A Ship Scheduling Method, Device, Equipment and Medium in Multi-Project Marine Operations

Abstract

The present invention discloses a ship scheduling method, device, equipment and medium in multi-project ocean operations, belonging to the field of ocean operation scheduling. The method includes obtaining detailed information of ocean operation projects by identifying at least one construction design, inputting the ocean operation project information into a first operation scheduling model to generate first scheduling information, generating a first scheduling chart according to the first scheduling information, obtaining real-time information of the operation area, inputting the real-time information of the operation area and the first scheduling chart into a second operation scheduling model to generate second scheduling information, and generating a second scheduling chart according to the second scheduling information, and finally performing ship scheduling according to the second scheduling chart. The present invention constructs a first operation scheduling model and a second operation scheduling model for the ocean operation scheduling task in the multi-ship multi-project mode, and generates a first scheduling chart and a second scheduling chart according to the operation project information and the real-time information of the operation area, improving the real-time performance and accuracy of ocean operation scheduling.

Description

Technical Field

[0001] The present invention relates to the technical field of ship operation scheduling, and particularly relates to a ship scheduling method, device, equipment and medium in multi-project ocean operations. Background Art

[0002] At present, the execution of ocean operation projects involves single-ship single-project, single-ship multi-project, multi-ship single-project and multi-ship multi-project modes. For the multi-ship multi-project mode, usually multiple ships carry tools and equipment for executing corresponding projects, and there are overlapping and dependent relationships among the projects that can be executed between ships.

[0003] In current actual operations, for job scheduling in the multi-ship multi-project mode, there are usually the following methods: One is mainly based on the experience of schedulers, and the schedulers obtain the scheduling plan manually. This method highly depends on the subjective experience of schedulers, it is difficult to obtain the optimal scheduling plan, and this method requires manual calculation and review, with low efficiency. The other is to train a job scheduling model based on machine learning, neural network or deep learning according to the comprehensive experience of schedulers and historical data, and the job scheduling model generates the scheduling plan. This method only uses simple machine learning, neural network or deep learning models, and the accuracy of the generated scheduling plan remains to be further discussed. At the same time, this method does not consider the real-time data of the operation area, making the generated scheduling plan unable to meet the requirements of real-time scheduling.

[0004] The foregoing description is provided to give general background information and does not necessarily constitute prior art. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a ship scheduling method, device, equipment and medium in multi-project ocean operations. The first aspect of the present invention provides a ship scheduling method in multi-project ocean operations, including the following steps:

[0006] Obtain ocean operation project information;

[0007] Input the ocean operation project information into the first job scheduling model to generate first scheduling information;

[0008] Generate a first scheduling diagram according to the first scheduling information;

[0009] Obtain real-time information of the operation area;

[0010] Input the real-time information of the operation area and the first scheduling diagram into the second job scheduling model to generate second scheduling information;

[0011] Generate a second scheduling diagram according to the second scheduling information; Schedule the ships according to the second scheduling diagram.

[0012] Further, the obtaining of the offshore operation project information specifically includes the following steps:

[0013] Obtain at least one construction design plan, where there are multiple sub-projects in the construction design plan;

[0014] Identify the construction design plan to obtain the offshore operation project information in the construction design plan; the offshore operation project information includes multiple sub-project information and dependency relationship information between sub-projects, and the sub-project information at least includes sub-project identification, operation area, and sub-project workload.

[0015] Further, the first operation scheduling model includes an encoding network, a generation network, and a decision network;

[0016] Inputting the offshore operation information into the first operation scheduling model to generate the first scheduling information specifically includes:

[0017] Input the multiple sub-project information into the encoding network to obtain multiple sub-project vectors;

[0018] Input the multiple sub-project vectors into the generation network, and generate multiple first scheduling sub-information corresponding to the multiple sub-projects through the generation network; the first scheduling sub-information at least includes operation vessel information, operation days information, and window label information;

[0019] Input the multiple first scheduling sub-information and the dependency relationship information between sub-projects into the decision network to generate the first scheduling information.

[0020] Further, the decision network adopts a multi-network fusion structure based on dependency relationships, including an input layer, an embedding layer, a feature extraction layer, a first gating layer, a multi-block shared MLP layer, a linear layer, and an output layer;

[0021] Inputting the multiple scheduling sub-information and the dependency relationship information between sub-projects into the decision network to generate the first scheduling information specifically includes:

[0022] Input multiple first scheduling sub-information and the dependency relationship information between sub-projects through the input layer;

[0023] Use the embedding layer to convert the first scheduling sub-information and the corresponding dependency relationship information into feature vectors to obtain sub-information feature vectors and dependency relationship feature vectors;

[0024] Use the fusion layer to fuse the sub-information feature vectors and the dependency relationship feature vectors to obtain a fused feature vector;

[0025] Use multiple feature extraction networks in the feature extraction layer to extract features from the fused feature vector to obtain multiple initial feature vectors;

[0026] Use the first gating layer to generate the first weight data corresponding to each feature extraction network, and perform weighted summation on the initial feature vectors output by each feature extraction network to obtain the first combined feature vector;

[0027] Use multiple shared MLP layers to perform task migration processing on the first combined feature vector to obtain the first migration feature vector;

[0028] Use a linear layer to perform conversion processing on the first migration feature vector to obtain the first scheduling information;

[0029] Use the output layer to output the first scheduling information.

[0030] Furthermore, the multiple shared MLP layers are a multi-level block network structure. Each block includes m MLPs and a shared layer. The shared layer of the i-th block is used to extract features from the output features of the m MLPs in the current block to obtain m knowledge features, and the output features of the MLPs i k1 are fused with the knowledge features extracted by the MLPs i k2 as the input of the MLPs i+1 k1 , where m is the number of workboats, MLP represents a multi-layer perceptron model, k2 = 1:m and k2 ≠ k1.

[0031] Furthermore, the first scheduling information includes the workboat identification, the operation item identification, the project sub-identification, the operation area, and the execution order corresponding to the project sub-identification;

[0032] The generation of the first scheduling graph according to the first scheduling information is specifically as follows:

[0033] Taking the workboat as the root node, and taking the triple composed of the operation item identification, the project sub-identification, and the operation area as the leaf node, and using the execution order corresponding to the project sub-identification as the constraint condition, construct the first scheduling graph.

[0034] Furthermore, the second job scheduling model includes a first encoding layer, a second encoding layer, a feature fusion layer, and a decoding layer;

[0035] The input of the real-time information and the first scheduling graph into the second job scheduling model to generate the second scheduling information specifically includes:

[0036] Use the first encoding layer to encode the real-time information in the operation area to obtain the first encoded feature;

[0037] Use the second encoding layer to encode the first scheduling graph to obtain the second encoded feature;

[0038] The first encoded feature and the second encoded feature are concatenated using a feature fusion layer to obtain a fused feature;

[0039] The fused feature is decoded using a decoding layer to obtain second scheduling information.

[0040] The second aspect of the present invention discloses a ship scheduling device in multi-project ocean operations, and the device includes:

[0041] A first acquisition module for acquiring ocean operation project information;

[0042] A first generation module for inputting the ocean operation project information into a first operation scheduling model to generate first scheduling information;

[0043] A second generation module for generating a first scheduling diagram according to the first scheduling information;

[0044] A second acquisition module for acquiring real-time information of the operation area;

[0045] A third generation module for inputting the real-time information and the first scheduling diagram into a second operation scheduling model to generate second scheduling information;

[0046] A fourth generation module for generating a second scheduling diagram according to the second scheduling information.

[0047] The third aspect of the present invention discloses an electronic device, including a processor and a memory;

[0048] The memory is used for storing programs;

[0049] The processor executes the program to implement the ship scheduling method in multi-project ocean operations.

[0050] The fourth aspect of the present invention discloses a computer-readable storage medium, and the storage medium stores a program, and the program is executed by a processor to implement the ship scheduling method in multi-project ocean operations.

[0051] The embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the foregoing method.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] (1) The present invention proposes a method for obtaining a two-stage job scheduling scheme for ocean operation scheduling tasks in a multi-ship and multi-project mode. In the first stage, ocean operation project information is identified according to the construction design, and the ocean operation project information is input into the first job scheduling model to generate a first scheduling diagram. Since the first job scheduling model is trained based on historical data, the first scheduling diagram generated in this stage is a static scheduling diagram. In the second stage, according to the real-time information in the operation area and the first scheduling diagram, a second scheduling diagram is generated through the second job scheduling model. This stage is essentially using real-time information to correct the first scheduling diagram in real time, so the second scheduling diagram generated is a dynamic scheduling diagram. Therefore, the present invention proposes a combination of a static scheduling diagram and a dynamic scheduling diagram for ocean operation scheduling tasks in a multi-ship and multi-project mode, improving the real-time performance and accuracy of job scheduling, and also enhancing the experience of schedulers.

[0054] (2) When constructing the first job scheduling model of the present invention, considering that different operation ships can execute the same sub-projects and there are dependency relationships in the execution of different sub-projects, a decision network with a multi-network fusion structure based on dependency relationships is constructed to obtain the first scheduling information. Multiple shared MLP layers are used in this decision network. The shared layer in each block learns the knowledge features of other MLPs in the block, and fuses the knowledge features of other MLPs and the output features of the current MLP as the input of the MLP in the next block. Due to the incorporation of prior knowledge, the obtained scheduling scheme is more in line with the multi-ship and multi-project mode.

[0055] The present invention constructs multiple generation sub-networks to generate the first scheduling sub-information, and the first scheduling sub-information includes job window label information. By performing a fine-grained division of the operation time, multiple job window label information are obtained, making the generated first scheduling sub-information more in line with the requirements of ocean operation scheduling.

[0056] The additional aspects and advantages of the present invention will be given in the following description section, some will become obvious from the following description, or will be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0058] Figure 1 It is a schematic diagram of the implementation process of a ship scheduling method in multi-project ocean operations of the present invention.

[0059] Figure 2 This is a schematic diagram of the architecture of ocean operation scheduling in a ship scheduling method for multiple projects of the present invention.

[0060] Figure 3 This is a schematic diagram of the architecture for generating the first scheduling information in a ship scheduling method for multiple projects of the present invention.

[0061] Figure 4 This is a schematic diagram of the decision network in a ship scheduling method for multiple projects of the present invention.

[0062] Figure 5 This is a schematic diagram of the architecture of the multi-block shared MLP layer in a ship scheduling method for multiple projects of the present invention.

[0063] Figure 6 This is a schematic diagram of the first scheduling graph in a ship scheduling method for multiple projects of the present invention.

[0064] Figure 7 This is a schematic diagram of the second scheduling graph in a ship scheduling method for multiple projects of the present invention.

[0065] Figure 8 This is a schematic diagram of the structure of a ship scheduling device for multiple projects of the present invention.

[0066] Figure 9 This is a schematic diagram of the architecture of an electronic device of the present invention.

[0067] Figure 10 This is a schematic diagram of the architecture of a computer-readable storage medium of the present invention. Detailed implementation manners

[0068] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0069] At present, the execution of offshore operation projects involves single-vessel single-project, single-vessel multi-project, multi-vessel single-project, and multi-vessel multi-project modes. For the multi-vessel multi-project mode, usually multiple vessels carry tools and equipment for corresponding projects, and there are overlapping and dependent relationships among the projects that can be executed between vessels. For example, vessel A carries equipment for gravity and magnetic, seismic, and topographic and geomorphic exploration, vessel B only carries equipment for seismic exploration, and vessel C carries equipment for geological sampling and gravity and magnetic exploration. Since both vessel A and vessel B can perform seismic exploration, and both vessel A and vessel C can perform gravity and magnetic exploration, the projects that vessels A, B, and C can execute have an overlapping relationship. At the same time, in order to improve the safety and accuracy of sampling, it is usually necessary to conduct topographic and geomorphic exploration before sampling, that is, before vessel C performs the sampling task, vessel A needs to complete the topographic and geomorphic exploration in the same operation area. This makes it very difficult to perform operation scheduling in the multi-vessel multi-project mode.

[0070] As Figure 1 shown, the first embodiment of the present invention provides a method for ship scheduling in multi-project offshore operations, including the following steps:

[0071] S1. Obtain offshore operation project information.

[0072] Offshore operation project information is usually recorded in the form of construction design documents. The key information of the project is recorded through the construction design documents, such as detailed project plans and technical specifications, etc. The construction design documents may include, but are not limited to, project plans, technical specification sheets, drawings, charts, engineering specifications, etc., which record all aspects of the project in detail, including, but not limited to, project names, sub-project information, operation areas, sub-project workloads, and dependencies between sub-projects, etc. For example, whether sub-projects can be executed simultaneously, whether sub-project A is executed before sub-project B or sub-project B is executed after sub-project A, etc. The present invention proposes to obtain offshore operation project information by identifying multiple construction designs, thereby improving the efficiency of obtaining offshore operation project information.

[0073] Specifically, as Figure 2 shown, the embodiment of the present invention obtains offshore operation project information through an identification network. The identification network adopts an OCR network and a deep neural network, etc. Among them, the OCR network is used to recognize PDFs and image versions into text; the deep neural network is used to extract sub-project information and dependency information between sub-projects in the text. The deep neural network can specifically adopt BILSTM, BIGRU networks, etc. The extracted sub-project information includes information such as sub-project names, operation areas, and sub-project workloads, and the dependency information includes pre-tasks, post-tasks, etc.

[0074] By identifying at least one construction design, the obtained offshore operation project information is shown in Table 1:

[0075] Table 1

[0076]

[0077]

[0078] S2. Input the offshore operation project information into the first operation scheduling model to generate the first scheduling information.

[0079] In the embodiment of the present invention, the first operation scheduling model is trained by the stored historical offshore operation project information and ship scheduling information; the trained first operation scheduling model can accept new offshore operation project information as input and output reasonable first scheduling information.

[0080] Refer to Figure 3 , after obtaining the trained first operation scheduling model, use the first operation scheduling model and the identified offshore operation project information to generate the first scheduling information, specifically including:

[0081] S2-1. Input the information of multiple sub-projects into the encoding network to obtain multiple sub-project vectors;

[0082] S2-2. Input the multiple sub-project vectors into the generation network, and generate multiple first scheduling sub-information corresponding to the multiple sub-projects through the generation network; the first scheduling sub-information includes operation ship information, operation days information, and window label information;

[0083] S2-3. Input the multiple first scheduling sub-information and the dependency relationship data between sub-projects into the decision network to generate the first scheduling information.

[0084] Specifically, in S2-1, input the information of multiple sub-projects into the encoding network to obtain multiple sub-project vectors. In the embodiment of the present invention, the encoding network is used to receive the offshore operation project information, including the sub-project information and dependency relationship extracted in step S1, and convert the input offshore operation project information into one or more sub-project vectors representing the key attributes of the sub-project information.

[0085] In the actual operation and production process, considering the influence of various factors such as weather and sea waves, the operation cycle is divided into multiple consecutive operation windows by month. For example, from March of the current year to September of the current year is divided into the first window, and from September of the current year to March of the next year is divided into the second window, and the first window label and the second window label are used to identify the first window and the second window respectively.

[0086] Specifically, in S2-2, input the multiple sub-project vectors into the generation network, and generate multiple first scheduling sub-information corresponding to the multiple sub-projects through the generation network, including:

[0087] S2-2-1. Obtain the sub-project identifier corresponding to the sub-project vector and generate the label of the sub-network;

[0088] S2-2-2. Match the sub-project identifier and the label of the sub-network to obtain the generated sub-network;

[0089] S2-2-3. Input the sub-project vector into the generated sub-network to generate the first scheduling sub-information.

[0090] Exemplarily, the generation network includes multiple generated sub-networks, and each generated sub-network is responsible for generating specific types of scheduling information, such as start time, end time, resource allocation, etc.

[0091] In the embodiment of the present invention, when constructing the generation network, multiple generated sub-networks are respectively constructed for multiple workboats. For example, a first generated sub-network for workboat V1, a second generated sub-network for workboat V2, and a third generated sub-network for workboat V3 are respectively constructed, and labels are set for the multiple generated sub-networks according to the sub-project categories executable by the workboats. For example, label a is set for the first generated sub-network, labels b, c, and d are set for the second generated sub-network, and labels a, b, and d are set for the third generated sub-network. The generated sub-network adopts a generative adversarial network model.

[0092] Specifically, S2-3. Input the multiple first scheduling sub-information and the dependency relationship data between sub-projects into the decision network to generate the first scheduling information, including:

[0093] According to the sub-project identifier and the label of the generated sub-network, match and obtain the corresponding generated sub-network; for example, according to sub-project category a, the first generated sub-network and the third generated sub-network are obtained by matching, according to sub-project category b, the second generated sub-network and the third generated sub-network are obtained by matching, and according to sub-project category c, the second generated sub-network is obtained by matching.

[0094] Input the sub-project vector into the matched generated sub-network. For example, input the sub-project vector corresponding to the sub-project information (A, a, Ar1, 5000) into the first generated sub-network and the third generated sub-network, input the sub-project information (B, b, Ar2, 300) into the second generated sub-network and the third generated sub-network, and input the sub-project information (B, c, Ar2, 3000) into the second generated sub-network.

[0095] Output the first scheduling sub-information through the generated sub-network. The first scheduling sub-information includes project identifier, sub-project identifier, operation area information, workboat information, first window label and first operation days information, second window label and second operation days information.

[0096] The first scheduling sub-information generated according to the offshore operation information shown in Table 1 is shown in Table 2:

[0097] Table 2

[0098]

[0099]

[0100] After obtaining the first scheduling sub-information, input the dependency relationships between multiple first scheduling sub-information and sub-items into the decision network, and output the first scheduling information through the decision network; the first scheduling information includes the working vessel, the job item identifier, the project sub-identifier, the working area, and the execution sequence corresponding to the project sub-identifier.

[0101] Refer to Figure 4 , the decision network proposed in the embodiment of the present invention adopts a multi-network fusion structure based on dependency relationships, including an input layer, an embedding layer, a feature extraction network, a first gating layer, a multi-block shared MLP layer, a linear layer, and an output layer, where:

[0102] The input layer is used to input the data of the dependency relationships between multiple first scheduling sub-information and sub-items;

[0103] The embedding layer is used to transform the first scheduling sub-information and the corresponding dependency relationship data into feature vectors, and obtain sub-information feature vectors and dependency relationship feature vectors;

[0104] The fusion layer is used to fuse the sub-information feature vectors and the dependency relationship feature vectors to obtain a fused feature vector;

[0105] Use multiple feature extraction networks in the feature extraction layer to extract features from the fused feature vector to obtain multiple initial feature vectors; the feature extraction layer can adopt a deep neural network model;

[0106] The first gating layer is used to generate the first weight data corresponding to each feature extraction network, and perform weighted summation on the initial feature vectors output by each feature extraction network to obtain a first combined feature vector;

[0107] The multi-block shared MLP layer is used to perform task migration processing on the first combined feature vector to obtain a first migration feature vector;

[0108] The linear layer is used to perform conversion processing on the first migration feature vector to obtain the first scheduling information;

[0109] The output layer is used to output the first scheduling information.

[0110] Refer to Figure 5 , the multi-block shared MLP layer is a multi-level block network structure, each block includes m MLPs and a shared layer, and the shared layer of the i-th block is used to extract features from the output features of the m MLPs in the current block to obtain m knowledge features, and the MLP ik1 The output features are fused with the knowledge features extracted by the MLP i k2 as the input of the MLP i+1 k1 where m is the number of workboats, MLP represents a multi-layer perceptron model, k2 = 1:m and k2 ≠ k1

[0111] Assume that the output of the MLPs in the i-th block is: X_MLP i 1 ,..., X_MLP i k1 ,..., X_MLP i m ,

[0112] This input is shared to the shared layer, and the shared layer extracts knowledge to obtain the knowledge feature data at the i-th level as:

[0113] Y_MLP i 1 = EXTRACT(X_MLP i 1 ),..., Y_MLP i k1 = EXTRACT(X_MLP i k1 ),..., Y_MLP i m = EXTRACT(XMLP i m );

[0114] Then the feature data input to the MLPs at the i+1-th level is:

[0115] {Input_MLP i+1 1} = concat(X_MLP i 1 , Y_MLP i 2 ,..., Y_MLP i k1 ,..., Y_MLP i m );

[0116] {Input_MLP i+1 k1} = concat(X_MLP i k1 , Y_MLP i 1 ,..., Y_MLP ik1-1 , Y_MLP i k1+1 , ……, Y_MLP i m );

[0117] {Input_MLP i+1 m} = concat(X_MLP i m , Y_MLP i 1 , ……, Y_MLP i k1 , ……, Y_MLP i m-1 ).

[0118] Make a decision on the first scheduling sub - information in Table 2 through the decision network, and the first scheduling information is as shown in Table 3:

[0119] Table 3

[0120] Vessel Number V1 V2 V3 (V1, A, a, Ar1, 1) (V2, C, c, d, Ar3, 1) (V3, D, d, Ar4, 1) (V1, C, a, Ar3, 2) (V2, B, c, Ar2, 2) (V3, B, a, Ar2, 1) (V3, B, b, Ar2, 3)

[0121] The decision network constructed in the embodiment of the present invention, through multiple shared MLP layers, can learn the prior knowledge of the MLP in the previous block, so that during the decision - making process, it can perform prior - knowledge constraints on the computer results, making the calculated results more accurate and improving the accuracy of result calculation.

[0122] S3. Generate the first scheduling diagram according to the first scheduling information;

[0123] In the embodiment of the present invention, after generating the first scheduling information, taking the working vessel as the root node, and the triple composed of the job item identifier, project sub - identifier, and working area as the leaf nodes, and the execution sequence corresponding to the project sub - identifier as the constraint condition, construct the first scheduling diagram, as Figure 6 shown, Figure 6 where the solid line represents the execution sequence of sub - projects for the same vessel, and the dashed line represents the execution sequence of sub - projects between different vessels. For example, Figure 6 in it, after the working vessel V3 finishes executing the working area Ar2, project identifier B, and sub - project identifier a, then the working vessel executes the working area Ar2, project identifier B, and sub - project identifier c, and finally the working vessel V3 finishes executing the working area Ar2, project identifier B, and sub - project identifier b. By constructing the first scheduling diagram, the job scheduling plan can be clearly reflected.

[0124] S4. Obtain the real - time information of the working area;

[0125] In the embodiments of the present invention, during offshore operations, factors such as typhoons, wave heights, fisheries, and exercises will all affect the smooth progress of offshore operations. Since the first scheduling diagram is generated based on offshore operation project information and the first operation scheduling model, and the first operation scheduling model is obtained by training based on historical data, the essence of the first scheduling diagram is generated based on static data, without considering the real-time information of the actual operation area. Therefore, the first scheduling diagram cannot fully meet the requirements of real-time scheduling.

[0126] To address this issue, the present invention also uses the real-time information of the operation area and the second operation scheduling model to correct the first scheduling diagram, obtaining a real-time second scheduling diagram. The specifically obtained real-time information of the operation area includes one or more of typhoon information, wave information, fishery information, and exercise information within the operation area.

[0127] S5. Input the real-time information of the operation area and the first scheduling diagram into the second operation scheduling model to generate second scheduling information;

[0128] In the embodiments of the present invention, the second operation scheduling model includes a first encoding layer, a second encoding layer, a feature fusion layer, and a decoding layer. The first encoding layer is used to encode the real-time information within the operation area to obtain a first encoded feature FeatureReal. During the encoding process, the operation area information is represented by a region identifier. For example, operation area Ar1 is represented by 1, operation area Ar2 is represented by 2, and operation area Ar3 is represented by 3; the wave information is represented by the average wave height information within the operation area. For example, if the average wave height is 3m, it is represented by 3, and if the average wave height is 7m, it is represented by 7; the typhoon information, fishery information, and exercise information are represented by 0 or 1. 0 indicates that there is no typhoon within the operation area, 1 indicates that there is a typhoon within the operation area, 0 indicates that there is no fishery activity within the operation area, 1 indicates that there is a fishery activity within the operation area, 0 indicates that there is no exercise activity within the operation area, and 1 indicates that there is an exercise activity within the operation area;

[0129] For example, the obtained real-time information is: operation area Ar1, no typhoon, average wave height 1m, no fishery activity, no exercise activity, operation area Ar2, typhoon, average wave height 6m, no fishery activity, no exercise activity, operation area Ar3, no typhoon, average wave height 1m, no fishery activity, exercise activity. Then, the first encoded feature FeatureReal after encoding by the first encoding layer is: {(1, 0, 1, 0, 0); (2, 1, 6, 0, 0); (3, 0, 0, 0, 1)};

[0130] The second encoding layer is used to encode the first scheduling graph to obtain the second encoded feature. The second encoding layer can adopt a graph convolutional neural network based on the attention mechanism. The graph convolutional neural network based on the attention mechanism encodes each node in the first scheduling graph to obtain the hidden vectors of each node, and then obtains the feature of the first scheduling graph based on the hidden vectors of each node, and determines the feature of the first scheduling graph as the second encoded feature Featuregraph;

[0131] The feature fusion layer is used to splice the first encoded feature FeatureReal and the second encoded feature Featuregraph to obtain the fused feature, FeatureConcat = FeatureReal ⊕ FeatureGraph;

[0132] The decoding layer is used to decode the fused feature to obtain the second scheduling information. The decoding layer can adopt a multi-objective prediction model based on multiple multi-layer perceptrons. By inputting the fused feature FeatureConcat into the decoding layer, the second scheduling information is decoded. The second scheduling information includes the working vessel, the working project identifier, the project sub-identifier, the working area, and the execution order corresponding to the project sub-identifier.

[0133] Suppose when the working vessel V3 executes the sub-project a in the working area Ar2, the real-time information obtained is that there will be fishing activities in the working area Ar2. Then the second scheduling information adjusted by this real-time information is shown in Table 4:

[0134] Table 4

[0135] Vessel Number V1 V2 V3 (V1, A, a, Ar1, 1) (V2, C, c, d, Ar3, 1) (V3, D, d, Ar4, 1) (V1, C, a, Ar3, 2) (V2, B, c, Ar2, 3) (V3, B, a, Ar2, 1) (V3, B, b, Ar2, 2)

[0136] S6. Generate a second scheduling graph according to the second scheduling information; perform scheduling operations on the vessels according to the second scheduling graph.

[0137] Refer to Figure 7 , after generating the second scheduling information, taking the working vessel as the root node, the triple composed of the working project identifier, the project sub-identifier, and the working area as the leaf nodes, and the execution order corresponding to the project sub-identifier as the constraint condition, construct the second scheduling graph; perform scheduling operations on the vessels through the second scheduling graph.

[0138] The vessel scheduling method in multi-project ocean operations provided by the present invention uses the first operation scheduling model and the second scheduling operation model to generate a scheduling plan that integrates real-time information, which is beneficial for schedulers to perform precise scheduling of ocean operation tasks. At the same time, the present invention proposes a method for generating an operation scheduling plan suitable for the multi-vessel multi-project mode. Through a decision-making network including multiple shared MLP layers, the knowledge features of other MLP layers are learned during the decision-making process, further improving the generation accuracy of the scheduling plan.

[0139] Reference Figure 8 , the second embodiment of the present invention proposes an ocean operation scheduling device, which includes:

[0140] The first acquisition module 801 is used to acquire ocean operation project information;

[0141] The first generation module 802 is used to input the ocean operation project information into the first operation scheduling model to generate the first scheduling information;

[0142] The second generation module 803 is used to generate the first scheduling diagram according to the first scheduling information;

[0143] The second acquisition module 804 is used to acquire real-time information of the operation area;

[0144] The third generation module 805 is used to input the real-time information and the first scheduling diagram into the second operation scheduling model to generate the second scheduling information;

[0145] The fourth generation module 806 is used to generate the second scheduling diagram according to the second scheduling information, and perform scheduling operations on the ships according to the second scheduling diagram.

[0146] When the first acquisition module 801 acquires ocean operation project information, it includes:

[0147] Acquire at least one construction design;

[0148] Input at least one construction design into the recognition network, and recognize the ocean operation project information. The ocean operation project information includes multiple sub-project information and the dependency relationship information between sub-projects. The sub-project information at least includes sub-project identification, operation area, and sub-project workload.

[0149] The first operation scheduling model includes an encoding network, a generation network, and a decision network;

[0150] When the first generation module 802 inputs the ocean operation project information into the first operation scheduling model to generate the first scheduling information, it includes:

[0151] Input multiple sub-project information into the encoding network to obtain multiple sub-project vectors;

[0152] Input multiple sub-project vectors into the generation network, and generate multiple first scheduling sub-information corresponding to multiple sub-projects through the generation network; The first scheduling sub-information includes operation ship information, operation days information, and window label information;

[0153] Input multiple first scheduling sub-information and the dependency relationship data between sub-projects into the decision network to generate the first scheduling information.

[0154] The generation network includes multiple generation sub-networks. Inputting multiple sub-item vectors into the generation network, multiple first scheduling sub-information corresponding to multiple sub-items are generated by the generation network, including:

[0155] Obtain the sub-item identifier corresponding to the sub-item vector and the label of the generation sub-network;

[0156] Match the sub-item identifier and the label of the generation sub-network to obtain the generation sub-network;

[0157] Input the sub-item vector into the generation sub-network to generate the first scheduling sub-information.

[0158] The decision-making network adopts a multi-network fusion structure based on dependency relationships, including an input layer, an embedding layer, a feature extraction layer, a first gating layer, a multi-block shared MLP layer, a linear layer, and an output layer;

[0159] Input multiple scheduling sub-information and dependency relationship data between sub-items into the decision-making network to generate the first scheduling information, including:

[0160] Use the input layer to input multiple first scheduling sub-information and dependency relationship information between sub-items;

[0161] Use the embedding layer to transform the first scheduling sub-information and the corresponding dependency relationship information into feature vectors, obtaining sub-information feature vectors and dependency relationship feature vectors;

[0162] Use the fusion layer to fuse the sub-information feature vectors and the dependency relationship feature vectors to obtain a fused feature vector;

[0163] Use multiple feature extraction networks in the feature extraction layer to extract features from the fused feature vector to obtain multiple initial feature vectors;

[0164] Use the first gating layer to generate first weight data corresponding to each feature extraction network, and perform weighted summation on the initial feature vectors output by each feature extraction network to obtain a first combined feature vector;

[0165] Use the multi-block shared MLP layer to perform task migration processing on the first combined feature vector to obtain a first migration feature vector;

[0166] Use the linear layer to perform transformation processing on the first migration feature vector to obtain the first scheduling information;

[0167] Use the output layer to output the first scheduling information.

[0168] The multi-block shared MLP layer is a multi-level block network structure. Each block includes m MLPs and a shared layer. The shared layer of the i-th block is used to extract features from the output features of the m MLPs in the current block to obtain m knowledge features, and the MLP ik1 The output features are fused with the knowledge features extracted by the MLP i k2 and used as the input of the MLP, where m is the number of workboats, MLP represents a multi-layer perceptron model, k2 = 1:m and k2 ≠ k1. i+1 k1

[0169] The second generation module 803 generates a first scheduling diagram according to the first scheduling information, including: using the workboat as the root node, and using the triple composed of the job item identifier, the project sub-identifier, and the operation area as the leaf node, and using the execution sequence corresponding to the project sub-identifier as the constraint condition to construct the first scheduling diagram.

[0170] The second acquisition module 804 acquires the real-time information of the operation area, including: acquiring one or more of typhoon information, wave information, fishery information, and exercise information in the operation area.

[0171] The third generation module 805 inputs the real-time information and the first scheduling diagram into the second job scheduling model to generate the second scheduling information, including:

[0172] Encoding the real-time information in the operation area using the first encoding layer to obtain the first encoded feature;

[0173] Encoding the first scheduling diagram using the second encoding layer to obtain the second encoded feature;

[0174] Using the feature fusion layer to splice the first encoded feature and the second encoded feature to obtain the fused feature;

[0175] Using the decoding layer to decode the fused feature to obtain the second scheduling information.

[0176] The fourth generation module 806 generates a second scheduling diagram according to the second scheduling information, including: using the workboat as the root node, and using the triple composed of the job item identifier, the project sub-identifier, and the operation area as the leaf node, and using the execution sequence corresponding to the project sub-identifier as the constraint condition to construct the second scheduling diagram.

[0177] The content of the method in the first embodiment of the present invention is applicable to the device embodiment. The functions specifically implemented by the device embodiment are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method.

[0178] Figure 9 ​It is a schematic structural diagram of the electronic device proposed in the third embodiment of the present invention. In this embodiment, the memory stores program instructions for implementing the ship scheduling method in the multi-project ocean operation of any of the above embodiments. The processor is used to execute the program instructions stored in the memory to perform ship scheduling for the multi-project ocean operation. Among them, the processor can also be called a CPU (Central Processing Unit, central processing unit). The processor may be an integrated circuit chip with signal processing capabilities. The processor can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0179] The content of the method in the first embodiment of the present invention is applicable to this embodiment of the electronic device. The functions specifically implemented by this embodiment of the electronic device are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method.

[0180] Figure 10 It is a schematic structural diagram of the computer-readable storage medium of the fourth embodiment of the present invention. The computer-readable storage medium of the fourth embodiment of the present invention stores program instructions capable of implementing the ship scheduling method in the multi-project ocean operation. Among them, the program instructions can be stored in the above storage medium in the form of a software product, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in various embodiments of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0181] The content of the method in the first embodiment of the present invention is applicable to this embodiment of the computer-readable storage medium. The functions specifically implemented by this embodiment of the computer-readable storage medium are the same as those of the above method embodiment, and the beneficial effects achieved are also the same as those of the above method.

[0182] This embodiment also provides a computer program product. When the computer program product runs on a computer, it enables the computer to execute the above-related steps to implement the ship scheduling method in the multi-project ocean operation provided in the above embodiment.

[0183] Those skilled in the art can understand that the modules in the devices in the embodiments of the present invention can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments of the present invention can be combined into one module or unit or component, and in addition, they can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, any combination can be adopted to combine all the features disclosed in this specification (including the corresponding claims, abstract and drawings) and all the processes or units of any method or device so disclosed. Unless otherwise clearly stated, each feature disclosed in this specification (including the corresponding claims, abstract and drawings) can be replaced by an alternative feature that provides the same, equivalent or similar purpose.

[0184] Through the description of the above embodiments, those skilled in the art can understand that for the convenience and conciseness of description, only the division of the above functional modules is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0185] It should be noted that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus or device), or in combination with these instruction execution systems, apparatus or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate or transport a program for use by or in connection with an instruction execution system, apparatus or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation or other suitable processing as necessary, and then stored in a computer memory.

[0186] In addition, the various embodiments in this specification are described in a progressive manner. For the same or similar parts among the various embodiments, reference can be made to each other. In particular, for embodiments such as devices and equipment, since they are basically similar to the method embodiments, the relevant parts can refer to the partial description of the method embodiments. The embodiments of the devices, equipment, etc. described above are only illustrative. The modules, units, etc. described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed to multiple places, such as the nodes of a system network. Specifically, some or all of the modules and units can be selected according to actual needs to achieve the purpose of the above embodiment solutions. Those skilled in the art can understand and implement them without creative efforts.

[0187] It should be understood that each part of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following well-known technologies in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0188] In the description of this specification, the description with reference to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0189] In addition, the terms "first", "second", etc. used in the embodiments of the present invention are only for descriptive purposes and cannot be understood as indicating or implying relative importance, or implicitly indicating the number of technical features indicated in this embodiment. Thus, the features defined with the terms "first", "second", etc. in the embodiments of the present invention can clearly or implicitly indicate that at least one such feature is included in this embodiment. In the description of the present invention, the meaning of the word "plural" is at least two or more, such as two, three, four, etc., unless otherwise specifically defined in the embodiment.

[0190] In the embodiments of the present invention, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or apparatus comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or apparatus. Without further limitation, an element defined by the phrase "comprising an …" does not exclude the presence of additional identical elements in the process, method, article or apparatus comprising such element. In addition, components, features, and elements with the same name in different embodiments of the present invention may have the same meaning or different meanings, and their specific meanings need to be determined according to their explanations in the specific embodiments or further in combination with the context of the specific embodiments.

[0191] Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention. After considering the specification and practicing the present invention, those skilled in the art will readily conceive of other embodiments of the present invention. This application is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include known common general knowledge or conventional technical means in the technical field not disclosed by the present invention. The specification and embodiments are only to be regarded as exemplary, and the true scope and spirit of the present invention are pointed out by the following claims.

Claims

1. A method for dispatching ships in multi-project marine operations, characterized in that: The following steps are involved: Obtain information on marine operation projects; Inputting the marine operation project information into a first operation scheduling model to generate first scheduling information; generating a first scheduling graph according to the first scheduling information; Obtain real-time information of the operation area; Inputting the real-time information of the operation area and the first scheduling diagram into a second operation scheduling model to generate second scheduling information; generating a second scheduling diagram according to the second scheduling information; and performing scheduling operations on the ship according to the second scheduling diagram; Wherein, the acquisition of marine operation project information specifically includes the following steps: Obtain at least one construction design plan, wherein the construction design plan has a plurality of sub-projects; Identify the construction design scheme, and obtain marine operation project information in the construction design scheme; the marine operation project information includes a plurality of sub-project information and dependency information between sub-projects, and the sub-project information includes at least a sub-project identifier, an operation area, and a sub-project workload; The first job scheduling model includes an encoding network, a generation network and a decision network; The inputting of the marine operation project information into the first operation scheduling model to generate the first scheduling information specifically includes: Inputting the plurality of sub-item information into an encoding network to obtain a plurality of sub-item vectors; Input the plurality of sub-item vectors into a generation network, and generate a plurality of first scheduling sub-information corresponding to the plurality of sub-items through the generation network; the first scheduling sub-information at least includes operation vessel information, operation day information and window label information; Inputting the plurality of first scheduling sub-information and dependency information between the sub-items into a decision network to generate first scheduling information; The second job scheduling model includes a first encoding layer, a second encoding layer, a feature fusion layer and a decoding layer; The step of inputting the real-time information of the operation area and the first scheduling diagram into a second operation scheduling model to generate second scheduling information specifically includes: Encode the real-time information in the operation area using the first encoding layer to obtain a first encoding feature; Encoding the first scheduling graph using a second encoding layer to obtain a second encoding feature; The first coding feature and the second coding feature are concatenated using a feature fusion layer to obtain a fused feature; The fused features are decoded using the decoding layer to obtain the second scheduling information.

2. A method for dispatching ships in multi-project marine operations according to claim 1, characterized in that: The decision network adopts a multi-network fusion structure based on dependency, including an input layer, an embedding layer, a feature extraction layer, a first gating layer, a multi-block shared MLP layer, a linear layer and an output layer; The step of inputting the plurality of scheduling sub-information and the dependency relationship information between the sub-items into the decision network to generate the first scheduling information specifically includes: Inputting a plurality of first scheduling sub-information and dependency relationship information between sub-items through an input layer; The first scheduling sub-information and the corresponding dependency information are converted into feature vectors by using an embedding layer to obtain a sub-information feature vector and a dependency feature vector; The sub-information feature vector and the dependency feature vector are fused using the fusion layer to obtain a fused feature vector; Using multiple feature extraction networks in the feature extraction layer to extract features from the fused feature vector, multiple initial feature vectors are obtained; Using the first gating layer to generate first weight data corresponding to each feature extraction network, performing weighted summation on the initial feature vectors output by each feature extraction network to obtain a first combined feature vector; Performing task migration processing on the first combined feature vector using multiple shared MLP layers to obtain a first migration feature vector; The first migration feature vector is transformed by using a linear layer to obtain first scheduling information; The output layer is used to output the first scheduling information.

3. A method for dispatching ships in multi-project marine operations according to claim 2, characterized in that: The multi-block shared MLP layer is a multi-level block network structure, each block includes m MLPs and a shared layer, the shared layer of the i-th block is used to extract the output features of the m MLPs in the current block, obtain m knowledge features, and convert the MLP i k1 The output features of MLP i k2 The extracted knowledge features are fused as MLP i+1 k1 The input of , where m is the number of operating ships, MLP represents the multi-layer perceptron model, k2=1:m and k2≠k1.

4. A method for dispatching ships in multi-project marine operations according to claim 1, characterized in that: The first scheduling information includes the operation vessel identifier, the operation project identifier, the project sub-identifier, the operation area and the execution sequence corresponding to the project sub-identifier; The generating of the first scheduling graph according to the first scheduling information is specifically: The first scheduling graph is constructed with the operating vessel as the root node, the triple consisting of the operating project ID, the project sub-ID, and the operating area as the leaf node, and the execution sequence corresponding to the project sub-ID as the constraint condition.

5. A ship dispatching device for multi-project marine operations, characterized in that: The device comprises: The first acquisition module is used to acquire marine operation project information; Wherein, the acquisition of marine operation project information specifically includes the following steps: Obtain at least one construction design plan, wherein the construction design plan has a plurality of sub-projects; Identify the construction design scheme, and obtain marine operation project information in the construction design scheme; the marine operation project information includes a plurality of sub-project information and dependency information between sub-projects, and the sub-project information includes at least a sub-project identifier, an operation area, and a sub-project workload; A first generating module, used for inputting the marine operation project information into a first operation scheduling model to generate first scheduling information; Wherein, the first job scheduling model includes an encoding network, a generation network and a decision network; The inputting of the marine operation project information into the first operation scheduling model to generate the first scheduling information specifically includes: Inputting the plurality of sub-item information into an encoding network to obtain a plurality of sub-item vectors; Input the plurality of sub-item vectors into a generation network, and generate a plurality of first scheduling sub-information corresponding to the plurality of sub-items through the generation network; the first scheduling sub-information at least includes operation vessel information, operation day information and window label information; Inputting the plurality of first scheduling sub-information and dependency information between the sub-items into a decision network to generate first scheduling information; A second generating module, used to generate a first scheduling graph according to the first scheduling information; The second acquisition module is used to obtain real-time information of the operation area; A third generating module, used for inputting the real-time information of the operation area and the first scheduling diagram into a second operation scheduling model to generate second scheduling information; Wherein, the second job scheduling model includes a first encoding layer, a second encoding layer, a feature fusion layer and a decoding layer; The step of inputting the real-time information of the operation area and the first scheduling diagram into a second operation scheduling model to generate second scheduling information specifically includes: Encode the real-time information in the operation area using the first encoding layer to obtain a first encoding feature; Encoding the first scheduling graph using a second encoding layer to obtain a second encoding feature; The first coding feature and the second coding feature are concatenated using a feature fusion layer to obtain a fused feature; Using a decoding layer to decode the fused features to obtain second scheduling information; The fourth generating module is used to generate a second scheduling diagram according to the second scheduling information; and perform scheduling operations on the ship according to the second scheduling diagram.

6. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement a method for scheduling ships in multi-project marine operations as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement a method for scheduling ships in multi-project marine operations according to any one of claims 1 to 4.

Images