Ship inspection method and device based on artificial intelligence

Abstract

The present invention relates to the field of artificial intelligence technology, and discloses a ship inspection method and device based on artificial intelligence, the method comprising: obtaining inspection demand information and ship information of a ship; generating adaptive correction parameters of a pre-trained ship inspection model according to the ship information; correcting the ship inspection model according to the adaptive correction parameters to obtain an adaptive inspection model of the ship; analyzing the inspection result information of the ship according to the adaptive inspection model and the inspection demand information, the inspection result information including the inspection result of the ship and the target guidance strategy of the ship, the target guidance strategy including at least one of the ship's berthing guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transport guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy. It can be seen that the implementation of the present invention can improve the accuracy of ship inspection.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an artificial intelligence-based ship inspection method and device. Background Art

[0002] Regular or irregular inspections of ships will help improve safety in logistics, national defense and other fields, and in turn help improve the safety of people's work and life.

[0003] Existing ship inspections are mainly conducted on-site by law enforcement personnel with certain inspection experience. However, in practice, it is found that law enforcement personnel may have problems such as mental slackness, lack of experience, and subjective assumptions, which may lead to omissions in inspections, thereby making it impossible to guarantee the safety of ships and related objects (such as cargo, users, ship personnel, etc.). Especially in key inspection tasks, the above omissions may bring major safety hazards to people and national property.

[0004] It can be seen that it is particularly important to propose a technical solution to improve the accuracy of ship inspection. Summary of the invention

[0005] The present invention provides a ship inspection method and device based on artificial intelligence, which can improve the accuracy of ship inspection.

[0006] In order to solve the above technical problems, the first aspect of the present invention discloses a ship inspection method based on artificial intelligence, the method comprising:

[0007] Obtain ship inspection requirement information and ship information;

[0008] generating adaptive correction parameters of a pre-trained ship verification model according to the ship information;

[0009] Correcting the ship verification model according to the adaptive correction parameters to obtain an adaptive verification model of the ship;

[0010] According to the adaptive verification model and the verification requirement information, the verification result information of the ship is analyzed, and the verification result information includes the verification result of the ship and the target guidance strategy of the ship, and the target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy.

[0011] As an optional implementation, in the first aspect of the present invention, generating the adaptive correction parameters of the pre-trained ship inspection model according to the ship information includes:

[0012] According to the ship information, matching associated target reference information, the target reference information is used to represent the verification standards of all first verification items related to the ship;

[0013] Determining at least one first verification parameter in a pre-trained ship verification model according to the target reference information, wherein the first verification parameter is associated with the target reference information;

[0014] For each of the first verification parameters, determining whether the first verification parameter satisfies the first matching condition of the target reference information; when it is determined that the first verification parameter does not satisfy the first matching condition of the target reference information, generating an adaptive correction parameter of the ship verification model according to the target reference information and the first verification parameter, wherein the adaptive correction parameter is used to correct the first verification parameter to correct the ship verification model;

[0015] And, the method further comprises:

[0016] When it is determined that all of the first verification parameters meet the first matching condition of the target reference information, the ship verification model is determined as the adaptive verification model, and the operation of analyzing the verification result information of the ship according to the adaptive verification model and the verification requirement information is triggered.

[0017] As an optional implementation manner, in the first aspect of the present invention, the ship information includes at least one of ship ownership information, ship type information, and ship throughput information, and matching the associated target reference information according to the ship information includes:

[0018] Analyzing the carrying capacity information of the ship according to the ship information, wherein the carrying capacity information includes at least one of carrying authority information, carrying article information, and carrying method information;

[0019] Analyze the expected transport mission information and expected transport route information executable by the ship according to the transport capacity information and the acquired historical transport mission information and historical transport route information of the ship;

[0020] Determine the ship information, the carrying capacity information, the historical carrying mission information, the historical carrying route information, the expected carrying mission information and the expected carrying route information as a ship carrying information set of the ship;

[0021] According to the ship transport information set, the associated target reference information is matched.

[0022] As an optional implementation manner, in the first aspect of the present invention, analyzing the verification result information of the ship according to the adaptive verification model and the verification requirement information includes:

[0023] Analyzing at least one second inspection item of the ship according to the inspection requirement information;

[0024] Analyzing the verification purpose information of the ship according to all the second verification items;

[0025] According to the verification purpose information, matching a second verification parameter of the adaptive verification model;

[0026] For each of the second verification items, determining whether the second verification item satisfies a second matching condition of the second verification parameter, and obtaining a first determination result;

[0027] The verification result information of the ship is analyzed based on all the first judgment results and the verification purpose information.

[0028] As an optional implementation manner, in the first aspect of the present invention, analyzing at least one second inspection item of the ship according to the inspection requirement information includes:

[0029] According to the verification requirement information and a preset segmentation analysis model, the verification requirement information is divided into at least one verification requirement sub-information, each verification requirement sub-information corresponding to a different requirement item;

[0030] Obtaining current status information of the ship;

[0031] Determining a first priority of each of the verification requirement sub-information according to the current state information and all of the verification requirement sub-information;

[0032] analyzing at least one second inspection item of the ship according to all the first priorities of all the inspection requirement sub-information;

[0033] And, analyzing at least one second inspection item of the ship according to all the first priorities of all the inspection requirement sub-information includes:

[0034] Analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and a preset semantic analysis model;

[0035] At least one second check item of the ship is determined according to all the first priorities and the semantic information of all the check requirement sub-information, and each of the second check items has a corresponding second priority.

[0036] As an optional implementation manner, in the first aspect of the present invention, analyzing the verification result information of the ship according to all the first judgment results and the verification purpose information includes:

[0037] According to all the first judgment results, screening a third verification item among all the second verification items, the third verification item being used to represent the second verification item that does not satisfy the second matching condition of the second verification parameter;

[0038] Calculating the inspection performance value of the ship according to the second priority level corresponding to all the third inspection items;

[0039] The inspection result information of the ship is analyzed according to the inspection performance value and the inspection purpose information.

[0040] As an optional implementation manner, in the first aspect of the present invention, the target guidance strategy corresponds to the verification purpose information, and the analyzing the verification result information of the ship according to the verification performance value and the verification purpose information includes:

[0041] Calculating a distance value between the verification score value and a preset threshold, wherein the distance value matches the guidance degree of the target guidance strategy;

[0042] Acquiring surrounding environment information of the ship;

[0043] Analyzing the guidance trajectory information of the ship according to the surrounding environment information, the current state information, the distance value and the verification purpose information;

[0044] The verification result information of the ship is analyzed according to the guidance trajectory information and the verification score value.

[0045] The second aspect of the present invention discloses a ship inspection device based on artificial intelligence, the device comprising:

[0046] An acquisition module is used to obtain the ship's inspection requirement information and ship information;

[0047] A generating module, used for generating adaptive correction parameters of a pre-trained ship inspection model according to the ship information;

[0048] A correction module, used for correcting the ship verification model according to the adaptive correction parameter to obtain an adaptive verification model of the ship;

[0049] An analysis module is used to analyze the verification result information of the ship according to the adaptive verification model and the verification requirement information, wherein the verification result information includes the verification result of the ship and the target guidance strategy of the ship, and the target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy.

[0050] As an optional implementation, in the second aspect of the present invention, the specific manner in which the generating module generates the adaptive correction parameters of the pre-trained ship verification model according to the ship information includes:

[0051] According to the ship information, matching associated target reference information, the target reference information is used to represent the verification standards of all first verification items related to the ship;

[0052] Determining at least one first verification parameter in a pre-trained ship verification model according to the target reference information, wherein the first verification parameter is associated with the target reference information;

[0053] For each of the first verification parameters, determining whether the first verification parameter satisfies the first matching condition of the target reference information; when it is determined that the first verification parameter does not satisfy the first matching condition of the target reference information, generating an adaptive correction parameter of the ship verification model according to the target reference information and the first verification parameter, wherein the adaptive correction parameter is used to correct the first verification parameter to correct the ship verification model;

[0054] And, the device further comprises:

[0055] A determination module is used to determine the ship verification model as the adaptive verification model when the generation module determines that all of the first verification parameters meet the first matching condition of the target reference information, and trigger the analysis module to perform the operation of analyzing the verification result information of the ship according to the adaptive verification model and the verification requirement information.

[0056] As an optional implementation, in the second aspect of the present invention, the ship information includes at least one of ship ownership information, ship type information, and ship throughput information, and the specific manner in which the generation module matches the associated target reference information according to the ship information includes:

[0057] Analyzing the carrying capacity information of the ship according to the ship information, wherein the carrying capacity information includes at least one of carrying authority information, carrying article information, and carrying method information;

[0058] Analyze the expected transport mission information and expected transport route information executable by the ship according to the transport capacity information and the acquired historical transport mission information and historical transport route information of the ship;

[0059] Determine the ship information, the carrying capacity information, the historical carrying mission information, the historical carrying route information, the expected carrying mission information and the expected carrying route information as a ship carrying information set of the ship;

[0060] According to the ship transport information set, the associated target reference information is matched.

[0061] As an optional implementation, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the verification result information of the ship according to the adaptive verification model and the verification requirement information includes:

[0062] Analyzing at least one second inspection item of the ship according to the inspection requirement information;

[0063] Analyzing the verification purpose information of the ship according to all the second verification items;

[0064] According to the verification purpose information, matching a second verification parameter of the adaptive verification model;

[0065] For each of the second verification items, determining whether the second verification item satisfies a second matching condition of the second verification parameter, and obtaining a first determination result;

[0066] The verification result information of the ship is analyzed based on all the first judgment results and the verification purpose information.

[0067] As an optional implementation, in the second aspect of the present invention, the specific manner in which the analysis module analyzes at least one second inspection item of the ship according to the inspection requirement information includes:

[0068] According to the verification requirement information and a preset segmentation analysis model, the verification requirement information is divided into at least one verification requirement sub-information, each verification requirement sub-information corresponding to a different requirement item;

[0069] Obtaining current status information of the ship;

[0070] Determining a first priority of each of the verification requirement sub-information according to the current state information and all of the verification requirement sub-information;

[0071] analyzing at least one second inspection item of the ship according to all the first priorities of all the inspection requirement sub-information;

[0072] And, the specific manner in which the analysis module analyzes at least one second inspection item of the ship according to all the first priorities of all the inspection requirement sub-information includes:

[0073] Analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and a preset semantic analysis model;

[0074] At least one second check item of the ship is determined according to all the first priorities and the semantic information of all the check requirement sub-information, and each of the second check items has a corresponding second priority.

[0075] As an optional implementation manner, in the second aspect of the present invention, the specific manner in which the analysis module analyzes the verification result information of the ship according to all the first judgment results and the verification purpose information includes:

[0076] According to all the first judgment results, screening a third verification item among all the second verification items, the third verification item being used to represent the second verification item that does not satisfy the second matching condition of the second verification parameter;

[0077] Calculating the inspection performance value of the ship according to the second priority level corresponding to all the third inspection items;

[0078] The inspection result information of the ship is analyzed according to the inspection performance value and the inspection purpose information.

[0079] As an optional implementation, in the second aspect of the present invention, the target guidance strategy corresponds to the verification purpose information, and the specific manner in which the analysis module analyzes the verification result information of the ship according to the verification score value and the verification purpose information includes:

[0080] Calculating a distance value between the verification score value and a preset threshold, wherein the distance value matches the guidance degree of the target guidance strategy;

[0081] Acquiring surrounding environment information of the ship;

[0082] Analyzing the guidance trajectory information of the ship according to the surrounding environment information, the current state information, the distance value and the verification purpose information;

[0083] The verification result information of the ship is analyzed according to the guidance trajectory information and the verification score value.

[0084] The third aspect of the present invention discloses another ship inspection device based on artificial intelligence, the device comprising:

[0085] A memory storing executable program code;

[0086] a processor coupled to the memory;

[0087] The processor calls the executable program code stored in the memory to execute the artificial intelligence-based ship inspection method disclosed in the first aspect of the present invention.

[0088] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the artificial intelligence-based ship inspection method disclosed in the first aspect of the present invention.

[0089] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0090] In an embodiment of the present invention, verification requirement information and ship information of a ship are obtained; based on the ship information, adaptive correction parameters of a pre-trained ship verification model are generated; based on the adaptive correction parameters, the ship verification model is corrected to obtain an adaptive verification model of the ship; based on the adaptive verification model and the verification requirement information, the verification result information of the ship is analyzed, the verification result information includes the verification result of the ship and the target guidance strategy of the ship, and the target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy. It can be seen that the implementation of the present invention can generate adaptive correction parameters of a pre-trained ship inspection model according to the acquired ship information of the ship, so as to correct the ship inspection model and obtain an adaptive inspection model suitable for the ship. From the perspective of customized inspection model, the ship inspection adaptive pertinence is improved to improve the accuracy of ship inspection, thereby combining the above-mentioned acquired ship inspection demand information to analyze the inspection result information of the ship including the inspection result and the target guidance strategy, wherein the target guidance strategy includes at least one of the following: berthing guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transport guidance strategy, maintenance guidance strategy, compilation guidance strategy and business docking guidance strategy, thereby improving the analysis accuracy of the ship inspection result and the generation accuracy of the target guidance strategy based on the ship inspection result, and can improve the accuracy of ship inspection guidance on the basis of further improving the accuracy of ship inspection from the two dimensions of analyzing the ship inspection result and generating the target guidance strategy, so as to improve the safety of ship use. BRIEF DESCRIPTION OF THE DRAWINGS

[0091] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0092] Figure 1 It is a flow chart of a ship inspection method based on artificial intelligence disclosed in an embodiment of the present invention;

[0093] Figure 2 It is a flowchart of another ship inspection method based on artificial intelligence disclosed in an embodiment of the present invention;

[0094] Figure 3 It is a structural schematic diagram of a ship inspection device based on artificial intelligence disclosed in an embodiment of the present invention;

[0095] Figure 4 It is a structural schematic diagram of another ship inspection device based on artificial intelligence disclosed in an embodiment of the present invention;

[0096] Figure 5 It is a structural schematic diagram of another artificial intelligence-based ship inspection device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0097] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0098] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or end including a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or ends.

[0099] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0100] The present invention discloses a ship inspection method and device based on artificial intelligence, which can generate adaptive correction parameters of a pre-trained ship inspection model according to the acquired ship information of the ship, so as to correct the ship inspection model and obtain an adaptive inspection model adapted to the ship, and improve the pertinence of the ship inspection adaptation from the perspective of customizing the inspection model, so as to improve the accuracy of the ship inspection, thereby combining the above-mentioned inspection demand information of the ship to analyze the inspection result information of the ship including the inspection result and the target guidance strategy, wherein the target guidance strategy includes at least one of the berthing guidance strategy, the risk avoidance guidance strategy, the yaw guidance strategy, the transport guidance strategy, the maintenance guidance strategy, the compilation guidance strategy, and the business docking guidance strategy, so as to improve the analysis accuracy of the ship inspection result and the generation accuracy of the target guidance strategy based on the ship inspection result, and can improve the accuracy of the ship inspection guidance on the basis of further improving the accuracy of the ship inspection from the two dimensions of analyzing the ship inspection result and generating the target guidance strategy, so as to improve the safety of the ship use. The following are described in detail.

[0101] Embodiment 1

[0102] See also Figure 1 , Figure 1 : is a flow chart of a ship inspection method based on artificial intelligence disclosed in an embodiment of the present invention. Figure 1 The described artificial intelligence-based ship inspection method can be applied to customs inspection equipment, estuary checkpoint equipment, bridge inspection equipment, etc., and can also be applied to intelligent devices related to the above devices, including but not limited to geological equipment, cloud equipment, edge computing equipment, relay equipment, base station equipment, urban management equipment, intelligent network equipment, etc., which are not limited in the embodiments of the present invention. Figure 1 As shown, the ship verification method based on artificial intelligence may include the following operations:

[0103] 101. Obtaining the inspection requirement information and ship information of the ship;

[0104] In an embodiment of the present invention, optionally, the above-mentioned verification requirement information and ship information may be obtained by autonomously uploading by the object to which the above-mentioned ship belongs, or may be obtained by autonomously sensing based on the ship after the ship is detected by the device to which the method is applied. In an optional embodiment, the above-mentioned sensing method may be based on radar sensing, or may be based on other sensing signal sensing. The above-mentioned sensing method may add a communication sensing fusion frame structure while transmitting the sensing signal. The above-mentioned communication sensing fusion frame structure is determined according to the above-mentioned ship. Specifically, optionally, it may be based on the position of the above-mentioned ship, the distance to surrounding ships, the size of the ship, etc.

[0105] Further optionally, the above-mentioned ship information may include but is not limited to at least one of ship position information, ship type information, ship displacement information, ship mission information, ship onboard information, ship object information, ship historical mission information, ship location information, ship navigation route information, ship compilation information, and ship service life information.

[0106] 102. Generate adaptive correction parameters of a pre-trained ship inspection model based on the ship information;

[0107] In an embodiment of the present invention, as an optional implementation, the above-mentioned generating the adaptive correction parameters of the pre-trained ship inspection model according to the ship information may include the following operations:

[0108] According to the ship information, the associated target reference information is matched, where the target reference information is used to represent the verification standards of all first verification items related to the ship;

[0109] Determining at least one first verification parameter in a pre-trained ship verification model according to the target reference information, the first verification parameter being associated with the target reference information;

[0110] For each first verification parameter, determine whether the first verification parameter satisfies the first matching condition of the target reference information; when it is determined that the first verification parameter does not satisfy the first matching condition of the target reference information, generate an adaptive correction parameter of the ship verification model according to the target reference information and the first verification parameter, the adaptive correction parameter being used to correct the first verification parameter to correct the ship verification model;

[0111] In this optional embodiment, optionally, the above-mentioned first matching condition can be used to identify that the matching value between the target reference information and the first verification parameter is greater than or equal to a preset matching threshold value, and the above-mentioned matching value is calculated in the process of determining whether the first verification parameter satisfies the first matching condition of the target reference information. The method for calculating the above-mentioned matching value can be one-by-one matching, or it can be obtained by performing further information processing operations on the above-mentioned first verification parameter and the above-mentioned target parameter information. The above-mentioned information processing operations include but are not limited to one or more of decryption, format conversion, denoising, and additional identification.

[0112] It can be seen that the implementation of this optional embodiment can match the target reference information used to represent the verification standards of all first verification items related to the ship according to the above-mentioned ship information obtained, so as to further determine at least one first verification parameter associated with the target reference information in the pre-trained ship verification model. Based on each first verification parameter, when it is judged that the first verification parameter does not meet the first matching condition of the target reference information, an adaptive correction parameter of the ship verification model is generated according to the above-mentioned target reference information and the first verification parameter. The adaptive correction parameter is used to correct the first verification parameter to correct the ship verification model, thereby gradually correcting the ship verification model. From the perspective of customized verification model, the targetedness of ship verification adaptation is further improved to improve the accuracy of ship verification.

[0113] Optionally, the method may further include the following operations:

[0114] When it is determined that all first verification parameters meet the first matching condition of the target reference information, the ship verification model is determined as an adaptive verification model, and an operation of analyzing the ship's verification result information according to the adaptive verification model and the verification requirement information is triggered.

[0115] It can be seen that the implementation of this optional embodiment can further determine the above-mentioned pre-trained ship verification model as an adaptive verification model when it is judged that all the first verification parameters meet the first matching condition of the target reference information, and trigger the execution of the operation of analyzing the ship's verification result information according to the adaptive verification model and the verification requirement information, thereby improving the adaptive verification accuracy of the ship verification model to ensure the stability of the ship verification and the safety of the ship's use.

[0116] In this optional embodiment, as an optional implementation manner, the above-mentioned ship information includes at least one of ship ownership information, ship type information, and ship throughput information. The above-mentioned matching of the associated target reference information according to the ship information may include the following operations:

[0117] Analyzing the carrying capacity information of the ship according to the ship information, where the carrying capacity information includes at least one of carrying authority information, carrying goods information, and carrying method information;

[0118] Analyze the expected transport mission information and expected transport route information that can be performed by the ship based on the transport capacity information, the acquired historical transport mission information and historical transport route information of the ship;

[0119] Determine the ship information, carrying capacity information, historical carrying mission information, historical carrying route information, expected carrying mission information and expected carrying route information as a ship carrying information set of the ship;

[0120] According to the ship transport information set, the associated target reference information is matched.

[0121] In this optional embodiment, optionally, the above-mentioned ship throughput information includes the above-mentioned ship displacement information, and also includes ship waste discharge information, power resource consumption information, etc.

[0122] It can be seen that the implementation of this optional embodiment can analyze at least one of the carrying capacity information of the ship including carrying authority information, carrying goods information, and carrying method information according to all the ship information of the above-mentioned ship, and intelligently analyze the executable expected carrying mission information and expected carrying route information of the ship in combination with the historical carrying mission information and historical carrying route information of the ship acquired above, so as to improve the analysis accuracy of the expected carrying mission information and expected carrying route information executable by the ship on the basis of considering the safety and capability range of the ship, and determine the ship information, carrying capacity information, historical carrying mission information, historical carrying route information, expected carrying mission information and expected carrying route information as the ship's ship carrying information set; according to the ship carrying information set, matching the associated target reference information can improve the matching comprehensiveness and accuracy of the target reference information used to represent the verification standard of all first verification items related to the ship, which is conducive to improving the above-mentioned analysis of the adaptability of the ship verification model in combination with each first verification parameter and the accuracy of the correction of the ship verification model, and is conducive to further improving the pertinence of the ship verification adaptation to improve the accuracy of the ship verification.

[0123] 103. Correcting the ship verification model according to the adaptive correction parameters to obtain an adaptive verification model of the ship;

[0124] In this optional embodiment, optionally, in the process of correcting the above-mentioned ship verification model, in addition to correction based on the above-mentioned first verification parameter, the associated parameters of the first verification parameter are also adaptively corrected to improve the accuracy and adaptability of the corrected ship verification model, which is beneficial to improving the generation efficiency and accuracy of the adaptive verification model and preventing the occurrence of redundant correction.

[0125] 104. Analyze the verification result information of the ship based on the adaptive verification model and the verification demand information. The verification result information includes the verification result of the ship and the target guidance strategy of the ship. The target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, deviation guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy.

[0126] In the embodiment of the present invention, the above-mentioned target guidance strategy is generated based on the above-mentioned verification results in a targeted manner, and its purpose is to guide the ship to pass the verification and improve the safety of the ship's use.

[0127] It can be seen that the implementation of the embodiment of the present invention can generate adaptive correction parameters of a pre-trained ship inspection model according to the acquired ship information of the ship, so as to correct the ship inspection model and obtain an adaptive inspection model suitable for the ship. From the perspective of customizing the inspection model, the pertinence of the ship inspection adaptation is improved to improve the accuracy of the ship inspection, and thus, combined with the above-mentioned acquired ship inspection demand information, the inspection result information of the ship including the inspection result and the target guidance strategy is analyzed, wherein the target guidance strategy includes at least one of the following: berthing guidance strategy, risk avoidance guidance strategy, deviation guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy and business docking guidance strategy, thereby improving the analysis accuracy of the ship inspection result and the generation accuracy of the target guidance strategy based on the ship inspection result. From the two dimensions of analyzing the ship inspection result and generating the target guidance strategy, on the basis of further improving the accuracy of the ship inspection, the accuracy of the ship inspection guidance is improved to improve the safety of the ship use.

[0128] Embodiment 2

[0129] See also Figure 2 , Figure 2 is a flow chart of another method for ship inspection based on artificial intelligence disclosed in an embodiment of the present invention. Figure 2 The described artificial intelligence-based ship inspection method can be applied to customs inspection equipment, estuary checkpoint equipment, bridge inspection equipment, etc., and can also be applied to intelligent devices related to the above devices, including but not limited to geological equipment, cloud equipment, edge computing equipment, relay equipment, base station equipment, urban management equipment, intelligent network equipment, etc., which are not limited in the embodiments of the present invention. Figure 2 As shown, the ship verification method based on artificial intelligence may include the following operations:

[0130] 201. Obtaining the verification requirement information and ship information of the ship;

[0131] 202. Generate adaptive correction parameters of a pre-trained ship inspection model based on the ship information;

[0132] 203. Correcting the ship verification model according to the adaptive correction parameter to obtain an adaptive verification model of the ship;

[0133] In the embodiment of the present invention, for the supplementary explanation of step 201 to step 203, please refer to the supplementary explanation of step 101 to step 103 in the first embodiment, and the embodiment of the present invention will not elaborate on this.

[0134] 204. Analyze at least one second verification item of the ship according to the verification requirement information;

[0135] In the embodiment of the present invention, the above-mentioned verification requirement information is used to represent the verification content information actually required, and the corresponding actual verification item needs to be matched, so the first verification item in the first embodiment includes the second verification item.

[0136] In the embodiment of the present invention, as an optional implementation manner, the above-mentioned analyzing at least one second inspection item of the ship according to the inspection requirement information may include the following operations:

[0137] According to the verification requirement information and the preset segmentation analysis model, the verification requirement information is divided into at least one verification requirement sub-information, and each verification requirement sub-information corresponds to a different requirement item;

[0138] Get the current status information of the ship;

[0139] Determine the first priority of each verification requirement sub-information based on the current status information and all verification requirement sub-information;

[0140] analyzing at least one second inspection item of the ship according to all first priorities of all inspection requirement sub-information;

[0141] Optionally, the above-mentioned current status information is determined based on a combination of the ship sensed at the time of acquisition and the above-mentioned ship information.

[0142] It can be seen that the implementation of this optional embodiment can divide the verification requirement information into at least one corresponding verification requirement sub-information of different requirement items according to the obtained verification requirement information of the above-mentioned ship and the preset segmentation analysis model, so as to determine the first priority of each verification requirement sub-information in combination with the obtained current status information of the ship, and then analyze at least one second verification item of the ship according to all the first priorities of all the verification requirement sub-information, so as to improve the analysis accuracy of the second verification item from a practical perspective.

[0143] Optionally, the above-mentioned analyzing at least one second inspection item of the ship according to all the first priorities of all the inspection requirement sub-information may include the following operations:

[0144] Analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and the preset semantic analysis model;

[0145] At least one second check item of the ship is determined according to all the first priorities and semantic information of all the check requirement sub-information, and each second check item has a corresponding second priority.

[0146] In this optional embodiment, optionally, the above-mentioned preset semantic analysis model can be obtained by nesting and fusion training between underlying models, or can be obtained by integration model migration.

[0147] It can be seen that the implementation of this optional embodiment can analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and the preset semantic analysis model, thereby combining all the first priorities of all the verification requirement sub-information, determining at least one second verification item of the ship, and correspondingly matching the corresponding second priority for each second verification item, which can further improve the comprehensive understanding of the verification requirement information, so as to further improve the analysis accuracy of the second verification item.

[0148] 205. Analyze the verification purpose information of the ship according to all the second verification items;

[0149] 206. Matching a second verification parameter of the adaptive verification model according to the verification purpose information;

[0150] 207. For each second verification item, determine whether the second verification item satisfies a second matching condition of a second verification parameter, and obtain a first determination result;

[0151] 208. Analyze the verification result information of the ship based on all the first judgment results and the verification purpose information. The verification result information includes the verification result of the ship and the target guidance strategy of the ship. The target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, deviation guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy.

[0152] It can be seen that the implementation of the embodiment of the present invention can generate adaptive correction parameters of a pre-trained ship inspection model according to the acquired ship information of the ship, so as to correct the ship inspection model and obtain an adaptive inspection model suitable for the ship. From the perspective of customizing the inspection model, the pertinence of the ship inspection adaptation is improved. On the basis of improving the accuracy of the ship inspection, at least one second inspection item of the ship can be analyzed according to the inspection requirement information, so as to integrate all the second inspection items and analyze the inspection purpose information of the ship to improve the understanding of the inspection requirement information. Therefore, based on the inspection purpose actually required by the ship, each second inspection item is matched to see whether it meets the second inspection parameter of the matched adaptive inspection model to obtain a first judgment result. Based on all the first judgment results and the inspection purpose information, the inspection result information of the ship is analyzed, which can further improve the accuracy of the ship inspection based on the perspective of analyzing and understanding the real needs of the ship.

[0153] In the embodiment of the present invention, as another optional implementation, the above-mentioned analyzing the verification result information of the ship according to all the first judgment results and the verification purpose information may include the following operations:

[0154] According to all the first judgment results, a third verification item among all the second verification items is screened, where the third verification item is used to represent a second verification item that does not satisfy a second matching condition of a second verification parameter;

[0155] Calculate the inspection performance value of the ship according to the second priority level corresponding to all third inspection items;

[0156] Analyze the ship's inspection result information based on the inspection score value and inspection purpose information.

[0157] In this optional embodiment, the above-mentioned calculation of the ship's inspection performance value according to the second priority corresponding to all third inspection items can be calculated based on a preset calculation model, and the above-mentioned preset calculation model can be adaptively configured according to a specific application scenario to highlight the inspection focus of the application scenario.

[0158] It can be seen that the implementation of this optional embodiment can screen out the third verification items in all the second verification items that are used to indicate that the second matching condition of the second verification parameter is not satisfied according to all the first judgment results, calculate the verification performance value of the ship based on the second priority corresponding to all the third verification items, and then analyze the verification result information of the ship in combination with the above-mentioned verification purpose information, which can further improve the analysis accuracy, comprehensiveness and intuitiveness of the verification result information.

[0159] In this optional embodiment, as an optional implementation mode, the above-mentioned target guidance strategy corresponds to the verification purpose information, and the above-mentioned analysis of the verification result information of the ship according to the verification score value and the verification purpose information may include the following operations:

[0160] Calculate the distance between the verification score and the preset threshold, and match the distance with the guidance degree of the target guidance strategy;

[0161] Obtain information about the vessel's surrounding environment;

[0162] Analyze the ship's guidance trajectory information based on surrounding environment information, current status information, distance value and verification purpose information;

[0163] Analyze the ship's inspection result information based on the guidance trajectory information and inspection score value.

[0164] It can be seen that the implementation of this optional embodiment can further calculate the distance value between the verification score value and the preset threshold that matches the guidance degree of the target guidance strategy, and combine the acquired surrounding environment information, current status information and verification purpose information of the above-mentioned ship to analyze the guidance trajectory information of the ship, so as to further combine the above-mentioned verification score value to analyze the verification result information of the ship, thereby further improving the accuracy of the analysis of the verification results, and improving the accuracy and scientificity of the generation of the ship's target guidance strategy, which is conducive to further improving the accuracy of ship verification guidance on the basis of further improving the accuracy of ship verification, so as to further improve the safety of ship use.

[0165] Embodiment 3

[0166] See also Figure 3 , Figure 3 : is a schematic diagram of the structure of an artificial intelligence-based ship inspection device disclosed in an embodiment of the present invention. The artificial intelligence-based ship inspection device can be applied to customs inspection equipment, estuary checkpoint equipment, bridge inspection equipment, etc. It can also be applied to intelligent devices related to the above-mentioned equipment, which include but are not limited to geological equipment, cloud equipment, edge computing equipment, relay equipment, base station equipment, urban management equipment, intelligent network equipment, etc., which are not limited in the embodiment of the present invention. Figure 3 As shown, the artificial intelligence-based ship inspection device may include:

[0167] The acquisition module 301 is used to acquire the inspection requirement information and ship information of the ship;

[0168] A generating module 302 is used to generate adaptive correction parameters of a pre-trained ship inspection model according to the ship information;

[0169] A correction module 303 is used to correct the ship verification model according to the adaptive correction parameters to obtain an adaptive verification model of the ship;

[0170] The analysis module 304 is used to analyze the verification result information of the ship according to the adaptive verification model and the verification requirement information. The verification result information includes the verification result of the ship and the target guidance strategy of the ship. The target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy.

[0171] It can be seen that the implementation of the embodiment of the present invention can generate adaptive correction parameters of a pre-trained ship inspection model according to the acquired ship information of the ship, so as to correct the ship inspection model and obtain an adaptive inspection model suitable for the ship. From the perspective of customizing the inspection model, the pertinence of the ship inspection adaptation is improved to improve the accuracy of the ship inspection, and thus, combined with the above-mentioned acquired ship inspection demand information, the inspection result information of the ship including the inspection result and the target guidance strategy is analyzed, wherein the target guidance strategy includes at least one of the following: berthing guidance strategy, risk avoidance guidance strategy, deviation guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy and business docking guidance strategy, thereby improving the analysis accuracy of the ship inspection result and the generation accuracy of the target guidance strategy based on the ship inspection result. From the two dimensions of analyzing the ship inspection result and generating the target guidance strategy, on the basis of further improving the accuracy of the ship inspection, the accuracy of the ship inspection guidance is improved to improve the safety of the ship use.

[0172] In the embodiment of the present invention, as an optional implementation, the specific manner in which the above-mentioned generating module 302 generates the adaptive correction parameters of the pre-trained ship inspection model according to the ship information includes:

[0173] According to the ship information, the associated target reference information is matched, where the target reference information is used to represent the verification standards of all first verification items related to the ship;

[0174] Determining at least one first verification parameter in a pre-trained ship verification model according to the target reference information, the first verification parameter being associated with the target reference information;

[0175] For each first verification parameter, determine whether the first verification parameter satisfies the first matching condition of the target reference information; when it is determined that the first verification parameter does not satisfy the first matching condition of the target reference information, generate an adaptive correction parameter of the ship verification model according to the target reference information and the first verification parameter, the adaptive correction parameter being used to correct the first verification parameter to correct the ship verification model;

[0176] It can be seen that the implementation of this optional embodiment can match the target reference information used to represent the verification standards of all first verification items related to the ship according to the above-mentioned ship information obtained, so as to further determine at least one first verification parameter associated with the target reference information in the pre-trained ship verification model. Based on each first verification parameter, when it is judged that the first verification parameter does not meet the first matching condition of the target reference information, an adaptive correction parameter of the ship verification model is generated according to the above-mentioned target reference information and the first verification parameter. The adaptive correction parameter is used to correct the first verification parameter to correct the ship verification model, thereby gradually correcting the ship verification model. From the perspective of customized verification model, the targetedness of ship verification adaptation is further improved to improve the accuracy of ship verification.

[0177] And, if Figure 4 As shown, the device may also include:

[0178] The determination module 305 is used to determine the ship verification model as an adaptive verification model when the generation module 302 determines that all the first verification parameters meet the first matching condition of the target reference information, and trigger the analysis module 304 to perform an operation of analyzing the verification result information of the ship according to the adaptive verification model and the verification requirement information.

[0179] It can be seen that the implementation of this optional embodiment can further determine the above-mentioned pre-trained ship verification model as an adaptive verification model when it is judged that all the first verification parameters meet the first matching condition of the target reference information, and trigger the execution of the operation of analyzing the ship's verification result information according to the adaptive verification model and the verification requirement information, thereby improving the adaptive verification accuracy of the ship verification model to ensure the stability of the ship verification and the safety of the ship's use.

[0180] In this optional embodiment, as an optional implementation, the above-mentioned ship information includes at least one of ship ownership information, ship type information, and ship throughput information. The specific manner in which the above-mentioned generation module 302 matches the associated target reference information according to the ship information includes:

[0181] Analyzing the carrying capacity information of the ship according to the ship information, where the carrying capacity information includes at least one of carrying authority information, carrying goods information, and carrying method information;

[0182] Analyze the expected transport mission information and expected transport route information that can be performed by the ship based on the transport capacity information, the acquired historical transport mission information and historical transport route information of the ship;

[0183] Determine the ship information, carrying capacity information, historical carrying mission information, historical carrying route information, expected carrying mission information and expected carrying route information as a ship carrying information set of the ship;

[0184] According to the ship transport information set, the associated target reference information is matched.

[0185] It can be seen that the implementation of this optional embodiment can analyze at least one of the carrying capacity information of the ship including carrying authority information, carrying goods information, and carrying method information according to all the ship information of the above-mentioned ship, and intelligently analyze the executable expected carrying mission information and expected carrying route information of the ship in combination with the historical carrying mission information and historical carrying route information of the ship acquired above, so as to improve the analysis accuracy of the expected carrying mission information and expected carrying route information executable by the ship on the basis of considering the safety and capability range of the ship, and determine the ship information, carrying capacity information, historical carrying mission information, historical carrying route information, expected carrying mission information and expected carrying route information as the ship's ship carrying information set; according to the ship carrying information set, matching the associated target reference information can improve the matching comprehensiveness and accuracy of the target reference information used to represent the verification standard of all first verification items related to the ship, which is conducive to improving the above-mentioned analysis of the adaptability of the ship verification model in combination with each first verification parameter and the accuracy of the correction of the ship verification model, and is conducive to further improving the pertinence of the ship verification adaptation to improve the accuracy of the ship verification.

[0186] In an optional embodiment, the specific manner in which the analysis module 304 analyzes the inspection result information of the ship according to the adaptive inspection model and the inspection requirement information includes:

[0187] Analyzing at least one second verification item of the ship according to the verification requirement information;

[0188] Analyze the ship's verification purpose information based on all second verification items;

[0189] According to the verification purpose information, matching a second verification parameter of the adaptive verification model;

[0190] For each second check item, determining whether the second check item satisfies a second matching condition of a second check parameter, and obtaining a first determination result;

[0191] Based on all first judgment results and verification purpose information, the verification result information of the ship is analyzed.

[0192] It can be seen that the implementation of the embodiment of the present invention can generate adaptive correction parameters of a pre-trained ship inspection model according to the acquired ship information of the ship, so as to correct the ship inspection model and obtain an adaptive inspection model suitable for the ship. From the perspective of customizing the inspection model, the pertinence of the ship inspection adaptation is improved. On the basis of improving the accuracy of the ship inspection, at least one second inspection item of the ship can be analyzed according to the inspection requirement information, so as to integrate all the second inspection items and analyze the inspection purpose information of the ship to improve the understanding of the inspection requirement information. Therefore, based on the inspection purpose actually required by the ship, each second inspection item is matched to see whether it meets the second inspection parameter of the matched adaptive inspection model to obtain a first judgment result. Based on all the first judgment results and the inspection purpose information, the inspection result information of the ship is analyzed, which can further improve the accuracy of the ship inspection based on the perspective of analyzing and understanding the real needs of the ship.

[0193] In this optional embodiment, as an optional implementation, the specific manner in which the above-mentioned analysis module 304 analyzes at least one second inspection item of the ship according to the inspection requirement information includes:

[0194] According to the verification requirement information and the preset segmentation analysis model, the verification requirement information is divided into at least one verification requirement sub-information, and each verification requirement sub-information corresponds to a different requirement item;

[0195] Get the current status information of the ship;

[0196] Determine the first priority of each verification requirement sub-information based on the current status information and all verification requirement sub-information;

[0197] analyzing at least one second inspection item of the ship according to all first priorities of all inspection requirement sub-information;

[0198] It can be seen that the implementation of this optional embodiment can divide the verification requirement information into at least one corresponding verification requirement sub-information of different requirement items according to the obtained verification requirement information of the above-mentioned ship and the preset segmentation analysis model, so as to determine the first priority of each verification requirement sub-information in combination with the obtained current status information of the ship, and then analyze at least one second verification item of the ship according to all the first priorities of all the verification requirement sub-information, so as to improve the analysis accuracy of the second verification item from a practical perspective.

[0199] Optionally, the specific manner in which the analysis module 304 analyzes at least one second inspection item of the ship according to all first priorities of all inspection requirement sub-information includes:

[0200] Analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and the preset semantic analysis model;

[0201] At least one second check item of the ship is determined according to all the first priorities and semantic information of all the check requirement sub-information, and each second check item has a corresponding second priority.

[0202] It can be seen that the implementation of this optional embodiment can analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and the preset semantic analysis model, thereby combining all the first priorities of all the verification requirement sub-information, determining at least one second verification item of the ship, and correspondingly matching the corresponding second priority for each second verification item, which can further improve the comprehensive understanding of the verification requirement information, so as to further improve the analysis accuracy of the second verification item.

[0203] In this optional embodiment, as another optional implementation, the specific manner in which the above-mentioned analysis module 304 analyzes the verification result information of the ship according to all the first judgment results and the verification purpose information includes:

[0204] According to all the first judgment results, a third verification item among all the second verification items is screened, where the third verification item is used to represent a second verification item that does not satisfy a second matching condition of a second verification parameter;

[0205] Calculate the inspection performance value of the ship according to the second priority level corresponding to all third inspection items;

[0206] Analyze the ship's inspection result information based on the inspection score value and inspection purpose information.

[0207] It can be seen that the implementation of this optional embodiment can screen out the third verification items in all the second verification items that are used to indicate that the second matching condition of the second verification parameter is not satisfied according to all the first judgment results, calculate the verification performance value of the ship based on the second priority corresponding to all the third verification items, and then analyze the verification result information of the ship in combination with the above-mentioned verification purpose information, which can further improve the analysis accuracy, comprehensiveness and intuitiveness of the verification result information.

[0208] In this optional embodiment, as another optional implementation, the above-mentioned target guidance strategy corresponds to the verification purpose information, and the above-mentioned analysis module 304 analyzes the verification result information of the ship according to the verification score value and the verification purpose information in a specific manner including:

[0209] Calculate the distance between the verification score and the preset threshold, and match the distance with the guidance degree of the target guidance strategy;

[0210] Obtain information about the vessel's surrounding environment;

[0211] Analyze the ship's guidance trajectory information based on surrounding environment information, current status information, distance value and verification purpose information;

[0212] Analyze the ship's inspection result information based on the guidance trajectory information and inspection score value.

[0213] It can be seen that the implementation of this optional embodiment can further calculate the distance value between the verification score value and the preset threshold that matches the guidance degree of the target guidance strategy, and combine the acquired surrounding environment information, current status information and verification purpose information of the above-mentioned ship to analyze the guidance trajectory information of the ship, so as to further combine the above-mentioned verification score value to analyze the verification result information of the ship, thereby further improving the accuracy of the analysis of the verification results, and improving the accuracy and scientificity of the generation of the ship's target guidance strategy, which is conducive to further improving the accuracy of ship verification guidance on the basis of further improving the accuracy of ship verification, so as to further improve the safety of ship use.

[0214] Embodiment 4

[0215] See also Figure 5 , Figure 5 It is a schematic diagram of the structure of another artificial intelligence-based ship inspection device disclosed in an embodiment of the present invention. The artificial intelligence-based ship inspection device can be applied to customs inspection equipment, estuary checkpoint equipment, bridge inspection equipment, etc. It can also be applied to intelligent devices related to the above-mentioned equipment, which include but are not limited to geological equipment, cloud equipment, edge computing equipment, relay equipment, base station equipment, urban management equipment, intelligent network equipment, etc., which are not limited in the embodiment of the present invention. Figure 5As shown, the artificial intelligence-based ship inspection device may include:

[0216] The memory 401 stores executable program codes.

[0217] A processor 402 is coupled to the memory 401 .

[0218] The processor 402 calls the executable program code stored in the memory 401 to execute the steps in the ship inspection method based on artificial intelligence described in the first embodiment of the present invention or the second embodiment of the present invention.

[0219] Embodiment 5

[0220] An embodiment of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute the steps in the artificial intelligence-based ship inspection method described in Embodiment 1 or Embodiment 2 of the present invention.

[0221] Embodiment 6

[0222] An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps in the artificial intelligence-based ship inspection method described in Example 1 or Example 2.

[0223] The device embodiments described above are only illustrative, wherein the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, i.e., they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Those of ordinary skill in the art may understand and implement it without creative work.

[0224] Through the specific description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on such an understanding, the above technical solution can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable rewritable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0225] Finally, it should be noted that the artificial intelligence-based ship inspection method and device disclosed in the embodiments of the present invention only discloses the preferred embodiments of the present invention, which are only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A ship inspection method based on artificial intelligence, characterized in that: The method comprises: Obtain ship inspection requirement information and ship information; generating adaptive correction parameters of a pre-trained ship verification model according to the ship information; Correcting the ship verification model according to the adaptive correction parameters to obtain an adaptive verification model of the ship; Analyzing at least one second inspection item of the ship according to the inspection requirement information; Analyzing the verification purpose information of the ship according to all the second verification items; According to the verification purpose information, matching a second verification parameter of the adaptive verification model; For each of the second verification items, determining whether the second verification item satisfies a second matching condition of the second verification parameter, and obtaining a first determination result; Analyzing the verification result information of the ship according to all the first judgment results and the verification purpose information, the verification result information includes the verification result of the ship and the target guidance strategy of the ship, and the target guidance strategy includes at least one of the ship's berthing guidance strategy, risk avoidance guidance strategy, deviation guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy; And, analyzing at least one second inspection item of the ship according to the inspection requirement information includes: According to the verification requirement information and a preset segmentation analysis model, the verification requirement information is divided into at least one verification requirement sub-information, each verification requirement sub-information corresponding to a different requirement item; Obtaining current status information of the ship; Determining a first priority of each of the verification requirement sub-information according to the current state information and all of the verification requirement sub-information; Analyze the semantic information corresponding to the verification requirement information according to the verification requirement information and a preset semantic analysis model; Determining at least one second inspection item of the ship according to all the first priorities and the semantic information of all the inspection requirement sub-information, each of the second inspection items having a corresponding second priority; And, generating the adaptive correction parameters of the pre-trained ship inspection model according to the ship information includes: According to the ship information, matching associated target reference information, the target reference information is used to represent the verification standards of all first verification items related to the ship; Determining at least one first verification parameter in a pre-trained ship verification model according to the target reference information, wherein the first verification parameter is associated with the target reference information; For each of the first verification parameters, determining whether the first verification parameter satisfies the first matching condition of the target reference information; when it is determined that the first verification parameter does not satisfy the first matching condition of the target reference information, generating an adaptive correction parameter of the ship verification model according to the target reference information and the first verification parameter, wherein the adaptive correction parameter is used to correct the first verification parameter to correct the ship verification model; And, the method further comprises: When it is determined that all of the first verification parameters meet the first matching condition of the target reference information, the ship verification model is determined as the adaptive verification model, and the operation of analyzing the verification result information of the ship according to the adaptive verification model and the verification requirement information is triggered.

2. The ship inspection method based on artificial intelligence according to claim 1 is characterized in that: The ship information includes at least one of ship ownership information, ship type information, and ship throughput information. The matching of associated target reference information according to the ship information includes: Analyzing the carrying capacity information of the ship according to the ship information, wherein the carrying capacity information includes at least one of carrying authority information, carrying article information, and carrying method information; Analyze the expected transport mission information and expected transport route information executable by the ship according to the transport capacity information and the acquired historical transport mission information and historical transport route information of the ship; Determine the ship information, the carrying capacity information, the historical carrying mission information, the historical carrying route information, the expected carrying mission information and the expected carrying route information as a ship carrying information set of the ship; According to the ship transport information set, the associated target reference information is matched.

3. The ship inspection method based on artificial intelligence according to claim 1 is characterized in that: The analyzing the verification result information of the ship according to all the first judgment results and the verification purpose information includes: According to all the first judgment results, screening a third verification item among all the second verification items, the third verification item being used to represent the second verification item that does not satisfy the second matching condition of the second verification parameter; Calculating the inspection performance value of the ship according to the second priority level corresponding to all the third inspection items; The inspection result information of the ship is analyzed according to the inspection performance value and the inspection purpose information.

4. The ship inspection method based on artificial intelligence according to claim 3 is characterized in that: The target guidance strategy corresponds to the verification purpose information, and the verification result information of the ship is analyzed according to the verification score value and the verification purpose information, including: Calculating a distance value between the verification score value and a preset threshold, wherein the distance value matches the guidance degree of the target guidance strategy; Acquiring surrounding environment information of the ship; Analyzing the guidance trajectory information of the ship according to the surrounding environment information, the current state information, the distance value and the verification purpose information; The verification result information of the ship is analyzed according to the guidance trajectory information and the verification score value.

5. A ship inspection device based on artificial intelligence, characterized in that: The device is used to execute the ship inspection method based on artificial intelligence according to any one of claims 1 to 4, and the device includes: An acquisition module is used to obtain the ship's inspection requirement information and ship information; A generating module, used for generating adaptive correction parameters of a pre-trained ship inspection model according to the ship information; A correction module, used for correcting the ship verification model according to the adaptive correction parameter to obtain an adaptive verification model of the ship; An analysis module is used to analyze the verification result information of the ship according to the adaptive verification model and the verification requirement information, wherein the verification result information includes the verification result of the ship and the target guidance strategy of the ship, and the target guidance strategy includes at least one of the ship's docking guidance strategy, risk avoidance guidance strategy, yaw guidance strategy, transportation guidance strategy, maintenance guidance strategy, compilation guidance strategy, and business docking guidance strategy.

6. A ship inspection device based on artificial intelligence, characterized in that: The device comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the artificial intelligence-based ship inspection method as described in any one of claims 1-4.

7. A computer storage medium, characterized in that: The computer storage medium stores computer instructions, which, when called, are used to execute the artificial intelligence-based ship inspection method as described in any one of claims 1 to 4.

Images