spelling variant with inserted separators can be "QB", and the spelling variant with omitted characters in the abbreviation can be "Q". If the sensitive word is "zxck", its character substitution variant with alternating numbers and letters can be "z4ck", and the character substitution variant with alternating special symbols and characters can be "zck". The system includes all of the above variants in the scope of spelling variant acquisition. After standardization, "QB" is restored to "QB", the separator in "QB" is removed to obtain "QB", "z4ck" is restored to "zxck", and "zck" is restored to "zxck", ensuring that the ship name containing the above-mentioned variant words can be accurately identified in the subsequent matching process.

[0077] In some embodiments of this application, an initial sensitive dictionary is constructed based on sensitive words and spelling variants, including: processing the sensitive words and spelling variants, the processing including at least one of lowercase conversion, avoidance character restoration, and separator removal; constructing an initial sensitive dictionary with a multi-branch tree structure with individual characters as nodes based on the processed sensitive words and spelling variants; configuring a status flag bit for the terminal node corresponding to each sensitive word and spelling variant in the initial sensitive dictionary; sensitive words and spelling variants with a common prefix share the corresponding node of the initial sensitive dictionary, and the status flag bit is used to mark whether the character path from the root node to the corresponding node constitutes a complete sensitive word.

[0078] In the above embodiments, lowercase conversion is a specific method for processing sensitive words and spelling variants, referring to a standardized processing method that uniformly converts all uppercase characters in sensitive words and spelling variants to lowercase characters. Avoidance character restoration is a specific method for processing sensitive words and spelling variants, referring to a standardized processing method that restores avoidance characters transformed by character substitution or other methods in spelling variants to the original characters of the sensitive words. Separator removal is a specific method for processing sensitive words and spelling variants, referring to a standardized processing method that deletes meaningless separators inserted into sensitive words and spelling variants. A single character, after standardization, constitutes the smallest symbolic unit of sensitive words and spelling variants, and is the node basis for constructing the initial sensitive dictionary tree, including letters, Chinese characters, numbers, symbols, etc. The multi-branch tree structure is the tree-like data structure adopted by the initial sensitive dictionary tree, referring to a structure where each node in the tree can have multiple child nodes, adapting to the needs of multi-branch string retrieval. The terminating node is the node in the initial sensitive dictionary tree that corresponds to the last character of the complete sensitive word or spelling variant, and is the key node identifying the complete sensitive word. The status flag is an identifier configured on the terminal node of the initial sensitive dictionary tree, used to mark whether the character path from the root node to that node constitutes a complete sensitive word. A common prefix is ​​a sequence of characters that share the same starting part among multiple sensitive words or spelling variations. The root node is the starting node of the initial sensitive dictionary tree and is the starting point of all character paths.

[0079] First, the system standardizes sensitive words and their spelling variants obtained from a pre-defined sensitive word database. This is achieved by converting all characters to lowercase to eliminate matching errors caused by case differences, restoring transformed characters to their original form through character restoration, and removing meaningless delimiters. This ensures all sensitive words and spelling variants are converted into standard, uniform character sequences, providing a standardized data foundation for subsequent trie construction and matching. Second, based on the standardized sensitive words and spelling variants, individual characters constituting these sequences are extracted. Using these individual characters as nodes, an initial sensitive trie is constructed according to a multi-branch tree structure, ensuring each node uniquely corresponds to a single character. Character paths from the root node to each node correspond to sensitive words or sensitive word prefixes. Third, in the initial sensitive trie, a status flag is configured for the terminal node corresponding to each sensitive word and spelling variant. This status flag clearly indicates whether the character path from the root node to that node is a complete sensitive word, achieving accurate differentiation between complete sensitive words and prefixes. Meanwhile, during the construction process, for multiple sensitive words and spelling variations with a common prefix, they share the node corresponding to the common prefix. Branch nodes are only built based on different characters after the common prefix is ​​exhausted, avoiding the construction of duplicate nodes and significantly reducing the number of nodes. The standardized character sequence ensures that there are no formatting or deformation errors during the matching process. The multi-branch tree structure combined with the single-character node design adapts to the needs of fast string retrieval. The shared nodes for common prefixes save memory space, and the status flag avoids misjudgments. The combination of these aspects gives the initial sensitive dictionary tree the characteristics of efficient storage and accurate and fast matching, laying a solid structural foundation for the initial screening of massive ship data.

[0080] In one embodiment, if the sensitive words are "quad" and "quadmapan", and their common prefix is ​​"quad", after the system performs lowercase conversion (if uppercase exists), the individual characters are extracted as "q, u, a, d" and "q, u, a, d, m, a, p, a, n". When constructing the initial sensitive dictionary tree, the root node is constructed first, then the "q" node is constructed from the root node, the "u" node is constructed from the "q" node, the "a" node is constructed from the "u" node, and the "d" node is constructed from the "a" node. The "d" node is the terminal node corresponding to "quad", and its status flag is configured to mark it as a complete sensitive word. The "m" node is constructed from the "d" node, and then the "a, p, a, n" nodes are constructed in sequence. The last "n" node is the terminal node corresponding to "quadmapan", and its status flag is configured to mark it as a complete sensitive word. The two share the nodes corresponding to "q, u, a, d", so there is no need to construct them repeatedly, which greatly saves the memory space for node storage. During the matching process, if the character sequence in the ship name is "qua", when traversing to the "a" node, because this node does not have a status flag, the system determines it as a sensitive word prefix and does not trigger the sensitive ship flag. If the character sequence is "quad", when traversing to the "d" node, because this node has a status flag, the system determines it as a complete sensitive word and triggers the sensitive ship flag, effectively avoiding false positives.

[0081] In some embodiments of this application, the ship navigation data is Automatic Identification System (AIS) data, which includes at least one of the following: the name of the ship to be detected, the Maritime Mobile Service Identifier (MMIS), the call sign, and the real-time location information; the AIS data is the basic data characterizing the identity and navigation status of the ship to be detected.

[0082] In the above embodiments, Automatic Identification System (AIS) data refers to all types of data collected and transmitted by the AIS regarding a vessel's identity, navigation status, location information, etc., and is a specific form of vessel navigation data. Name data is the specific data representing the vessel's name within the AIS data and is a core retrieval field for identifying sensitive vessels. The Maritime Mobile Service Identifier (MMSI) is a digital code used to uniquely identify a vessel within the AIS data, serving as the vessel's exclusive identifier. The call sign is the exclusive identifier used by the vessel in radio communication within the AIS data, and is another important identifier for the vessel. Real-time location information is the information representing the vessel's real-time geographical location within the AIS data and is the core data for spatial range filtering.

[0083] The system explicitly defines vessel navigation data as data from the Automatic Identification System (AIS). This data is collected and transmitted in real time by the AIS, ensuring its authority and real-time nature. This guarantees that the data acquired by the system accurately reflects the actual state of the vessel, providing a reliable data foundation for subsequent screening. Furthermore, the system specifies that AIS data must include at least name data, Maritime Mobile Service (MMSS) identification code, call sign, and real-time location information. Name data serves as the core search field, directly matching the initial sensitive word dictionary. The system extracts name data to perform sensitive word matching and screening. The MMSS identification code and call sign serve as unique identifiers for each vessel, allowing the system to uniquely identify vessels and avoid misjudging sensitive vessels due to duplicate names. Real-time location information represents the vessel's real-time geographical location, providing crucial data for calculating spatial distance and coverage when spatial range thresholds are included in subsequent target search conditions. This enables the system to achieve precise screening based on spatial features. By defining the specific form and content of ship navigation data, the system gathers all the core data required for sensitive ship identification, ensuring the accuracy and comprehensiveness of the screening from a data perspective and providing data support for the smooth implementation of the entire sensitive ship identification process.

[0084] In one embodiment, in a real-world maritime regulatory scenario, the system acquires Automatic Identification System (AIS) data for a vessel to be inspected. The name data is "f4ck ship," the Maritime Mobile Service Identifier (MMSI) is "123456789," the call sign is "ABC," and the real-time location information is "30°N, 120°E." The system performs sensitive word matching based on the name data, identifies sensitive words after standardization, and simultaneously determines the vessel's unique identity using the MMSI "123456789" and call sign "ABC" to avoid confusion with other vessels with the same name. If the target search criteria include a spatial range threshold, the system uses the real-time location information "30°N, 120°E" to calculate spatial parameters for accurate filtering.

[0085] In some embodiments of this application, based on multiple ship navigation data and an initial sensitive dictionary, the process of obtaining sensitive ship data to be detected that matches the initial sensitive dictionary includes: extracting the name data of each ship to be detected from the Automatic Identification System (AIS) data; performing character-by-character traversal matching based on the name data and the initial sensitive dictionary, and determining the AIS data of the ships to be detected that match the sensitive words as the sensitive ship data to be detected.

[0086] In the above embodiments, character-by-character traversal matching is a specific method for matching the processed ship name data with the initial sensitive dictionary. It refers to starting from the first character of the ship name data and the root node of the initial sensitive dictionary, and sequentially matching each character of the ship name with the corresponding node of the dictionary, traversing the entire character sequence and the dictionary.

[0087] This application first extracts the name data of each vessel to be detected from the acquired Automatic Identification System (AIS) data of all vessels to be detected. The matching criteria are focused on the name data as the core search field for sensitive words, eliminating interference from other irrelevant data, reducing data processing volume, and improving matching efficiency. Subsequently, the extracted name data is traversed and matched character by character against the initial sensitive dictionary tree. Starting from the first character of the name data and the root node of the initial sensitive dictionary tree, each character of the name data is matched against the corresponding node in the dictionary tree. If the current character matches a node in the dictionary tree, the traversal continues to the next character and the next level node in the dictionary tree. If the match fails, the matching of that vessel's name is terminated, and the matching of the next vessel continues. If, during the traversal of a certain character in the name data, the corresponding dictionary tree node is a termination node configured with a status flag, then the vessel name is determined to contain a sensitive word, and all AIS data corresponding to that vessel is identified as sensitive vessel data to be detected. By focusing on core name data and adopting a character-by-character traversal matching method adapted to the trie structure, the system can quickly and accurately filter out sensitive ship data containing sensitive words from massive ship data, complete the initial screening, significantly reduce the size of the dataset for subsequent retrieval, and improve the processing efficiency of the entire process.

[0088] In one embodiment, the system acquires Automatic Identification System (AIS) data for 1000 vessels to be detected, and sequentially extracts the name data of each vessel. For example, if a vessel's name is "lapan123", the system performs a character-by-character traversal matching of this name data against an initial sensitive dictionary. Starting from the root node, it sequentially matches "l", "a", "p", "a", and "n". When it reaches node "n", which is a terminal node with a configured status flag, the system determines that the vessel's name contains a sensitive word and identifies all AIS data corresponding to that vessel as sensitive vessel data to be detected. Other vessels whose name data fails to match the initial sensitive dictionary or whose traversal does not reach a terminal node are not included in the sensitive vessel data to be detected. Finally, 50 vessels containing sensitive words are selected from the 1000 vessels, completing the initial screening. Subsequent processing only targets the data of these 50 vessels, significantly improving processing efficiency.

[0089] In some embodiments of this application, a sensitive vessel dictionary is constructed based on the sensitive vessel data to be detected and an initial sensitive dictionary, including: attaching a pointer to the sensitive vessel data to be detected to the corresponding terminal node in the initial sensitive dictionary; adding an invalidation flag to nodes in the initial sensitive dictionary that do not have a pointer to the sensitive vessel data to be detected attached, the invalidation flag being used to terminate the retrieval of invalid branches during traversal matching; adding skip character and error tolerance rules to the character matching logic of the initial sensitive dictionary, the skip character and error tolerance rules including skipping non-key characters and equivalent character matching; and determining the initial sensitive dictionary after adding invalidation flags and skip character and error tolerance rules as the sensitive vessel dictionary.

[0090] In the above embodiments, the data pointer is an identifier pointing to the data storage address of the sensitive vessel to be detected. The data pointer allows for quick retrieval of the corresponding sensitive vessel data and is the core identifier for associating the trie with the vessel data. The invalidity flag is an identifier added to nodes in the initial sensitive trie that do not have a data pointer attached. It marks that the node has no corresponding sensitive vessel data and is the core identifier for quickly terminating invalid branches. The character matching logic is the rule and algorithm in the initial sensitive trie used to match vessel name data with trie nodes, and is the core basis of the matching process. The skip character and error tolerance rules are supplementary matching rules added to the character matching logic, including skipping non-key characters and equivalent character matching. These are core rules for improving the ability to identify evasive sensitive words. Skipping non-key characters is a specific form of the skip character and error tolerance rules, referring to the rule of skipping meaningless non-key characters inserted in the vessel name data during the matching process and continuing with subsequent character matching. Equivalent character matching is a specific form of the skip character and error tolerance rules, referring to the rule of matching some characters in the vessel name data with the node characters in the initial sensitive trie according to equivalence relationships during the matching process.

[0091] This application, by clearly defining the specific construction steps of the sensitive vessel trie, achieves deep integration between the initial sensitive trie and the data of sensitive vessels to be detected, constructing a dedicated data structure for sensitive vessel retrieval, significantly improving the efficiency of subsequent target retrieval. Attaching data pointers allows the trie to directly link with actual vessel data, enabling rapid data retrieval. Adding invalidation markers allows for quick termination of invalid branch traversal during the retrieval process, further improving retrieval efficiency. The addition of skip characters and error-tolerance rules enhances the system's ability to identify various types of circumvented sensitive words, effectively solving the problem of missed detection caused by the insertion of non-key characters or equivalent character transformations in vessel names, improving the accuracy of screening. This application first attaches the data pointers of the sensitive vessel data to be detected obtained from the initial screening to the corresponding terminal nodes in the initial sensitive trie, establishing a connection between each terminal node containing sensitive words and the corresponding actual vessel data, achieving deep integration between the initial sensitive trie and the data of sensitive vessels to be detected. During subsequent retrieval, after matching a terminal node, the corresponding vessel data can be quickly retrieved through the data pointers, eliminating the need to search through massive amounts of data and significantly improving retrieval efficiency. Next, invalidation markers are added to nodes in the initial sensitive dictionary that do not have pointers to the sensitive vessel data to be detected. During subsequent retrieval and matching, when the system traverses to a node with an invalidation marker, it can directly terminate the traversal of that branch, avoiding invalid traversals of branches without relevant vessel data, reducing the number of traversals, and improving retrieval efficiency. Then, skipping and error-tolerance rules are added to the character matching logic of the initial sensitive dictionary. The skipping non-critical character rule allows the system to ignore meaningless separators, spaces, and other non-critical characters inserted in the vessel name during the matching process, continuing the matching of subsequent characters. The equivalent character matching rule allows the system to match numbers and special symbols in the vessel name with letters and Chinese characters in the dictionary according to equivalence relationships, such as matching "4" with "a" and "" with "c". By attaching data pointers, adding invalidation markers, and implementing skipping and error-tolerance rules, the system transforms the initial sensitive dictionary into a sensitive vessel dictionary that integrates vessel data, possesses efficient retrieval capabilities, and strong avoidance identification capabilities, laying the core structural foundation for subsequent accurate and efficient retrieval based on target search conditions.

[0092] In one embodiment, the system attaches the data pointers of the sensitive vessel data to be detected to the "k" node corresponding to "quck" and the "n" node corresponding to "papan" in the initial sensitive trie. It adds invalid markers to other nodes in the tree that do not have attached data pointers, such as "q" and "u". Skip-word and error-tolerance rules are added to the character matching logic. When the vessel name data is "qu ck123", the system skips "" and spaces according to the rule of skipping non-key characters. According to the equivalent character matching rule, "k" is matched normally with subsequent characters, and finally, the system traverses to the "k" termination node, successfully identifying the sensitive word. The corresponding sensitive vessel data to be detected is quickly retrieved through the attached data pointers. During the retrieval process, if the system traverses to other lower-level nodes (without data pointers) of the "q" node with invalid markers, the traversal of that branch is terminated directly, improving retrieval efficiency.

[0093] In some embodiments of this application, the target retrieval conditions are maritime regulatory screening conditions carried in the retrieval instructions, including at least one of the following: a single sensitive word, a logical AND condition of multiple sensitive words, a logical OR condition of multiple sensitive words, and a combination of a logical AND or OR condition of multiple sensitive words with a spatial range threshold; the spatial range threshold is the ship spatial coverage range or ship-to-ship distance threshold set in maritime regulation.

[0094] In the above embodiments, the maritime regulatory screening conditions are set by maritime regulatory personnel based on specific maritime regulatory needs, such as screening for specific sensitive words, screening for multiple sensitive words, and screening for regionally sensitive vessels. These conditions are used to screen target sensitive vessels. A single sensitive word condition is a specific form of target retrieval condition, referring to a condition that uses only one sensitive word as the screening basis. A logical AND condition for multiple sensitive words is a specific form of target retrieval condition, referring to a condition where multiple sensitive words are simultaneously satisfied as the screening basis, i.e., the vessel name must contain all specified sensitive words. A logical OR condition for multiple sensitive words is a specific form of target retrieval condition, referring to a condition where any one of multiple sensitive words is satisfied as the screening basis, i.e., the vessel name only needs to contain one of the specified sensitive words. The spatial range threshold is a numerical standard set by maritime regulatory personnel based on specific regulatory needs, used to determine whether the spatial location of a vessel meets the requirements, and is the core basis for implementing regionally sensitive vessel screening. The vessel spatial coverage range is the geographical area covered by the real-time location information of multiple vessels, and is a specific form of spatial parameter calculation. The distance threshold between vessels is a value set by maritime regulators to determine whether the distance between two or more vessels meets the sensitive screening criteria. It is a specific form of spatial range threshold.

[0095] This application defines the target search criteria as the maritime regulatory screening criteria carried in the search instructions, and limits them to include types such as single sensitive words, logical AND conditions of multiple sensitive words, logical OR conditions of multiple sensitive words, and logical AND / OR conditions of multiple sensitive words combined with spatial range thresholds. At the same time, the spatial range threshold is defined as the ship spatial coverage range or ship-to-ship distance threshold set by maritime regulatory authorities. When a search command carries a single sensitive word condition, the system matches the terminal node corresponding to that sensitive word in the sensitive vessel dictionary, retrieves all vessel data attached to that node, and identifies the target sensitive vessel. When the command carries a logical AND condition for multiple sensitive words, the system matches each sensitive word separately in the sensitive vessel dictionary, retrieves vessel data containing all sensitive words, and identifies the target sensitive vessel. When the command carries a logical OR condition for multiple sensitive words, the system matches each sensitive word separately in the sensitive vessel dictionary, retrieves vessel data containing any one of the sensitive words, and identifies the target sensitive vessel. When the command carries a condition combined with a spatial range threshold, the system first retrieves the corresponding vessel data in the sensitive vessel dictionary based on the logical AND / OR condition of the sensitive words, then extracts real-time location information from this vessel data, calculates the spatial distance between vessels or the spatial coverage of a vessel group, compares the calculation results with the set spatial range threshold, filters out vessel data that meets the spatial range requirements, and finally identifies the target sensitive vessel. By clearly defining the specific types of target search conditions, the system can adopt corresponding screening strategies according to different maritime regulatory needs, achieving multi-scenario adaptation from single sensitive word screening to composite screening of "sensitive words + spatial features". This significantly improves the accuracy and targeting of sensitive vessel identification and effectively solves the problem of regional accurate screening that cannot be achieved in the regulatory model.

[0096] In one embodiment, in a real-world maritime regulatory scenario, if the target search criteria set by maritime regulators are "containing the sensitive words 'abcd' and 'efgk', and the distance between ships is less than 1 nautical mile", this criterion is a logical AND condition combining multiple sensitive words with a ship distance threshold. The system first matches the two sensitive words "abcd" and "efgk" in the sensitive ship dictionary, retrieves all ship data containing both of these sensitive words, and extracts the real-time location information of three ships: Ship 1 "30°00′N, 120°00′E", Ship 2 is located at "30°00′01″N, 120°00′01″E" and Ship 3 is located at "30°01′N, 120°01′E". The system calculates the spatial distance between the ships and finds that the distance between Ship 1 and Ship 2 is 0.02 nautical miles, which is less than 1 nautical mile. The distance between Ship 1 and Ship 3, and between Ship 2 and Ship 3, is 1.1 nautical miles, which is greater than 1 nautical mile. The system identifies Ship 1 and Ship 2 as target sensitive ships, achieving accurate identification of sensitive ship clusters in local sea areas and providing accurate basis for on-site handling by maritime regulatory personnel.

[0097] like Figure 2 As shown, Figure 2 This is the overall architecture of a sensitive vessel discovery system corresponding to sensitive names with spatial characteristics and vessel discovery methods. It is divided into two core modules: the sensitive vessel discovery function on the left client side and the real-time vessel data processing service on the right server side. These two modules work together to support the intelligent identification and monitoring of sensitive vessels. The server side, as the underlying data support, encompasses four core services: vessel position data access, external interface processing, vessel position data management, and sensitive dictionary vessel tree management. It is responsible for the collection, interaction, and governance of multi-source vessel position data, as well as the construction and maintenance of the sensitive dictionary tree, providing data and algorithmic structural support for the entire system. The client side provides practical functions for regulatory users, including sensitive word and region input, real-time vessel position monitoring, sensitive vessel scanning, sensitive vessel query, sensitive vessel positioning and monitoring, sensitive vessel recording, and sensitive vessel alarms. It realizes the entire business process operation from sensitive rule configuration and real-time scanning and identification to target vessel query and tracking and alarm recording. All functions of the client side are based on the underlying data processing and dictionary tree management capabilities of the server side, forming a complete system closed loop of "back-end data support + front-end business operation".

[0098] like Figure 3 As shown, Figure 3 This is a schematic diagram of ship navigation status and sensitive target monitoring, intuitively demonstrating the application effect of the sensitive ship detection system in actual maritime scenarios, such as... Figure 3 Similar monitoring diagrams can use a sea area as a background, employing numerical serial numbers to mark time nodes and letters to identify core monitoring areas. Combined with ship icons, text labels, and line symbols, a dynamic ship monitoring scenario is constructed. The diagram shows two core monitoring areas, A and B. Through visualization, the core functions of the sensitive ship detection system—"area delineation, target identification, trajectory tracking, and multi-target monitoring"—are implemented in a real-world scenario. The combination of numerical serial numbers, geometric areas, and ship labels accurately reflects the complete application process of the system from data collection to situational awareness presentation, providing intuitive evidence of the "sensitive ship positioning and surveillance" and "sensitive area monitoring" functions in the technical solution.

[0099] like Figure 4As shown, an embodiment of this application provides a sensitive vessel determination device 200, including: a first acquisition module 210, a first construction module 220, a second acquisition module 230, a third acquisition module 240, a second construction module 250, a fourth acquisition module 260, and a first determination module 270. The first acquisition module 210 is used to acquire sensitive words and spelling variations of sensitive words according to a preset sensitive word library in response to a sensitive vessel retrieval command; the first construction module 220 is used to construct an initial sensitive dictionary tree according to the sensitive words and spelling variations; the second acquisition module 230 is used to acquire multiple targets to be detected. The system includes: navigation data for each vessel to be detected; a third acquisition module 240, which acquires the sensitive vessel data to be detected that matches the initial sensitive dictionary tree based on multiple vessel navigation data; a second construction module 250, which constructs a sensitive vessel dictionary tree based on the sensitive vessel data to be detected and the initial sensitive dictionary tree; a fourth acquisition module 260, which acquires the target vessel navigation data associated with the target search conditions based on the target search conditions carried by the search instruction and the sensitive vessel dictionary tree; and a first determination module 270, which determines the target sensitive vessel based on the target vessel navigation data.

[0100] The sensitive vessel identification device 200 of this application modularizes and implements the entire process of sensitive vessel identification through the coordinated cooperation of various modules. The first acquisition module 210 provides a complete sensitive word data foundation for the construction of the trie; the first construction module 220 builds an initial sensitive trie for efficient character matching; the second acquisition module 230 collects the core navigation data of the vessel to be detected; the third acquisition module 240 completes the preliminary sensitive screening of massive vessel data; the second construction module 250 integrates the vessel data with the initial trie to form a sensitive vessel trie specifically for retrieval; and the fourth acquisition module 260 implements a sensitive vessel identification device based on custom search conditions. The system now accurately matches and retrieves data, with the first module 270 outputting the final target sensitive vessel. Each module is tightly integrated and logically progressive, fully leveraging the advantages of rapid dictionary tree retrieval and prefix sharing. This effectively solves the problems of low efficiency in traditional maritime supervision, numerous missed detections due to keyword filtering, and the inability to combine spatial features for screening. It achieves automated, real-time, and precise identification and determination of sensitive vessels, significantly improving the efficiency and accuracy of maritime supervision in screening sensitive vessels. Simultaneously, the modular design allows the device to have good scalability and maintainability, adapting to the actual needs of various maritime supervision scenarios for screening sensitive vessels.

[0101] like Figure 5As shown, an embodiment of this application provides a sensitive vessel determination apparatus 300, including a processor 302 and a memory 304. The memory 304 stores a program or instructions. When the processor 302 executes the program or instructions in the memory 304, it implements the steps of the sensitive vessel determination method as described in any of the above embodiments. Therefore, the sensitive vessel determination apparatus 300 possesses all the beneficial effects of the sensitive vessel determination method as described in any of the above embodiments.

[0102] Embodiments of this application provide a readable storage medium storing a program or instructions that, when executed by a processor, implement the steps of the sensitive vessel determination method as described in any of the above embodiments. Therefore, the readable storage medium possesses all the beneficial effects of the sensitive vessel determination method as described in any of the above embodiments.

[0103] In the claims, description, and accompanying drawings of this invention, the term "plural" refers to two or more. Unless otherwise explicitly defined, the terms "upper," "lower," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and simplifying the descriptive process, and are not intended to indicate or imply that the device or element referred to must have the described specific orientation, or be constructed and operated in a specific orientation. Therefore, these descriptions should not be construed as limiting the invention. The terms "connected," "installed," "fixed," etc., should be interpreted broadly. For example, "connected" can be a fixed connection between multiple objects, a detachable connection between multiple objects, or an integral connection; it can be a direct connection between multiple objects or an indirect connection between multiple objects through an intermediate medium. For those skilled in the art, the specific meaning of the above terms in this invention can be understood based on the specific circumstances described above.

[0104] In the claims, description, and accompanying drawings of this invention, the terms "one embodiment," "some embodiments," "specific embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the invention. In the claims, description, and accompanying drawings of this invention, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0105] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for identifying sensitive vessels, characterized in that, include: In response to a search command for sensitive ships, the system retrieves sensitive words and their spelling variations based on a pre-defined sensitive word database. Construct an initial sensitive dictionary tree based on the sensitive words and the spelling variations; Acquire the navigation data of each of the multiple vessels to be inspected; Based on multiple ship navigation data and the initial sensitive dictionary, obtain the sensitive ship data to be detected that matches the initial sensitive dictionary; Based on the data of the sensitive ships to be detected and the initial sensitive dictionary tree, a sensitive ship dictionary tree is constructed; Based on the target search criteria carried by the search instruction and the sensitive ship dictionary, obtain the target ship navigation data associated with the target search criteria; Based on the navigation data of the target vessel, identify the target sensitive vessel; The step of constructing an initial sensitive dictionary tree based on the sensitive words and the spelling variations includes: The sensitive words and spelling variations are processed, including at least one of lowercase conversion, character avoidance restoration, and separator removal. Based on the processed sensitive words and spelling variations, an initial sensitive dictionary tree with a multi-way tree structure using individual characters as nodes is constructed. Configure a status flag bit for each of the sensitive words and spelling variants corresponding to the termination node in the initial sensitive dictionary tree; The sensitive words and spelling variants with a common prefix share the corresponding nodes of the initial sensitive dictionary tree, and the status flag is used to mark whether the character path from the root node to the corresponding node constitutes a complete sensitive word; The step of constructing a sensitive vessel dictionary tree based on the sensitive vessel data to be detected and the initial sensitive vessel dictionary tree includes: The pointer to the sensitive ship data to be detected is attached to the corresponding termination node in the initial sensitive dictionary tree. An invalid mark is added to the nodes in the initial sensitive dictionary tree that do not have the pointer to the sensitive ship data to be detected attached. The invalid mark is used to terminate the search of invalid branches when traversing and matching. Add skip and error tolerance rules to the character matching logic of the initial sensitive dictionary tree. The skip and error tolerance rules include skipping non-key characters and matching equivalent characters. The initial sensitive dictionary tree after adding invalid tags and skip words and fault tolerance rules is determined as the sensitive ship dictionary tree.

2. The method for determining sensitive vessels according to claim 1, characterized in that, The spelling variants include at least one of character substitution, homophonic rewriting, separator insertion, and abbreviation with omission of characters; The character substitution includes the substitution of numbers and letters, and the substitution of special symbols and characters.

3. The method for determining sensitive vessels according to claim 1, characterized in that, The vessel navigation data is Automatic Identification System (AIS) data, which includes at least one of the following: the name of the vessel to be detected, the Maritime Mobile Service (MMSS) identifier, the call sign, and the real-time location information. The Automatic Identification System (AIS) data is the basic data that characterizes the identity and navigation status of the vessel to be detected.

4. The method for determining sensitive vessels according to claim 3, characterized in that, The step of obtaining sensitive ship data to be detected that matches the initial sensitive dictionary based on multiple ship navigation data and the initial sensitive dictionary includes: Extract the name data of each vessel to be detected from the data of the Automatic Identification System (AIS); Based on the name data, a character-by-character traversal matching is performed with the initial sensitive dictionary tree, and the Automatic Identification System (AIS) data of the ships to be detected that match the sensitive words are identified as the sensitive ship data to be detected.

5. The method for determining sensitive vessels according to claim 1, characterized in that, The target search conditions are the maritime regulatory screening conditions carried in the search instructions, including at least one of the following: a single sensitive word, a logical AND condition of multiple sensitive words, a logical OR condition of multiple sensitive words, and a combination of logical AND and OR conditions of multiple sensitive words with a spatial range threshold. The spatial range threshold is the spatial coverage range of ships or the distance threshold between ships set in maritime supervision.

6. A device for identifying sensitive ships, characterized in that, include: The first acquisition module is used to respond to the search command for sensitive ships and acquire sensitive words and their spelling variations according to a preset sensitive word database. The first construction module is used to construct an initial sensitive dictionary tree based on the sensitive words and the spelling variants; The second acquisition module is used to acquire the navigation data of each of the multiple vessels to be detected. The third acquisition module is used to acquire sensitive ship data to be detected that matches the initial sensitive dictionary tree based on multiple ship navigation data and the initial sensitive dictionary tree; The second construction module is used to construct a sensitive ship dictionary tree based on the sensitive ship data to be detected and the initial sensitive dictionary tree; The fourth acquisition module is used to acquire target ship navigation data associated with the target search conditions based on the target search conditions carried by the search instruction and the sensitive ship dictionary tree; The first determining module is used to determine the target sensitive vessel based on the target vessel's navigation data; wherein, the step of constructing an initial sensitive dictionary tree based on the sensitive words and the spelling variants includes: The sensitive words and spelling variations are processed, including at least one of lowercase conversion, character avoidance restoration, and separator removal. Based on the processed sensitive words and spelling variations, an initial sensitive dictionary tree with a multi-way tree structure using individual characters as nodes is constructed. Configure a status flag bit for each of the sensitive words and spelling variants corresponding to the termination node in the initial sensitive dictionary tree; The sensitive words and spelling variants with a common prefix share the corresponding nodes of the initial sensitive dictionary tree, and the status flag is used to mark whether the character path from the root node to the corresponding node constitutes a complete sensitive word; The step of constructing a sensitive vessel dictionary tree based on the sensitive vessel data to be detected and the initial sensitive vessel dictionary tree includes: The pointer to the sensitive ship data to be detected is attached to the corresponding termination node in the initial sensitive dictionary tree. An invalid mark is added to the nodes in the initial sensitive dictionary tree that do not have the pointer to the sensitive ship data to be detected attached. The invalid mark is used to terminate the search of invalid branches when traversing and matching. Add skip and error tolerance rules to the character matching logic of the initial sensitive dictionary tree. The skip and error tolerance rules include skipping non-key characters and matching equivalent characters. The initial sensitive dictionary tree after adding invalid tags and skip words and fault tolerance rules is determined as the sensitive ship dictionary tree.

7. A device for identifying sensitive ships, characterized in that, include: processor; A memory storing programs or instructions, wherein the processor, when executing the programs or instructions in the memory, implements the steps of the method for determining sensitive ships as described in any one of claims 1 to 5.

8. A readable storage medium, characterized in that, The readable storage medium stores a program or instructions that, when executed by a processor, implement the steps of the method for determining a sensitive vessel as described in any one of claims 1 to 5.

Images