Container terminal loading and unloading resource scheduling system and method based on artificial intelligence

Abstract

The invention discloses a container terminal loading and unloading resource scheduling system and method based on artificial intelligence, and relates to the field of loading and unloading resource scheduling. The loading and unloading resource state parameters of each type of containers at the end moment of each stage in the current loading and unloading process are mapped subsequently, and then the loading and unloading priority data of a plurality of containers are adjusted, so that the condition that the resource state parameters at the end moment of a certain stage do not reach corresponding limit values in the current loading and unloading process is ensured; therefore, the subsequent loading and unloading process is smoothly carried out, and the loading and unloading efficiency is improved; wherein the random variables are introduced, so that the uncertain events can be predicted to a certain extent, and the robustness of a scheme for carrying out resource scheduling planning in advance is improved to a certain extent.

Description

Technical Field

[0001] The present invention belongs to the field of handling resource scheduling. Specifically, it particularly relates to a container terminal handling resource scheduling system and method based on artificial intelligence. Background Art

[0002] The existing loading and unloading priorities for containers are often set in advance. However, this does not consider the dynamic changes in the handling resources during the loading and unloading process, which may lead to situations where resources are already occupied or insufficient during the loading and unloading process, thus unable to ensure the smooth progress of the entire loading and unloading process and affecting the loading and unloading efficiency. Summary of the Invention

[0003] In view of the problems in the related art, the present invention proposes a container terminal handling resource scheduling system and method based on artificial intelligence to overcome the above-mentioned technical problems existing in the existing related technologies.

[0004] To solve the above technical problems, the present invention is realized through the following technical solutions: The present invention is a container terminal handling resource scheduling method based on artificial intelligence, including the following steps: S1. Collect the container handling resource status parameters and the corresponding container scale parameters at the start and end times of each handling stage of several groups of historical container handling to obtain a historical container handling resource status parameter matrix set and a historical container scale parameter matrix; S2. Use the historical container handling resource status parameter matrix set and the historical container scale parameter matrix to construct a final container handling resource status parameter moment mapping equation matrix; S3. Set the loading and unloading priority data for each current container to obtain a current initial container loading and unloading priority data set; S4. By looping, input the handling resource status parameters and the corresponding container scale data at the start time of each current handling stage into the corresponding mapping equation in the final container handling resource status parameter moment mapping equation matrix to obtain a mapping data set; then adjust the current initial container loading and unloading priority data set according to the number of resource status parameters reaching the corresponding resource status limit in the mapping data set to obtain a current final container loading and unloading priority data set; This solution first constructs the mapping relationship between the numerical values of the state parameters of each type of container handling resource at the start and end times of each handling stage, maps the state parameters of each type of container handling resource at the end time of each stage in the current handling process, and then adjusts the handling priority data of multiple containers according to the state parameters of each type of container handling resource at the end time of each stage obtained by the mapping, ensuring that the state parameter of the resource at the end time of a certain stage in the current handling process does not reach the corresponding limit value, thus ensuring the smooth progress of the subsequent handling process and improving the handling efficiency.

[0005] Preferably, S1 includes the following steps: S11. Set the state parameters of several types of terminal container handling resources to obtain the set of container handling resource state parameter types; divide the process of handling the current container into stages to obtain the set of current container handling stages; then set the scale parameters of several types of containers to obtain the set of container scale parameter types. S12. In cooperation with the set of container handling resource state parameter types, the set of container scale parameter types, and the set of current container handling stages, collect several groups of historical container handling resource state parameters and the corresponding container scale parameters at the start and end times of each handling stage of historical container handling at the same terminal to obtain the set of historical container handling resource state parameter matrices and the historical container scale parameter matrix. By setting the set of container handling resource state parameter types, it provides a basis for collecting the resource type parameters corresponding to the disassembly of containers at the terminal, which is a quantitative description of the resources required for handling various types of containers at the terminal; since the resources required in different stages are different during the process of handling containers, based on this, the process of handling containers is divided into stages, thus improving the accuracy of subsequent resource scheduling; in addition, by collecting the set of historical container handling resource state parameter matrices and the historical container scale parameter matrix, it provides a basis for constructing the mapping equation between the container handling resource state parameters at the start and end times of different stages.

[0006] Preferably, S2 includes the following steps: S21. In cooperation with the set of container handling resource state parameter types, the set of current container handling stages, and the set of container scale parameter types, construct the initial mapping equation of each container handling resource state parameter corresponding to the end time of each container handling stage to obtain the initial container handling resource state parameter end time mapping equation matrix. S22. Adjust each initial container handling resource state parameter engraving mapping equation in the initial container handling resource state parameter engraving mapping equation matrix by using the historical container handling resource state parameter matrix set and the historical container scale parameter matrix, so as to obtain the final container handling resource state parameter engraving mapping equation matrix; By taking the container handling resource state parameter data at the start time of the container stuffing and handling stage and the scale parameters of various types of containers as the independent variables of the initial container handling resource state parameter engraving mapping equation, it is convenient to subsequently achieve the direct mapping from the container handling resource state parameter data and the scale parameters of various types of containers at the start time to the container handling resource state parameter data at the end time; Due to the uncertainty of the container handling resource state parameter data, such as ship delays, equipment failures and other events; Based on this, by introducing random variables, it is possible to make a certain degree of prediction for these uncertain events, thereby improving the robustness of the resource scheduling plan made in advance to a certain extent; Among them, by adjusting the initial container handling resource state parameter engraving mapping equation by using the collected historical data, the fitting degree of the final container handling resource state parameter engraving mapping equation to the container handling resource scheduling in reality is improved, and further the accuracy of the subsequent resource scheduling plan specified by the final container handling resource state parameter engraving mapping equation is improved.

[0007] Preferably, S22 includes the following steps: S221. Substitute the data at the start time of each stage of the historical container handling resource state parameter matrix set and the data in the historical container scale parameter matrix into the corresponding initial container handling resource state parameter engraving mapping equation in the initial container handling resource state parameter engraving mapping equation matrix for mapping, so as to obtain the historical engraving container handling resource state parameter matrix set; S222. Set the engraving container handling resource state parameter mapping error threshold; Calculate the error data between the historical engraving container handling resource state parameter matrix set and the container handling resource state parameter at the end time of the same stage and the same type in the historical container handling resource state parameter matrix set, so as to obtain the historical engraving container handling resource state parameter mapping error data matrix; S223. When there is mapping error data greater than or equal to the engraving container handling resource status parameter mapping error threshold in the historical engraving container handling resource status parameter mapping error data matrix, use the initial container handling resource status parameter engraving mapping equation corresponding to this mapping error data as the container handling resource status parameter engraving mapping equation to be adjusted; adjust the container handling resource status parameter engraving mapping equation to be adjusted until there is no mapping error data greater than or equal to the engraving container handling resource status parameter mapping error threshold in the historical engraving container handling resource status parameter mapping error data matrix; otherwise, there is no need to adjust the container handling resource status parameter engraving mapping equation to be adjusted. By substituting the collected historical data into the corresponding initial container handling resource status parameter engraving mapping equation for mapping, and then calculating the error between the mapping result and the actual data, the mapping accuracy rate of the initial container handling resource status parameter engraving mapping equation can be detected; furthermore, it can be determined whether it is necessary to adjust the initial container handling resource status parameter engraving mapping equation; among them, by setting the engraving container handling resource status parameter mapping error threshold, a quantitative determination index is provided for determining whether it is necessary to adjust the initial container handling resource status parameter engraving mapping equation.

[0008] Preferably, in S223, the Harris hawk optimization algorithm is used to adjust the container handling resource status parameter engraving mapping equation to be adjusted.

[0009] Preferably, S3 includes the following steps: S31. Use the first current container handling stage in the current container handling stage set as the current container handling stage to be adjusted; set several containers that need to be handled currently to obtain the current container set. S32. Set the handling priority data of each container in the current container set to obtain the current initial container handling priority data set; set the value limit corresponding to the status parameter of each type of container handling resource to obtain the container handling resource status parameter limit value set; in combination with the current initial container handling priority data set, use the container with the highest priority as the current container to be handled. Since it is necessary to determine the order of handling containers, by setting the current initial container handling priority data set, the order for subsequent handling of current containers is determined; by setting the value limit corresponding to the status parameter of each type of container handling resource, when a certain handling stage is completed, if a certain status parameter reaches the limit value, the subsequent handling process will be completed, resulting in an increase in handling time. This provides a quantitative determination basis for subsequent determination of whether it is necessary to adjust the handling priority of each current container.

[0010] Preferably, S4 includes the following steps: S41. In combination with the container handling resource status parameter type set and the container scale parameter type set, obtain various types of handling resource status parameters at the start time of the current container handling stage to be adjusted, and obtain the container handling resource status parameter set at the current start time; then collect the scale parameters of each container in the current container set to obtain the current container scale parameter matrix; S42. Input the scale parameter corresponding to the current container to be handled and each status parameter in the container handling resource status parameter set at the current start time into the corresponding mapping equation in the final container handling resource status parameter end-time mapping equation matrix for mapping, and obtain the container handling resource status parameter set at the current end time; When there is a resource status parameter in the container handling resource status parameter set at the current end time that is the same as the corresponding resource status parameter limit value in the container handling resource status parameter limit value set, adjust the priority data corresponding to the containers that have not started handling or have not completed handling in the current initial container handling priority data set until there is no resource status parameter in the container handling resource status parameter set at the current end time that is the same as the corresponding resource status parameter limit value in the container handling resource status parameter limit value set; otherwise, there is no need to adjust the current initial container handling priority data set; after the adjustment is completed, use the next handling stage of the current container handling stage to be adjusted as the current container handling stage to be adjusted, replace the container handling resource status parameter set at the current start time with the container handling resource status parameter set at the current end time, and repeat S41 and S42 until the current container handling stage to be adjusted is the last handling stage in the current container handling stage set; S43. When the current container to be handled is completed, use the current container corresponding to the priority data next only to the current container to be handled in the current initial container handling priority data set as the current container to be handled, and repeat S41, S42, and S43 until all the containers in the current container set are handled; use the current adjusted container handling priority data set obtained after the adjustment of the priority data during the handling of the last current container in the current container set as the current final container handling priority data set; Since the sizes of different containers are different, the loading and unloading sequence has a certain impact on the entire loading and unloading process. For example, combining large containers and small containers for transportation results in higher utilization rate of the transportation space. Otherwise, the space utilization rate is lower. Based on this, by cycling through each current container and each loading and unloading stage, and according to the loading and unloading conditions of the corresponding containers at each stage, the loading and unloading sequence of the current containers is dynamically optimized to ensure that all current containers can be successfully loaded and unloaded, which not only ensures the successful completion of loading and unloading, but also improves the efficiency of the loading and unloading process.

[0011] Preferably, obtaining various types of loading and unloading resource status parameters at the start time of the current container to be adjusted for loading and unloading stage in S41, and obtaining the current start time container loading and unloading resource status parameter set includes the following steps: S411: Set several historical time points before the start of the current loading and unloading process to obtain a historical time point set; in combination with the container loading and unloading resource status parameter type set and the historical time point set, collect each type of container loading and unloading resource status parameter corresponding to each historical time point to obtain the current historical container loading and unloading resource status parameter matrix; S412: According to the current historical container loading and unloading resource status parameter matrix and using the BP neural network model, predict various types of loading and unloading resource status parameters at the start time of the current container to be adjusted for loading and unloading stage to obtain the current start time container loading and unloading resource status parameter set; The BP neural network model can map input data to output data. This mapping relationship can be linear or non-linear and is suitable for processing complex data patterns. Mathematical theory proves that a three-layer neural network can approximate any non-linear continuous function with arbitrary accuracy, which makes it particularly suitable for solving problems with complex internal mechanisms. After training, it can predict data that has not been seen before because it has a memory function and can remember the data patterns in training. Based on the above advantages, this solution uses the BP neural network model to predict various types of loading and unloading resource status parameters at the start time of the current container to be adjusted for loading and unloading stage, ensuring the accuracy of the predicted data, and thus ensuring the accuracy of adjusting the container loading and unloading priority data based on the predicted data.

[0012] Preferably, adjusting the priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set in S42 includes the following steps: S421. Set the value range of each priority data corresponding to the containers that have not started or completed loading and unloading in the current initial container loading and unloading priority dataset to obtain the current priority data value range set; construct a Harris hawk population for adjusting the loading and unloading priority; set the maximum number of iterations of the Harris hawk population for adjusting the loading and unloading priority to and the current number of iterations to , which are respectively denoted as the maximum number of iterations for loading and unloading adjustment and the current number of iterations for loading and unloading adjustment; S422. Set the initial position of each Harris hawk in the Harris hawk population for adjusting the loading and unloading priority according to the current priority data value range set to obtain the second initial position matrix; S423. Construct the fitness function of the Harris hawk population for adjusting the loading and unloading priority; S424. Start the iteration. Before the iteration, set the current number of iterations for loading and unloading adjustment to 1; in the first round of iteration, use the fitness function of the Harris hawk population for adjusting the loading and unloading priority to calculate the fitness values of the initial positions of each Harris hawk in the second initial position matrix to obtain the third fitness value set; take the maximum fitness value in the third fitness value set and the corresponding initial position of the Harris hawk as the third global best fitness and the third global best position respectively; update the initial positions of each Harris hawk in the second initial position matrix according to the third global best fitness and the third global best position; after the update is completed, increment the current number of iterations for loading and unloading adjustment by 1 and enter the next round of iteration; In each other round of iteration, use the fitness function of the Harris hawk population for adjusting the loading and unloading priority to calculate the fitness values of the positions of each Harris hawk in the Harris hawk population for adjusting the loading and unloading priority updated in the previous round of iteration to obtain the fourth fitness value set; take the maximum fitness value in the fourth fitness value set and the corresponding position of the Harris hawk as the fourth global best fitness and the fourth global best position respectively; update the positions of each Harris hawk in the Harris hawk population for adjusting the loading and unloading priority updated in the previous round of iteration according to the fourth global best fitness and the fourth global best position; after the update is completed, increment the current number of iterations for loading and unloading adjustment by 1 and enter the next round of iteration; S425. When , stop the iteration to obtain the second final global best fitness and the second final global best position; otherwise, continue the iteration until ; take the first final global best fitness as the optimized number of loading and unloading limits reached. When the optimized number of loading and unloading limits reached is 0, the adjustment is completed, and take the second final global best position as the current adjusted container loading and unloading priority dataset; otherwise, return to S424 to continue the iteration until the optimized number of loading and unloading limits reached is 0; In this solution, the Harris hawk optimization algorithm is used to adjust the respective priority data corresponding to the containers that have not started or completed loading and unloading in the current initial container loading and unloading priority dataset, and the number of resource status parameters in the current container loading and unloading resource status parameter set at the end time that are the same as the resource status parameter limits in the resource status parameter and container loading and unloading resource status parameter limit set is used as the fitness function. Therefore, as the iteration progresses, the number of resource status parameters in the current container loading and unloading resource status parameter set at the end time that are the same as the resource status parameter limits in the resource status parameter and container loading and unloading resource status parameter limit set becomes fewer and fewer, and finally there are no resource status parameters that are the same as the corresponding limit values, thus ensuring the smooth progress of the subsequent loading and unloading process.

[0013] An artificial intelligence-based container terminal loading and unloading resource scheduling system includes a current loading and unloading stage setting module, a container loading and unloading associated parameter setting module, a historical container loading and unloading data collection module, a container loading and unloading resource status parameter end-time mapping equation construction module, a current container loading and unloading priority set data setting module, and a current container loading and unloading priority data adjustment module.

[0014] The present invention has the following beneficial effects: 1. In the present invention, by constructing the mapping relationship between the numerical values of the container loading and unloading resource status parameters of each type at the start time and end time of each loading and unloading stage, it is possible to map the container loading and unloading resource status parameters of each type at the end time of each stage in the current loading and unloading process subsequently, and then adjust the loading and unloading priority data of multiple containers according to the container loading and unloading resource status parameters of each type at the end time of each stage obtained by the mapping, ensuring that there are no resource status parameters at the end time of a certain stage in the current loading and unloading process that reach the corresponding limit values, thus ensuring the smooth progress of the subsequent loading and unloading process and improving the loading and unloading efficiency.

[0015] 2. In the present invention, by dividing the process of loading and unloading containers into stages, the accuracy of subsequent resource scheduling is improved.

[0016] 3. In the present invention, by introducing random variables, it is possible to make a certain degree of prediction for these uncertain events, thereby improving the robustness of the resource scheduling plan for early resource scheduling to a certain extent.

[0017] 4. In the present invention, the Harris hawk optimization algorithm is used to adjust the respective priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set. As the iteration progresses, the number of resource status parameters in the current container loading and unloading resource status parameter set at the end moment that are the same as the resource status parameter limits in the resource status parameter and container loading and unloading resource status parameter limit set becomes fewer and fewer. Eventually, there is no resource status parameter that is the same as the corresponding limit value, thus ensuring the smooth progress of the subsequent loading and unloading process.

[0018] Of course, it is not necessary for any product implementing the present invention to achieve all the above-mentioned advantages simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0020] Figure 1 It is a flowchart showing the process of the container terminal loading and unloading resource scheduling method based on artificial intelligence of the present invention; Figure 2 It is a flowchart showing the process of constructing the final container loading and unloading resource status parameter moment mapping equation matrix of the present invention; Figure 3 It is a flowchart showing the process of adjusting the current initial container loading and unloading priority data set of the present invention; Figure 4 It is a block diagram showing the modules of the container terminal loading and unloading resource scheduling system based on artificial intelligence of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The technical solutions in the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the invention. Obviously, the described embodiments are only a part of the embodiments of the invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the invention without creative efforts belong to the scope of protection of the invention.

[0022] Embodiment 1 Please refer to Figures 1-3 , this embodiment is a container terminal loading and unloading resource scheduling method based on artificial intelligence, including the following steps: S1. Collect the container handling resource status parameters and the corresponding container size parameters at the start and end times of each handling stage in several groups of historical container handling operations, to obtain a historical container handling resource status parameter matrix set and a historical container size parameter matrix; S1 includes the following steps: S11. Set several types of quay container handling resource status parameters to obtain a container handling resource status parameter type set; divide the process of current container handling into stages to obtain a current container handling stage set; then set several types of container size parameters to obtain a container size parameter type set; The container handling resource status parameter type set includes quay crane / yard crane busy / idle status, truck position and load, yard storage occupancy rate, ship operation priority, etc.; the container size parameter type set includes total length, total width, total height, door frame opening length, and door frame opening width, etc.; among them, the process of current container handling can be divided into stages according to time or also according to the handling steps; Among them, the quay crane / yard crane busy / idle status can be represented by binary coding (0 - idle, 1 - in operation, 2 - faulty), such as [Quay Crane 1:1, Quay Crane 2:0, Yard Crane:2], and data can be obtained using a PLC controller or device IoT sensor (such as motor current monitoring); the truck position can be represented by longitude and latitude, and the truck load is represented as 0: empty load, 1: full load; the truck position and load can be obtained through GPS / UWB (Ultra Wideband) and in-vehicle weight sensors respectively; the yard storage occupancy rate can be divided by block, such as the occupied storage positions / total storage positions in Area A01 and Area B02 are represented as {"A01":0.85,"B02":0.3}, and data can be collected through yard block scanners (lidar or cameras); Ship operation priority: The priority score can be calculated based on the ship type (liner > bulk carrier); S12. In cooperation with the container handling resource status parameter type set, the container size parameter type set, and the current container handling stage set, collect the container handling resource status parameters and the corresponding container size parameters at the start and end times of each handling stage in several groups of historical container handling operations at the same quay, to obtain a historical container handling resource status parameter matrix set and a historical container size parameter matrix a2, where a1i represents the historical container handling resource status parameter matrix corresponding to the i-th group of historical container handling operations collected, represents the total number of groups in the historical container handling process; a1i and a2 are as follows respectively, ; ; Among them, and respectively represent the state parameters of the k-th type of quay container handling resources at the start and end times of the j-th handling stage in a1i, represents the total number of types of quay container handling resource state parameters set, represents the total number of stages of container handling set; Table The scale parameter of the k-th type of the container corresponding to the i-th group of historical container handling collected ; S2. Construct a final container handling resource state parameter end-time mapping equation matrix using the historical container handling resource state parameter matrix set and the historical container scale parameter matrix; The said S2 includes the following steps: S21. Cooperate with the container handling resource state parameter type set, the current container handling stage set, and the container scale parameter type set to construct an initial mapping equation for each type of container handling resource state parameter corresponding to the end time of each container handling stage, and obtain an initial container handling resource state parameter end-time mapping equation matrix ; as follows, ; Among them, represents the initial mapping equation of the k-th type of container handling resource state parameter corresponding to the end time of the j-th container loading and unloading stage; as follows, ; Among them, bjk1 is 's dependent variable, representing the data of the k-th type of container handling resource state parameter at the end time of the j-th container loading and unloading stage; bjk2 is 's mapping relationship, representing 's combination relationship of each independent variable; such as product, addition, exponentiation, direct proportion, and inverse proportion, etc.; bjk2 is 's first independent variable, representing the data of the k-th type of container handling resource state parameter at the start time of the j-th container loading and unloading stage; is 's th independent variable, representing the scale parameter of the k-th type of the container ; is a random variable constructed for , representing a random perturbation, such as the probability of the quay crane stopping due to sudden weather changes increasing; S22. Adjust each initial container handling resource status parameter engraving mapping equation in the initial container handling resource status parameter engraving mapping equation matrix by using the historical container handling resource status parameter matrix set and the historical container scale parameter matrix to obtain the final container handling resource status parameter engraving mapping equation matrix; S22 includes the following steps: S221. Substitute the data at the start time of each stage of the historical container handling resource status parameter matrix set and the data in the historical container scale parameter matrix into the corresponding initial container handling resource status parameter engraving mapping equation in the initial container handling resource status parameter engraving mapping equation matrix for mapping to obtain the historical engraving container handling resource status parameter matrix set , represents the historical engraving container handling resource status parameter matrix obtained by mapping the historical container handling resource status parameter matrix corresponding to the i-th group of historical container handling collected; as follows, ; where, represents the data of the k-th type of terminal container handling resource status parameter at the end time of the j-th handling stage obtained by mapping; S222. Set the engraving container handling resource status parameter mapping error threshold; calculate the error data between the container handling resource status parameters at the end time of the same stage and the same type in the historical engraving container handling resource status parameter matrix set and the historical container handling resource status parameter matrix set to obtain the historical engraving container handling resource status parameter mapping error data matrix ; as follows, ; where, represents the error data between the k-th type of container handling resource status parameter corresponding to the end time of the j-th container loading and unloading stage between the historical engraving container handling resource status parameter matrix set and the historical container handling resource status parameter matrix set; the calculation formula is as follows, ; S223. When there is mapping error data greater than or equal to the engraving container handling resource status parameter mapping error threshold in the historical engraving container handling resource status parameter mapping error data matrix, use the initial container handling resource status parameter engraving mapping equation corresponding to this mapping error data as the container handling resource status parameter engraving mapping equation to be adjusted; adjust the container handling resource status parameter engraving mapping equation to be adjusted until there is no mapping error data greater than or equal to the engraving container handling resource status parameter mapping error threshold in the historical engraving container handling resource status parameter mapping error data matrix; otherwise, there is no need to adjust the container handling resource status parameter engraving mapping equation to be adjusted; The adjustment of the container handling resource status parameter engraving mapping equation to be adjusted in S223 includes the following steps: S2231. Set the value range of each constant coefficient in the container handling resource status parameter engraving mapping equation to be adjusted to obtain the set c1 of value ranges of constant coefficients of the engraving mapping equation to be adjusted; as follows, ; Where, 、 represent the lower limit and upper limit of the value of the i-th constant coefficient in the container handling resource status parameter engraving mapping equation to be adjusted, represents the total number of constant coefficients of the container handling resource status parameter engraving mapping equation to be adjusted; Construct a Harris hawk population for adjusting the engraving mapping of container handling resource status parameters; set the maximum number of iterations of the Harris hawk population for adjusting the engraving mapping of container handling resource status parameters to be and the current number of iterations to be , which are respectively recorded as the maximum number of engraving mapping iterations and the current number of engraving mapping iterations; the number of search space dimensions of the Harris hawk population for adjusting the engraving mapping of container handling resource status parameters is the same as ; S2232. Generate the initial position of each Harris hawk in the Harris hawk population for adjusting the engraving mapping of container handling resource status parameters according to the set of value ranges of constant coefficients of the engraving mapping equation to be adjusted to obtain the first initial position matrix ; as follows, ; Where, It represents the position component of the initial position of the j-th Harris hawk in the Harris hawk population for adjusting the moment mapping of the container handling resource status parameters in the i-th constant coefficient dimension of the moment mapping equation for adjusting the container handling resource status parameters. d1 represents the scale of the Harris hawk population for adjusting the moment mapping of the container handling resource status parameters; The generation formula is as follows. ; In the formula, rand1ji represents a random number between 0 and 1 generated for ; S2233. Construct the fitness function of the Harris hawk population for adjusting the moment mapping of the container handling resource status parameters ; as follows ; In the formula, It represents the error between the data obtained by substituting a set of constant coefficients obtained in each iteration into the moment mapping equation for adjusting the container handling resource status parameters, and then substituting the data at the start time of each stage of the historical container handling resource status parameter matrix set and the corresponding data in the historical container scale parameter matrix into the moment mapping equation for adjusting the container handling resource status parameters for mapping and the corresponding actual data. S2234. Start the iteration. Before the iteration, set the current iteration number of the moment mapping to 1; in the first round of iteration, use the fitness function of the Harris hawk population for adjusting the moment mapping of the container handling resource status parameters to calculate the fitness value of the initial position of each Harris hawk in the first initial position matrix, and obtain the first fitness value set; take the maximum fitness value in the first fitness value set and the corresponding initial position of the Harris hawk as the first global best fitness and the first global best position respectively; update the initial position of each Harris hawk in the first initial position matrix according to the first global best fitness and the first global best position; after the update is completed, add 1 to the current iteration number of the moment mapping and enter the next round of iteration. In each other round of iteration, use the fitness function of the Harris hawk population for adjusting the moment mapping of the container handling resource status parameters Calculate the fitness value of the position of each Harris hawk in the Harris hawk population adjusted by the container handling resource status parameter knot mapping updated in the previous iteration process to obtain the second fitness value set; take the maximum fitness value in the second fitness value set and the position of the corresponding Harris hawk as the second global best fitness and the second global best position respectively; update the position of each Harris hawk in the Harris hawk population adjusted by the container handling resource status parameter knot mapping updated in the previous iteration process according to the second global best fitness and the second global best position; after the update is completed, increment the knot mapping current iteration count by 1 and enter the next iteration; S2235. When is satisfied, stop the iteration to obtain the first final global best fitness and the first final global best position; otherwise, continue the iteration until is satisfied; take the first final global best fitness as the optimized mapping error data; when the optimized mapping error data is less than the knot container handling resource status parameter mapping error threshold, substitute each position component of the first final global best position into the knot mapping equation of the container handling resource status parameter to be adjusted and replace the corresponding mapping equation in the initial container handling resource status parameter knot mapping equation matrix, and the adjustment is completed; otherwise, return to S2234 to continue the iteration until the optimized mapping error data is less than the knot container handling resource status parameter mapping error threshold; The Harris hawk optimization algorithm can conduct extensive searches within the entire search space during the exploration stage, effectively avoiding the problem of falling into local optimal solutions and increasing the possibility of finding the global optimal solution; during the exploitation stage, the algorithm can conduct fine searches in the area near the current optimal solution according to different strategies, further improving the quality of the solution and having strong local search capabilities; it has good adaptability to different types of optimization problems and different initial conditions, and can still show good performance when facing complex optimization problems; based on the above advantages, the Harris hawk optimization algorithm is used in this solution to iteratively adjust multiple constant coefficients of the knot mapping equation of the container handling resource status parameter to be adjusted, and the mapping accuracy rate of the knot mapping equation of the container handling resource status parameter to be adjusted is used as the fitness function; therefore, as the iteration progresses, the mapping accuracy rate of the knot mapping equation of the container handling resource status parameter to be adjusted becomes higher and higher, and finally meets the mapping requirements; S3. Set the handling priority data of each current container to obtain the current initial container handling priority data set; The S3 includes the following steps: S31. Take the first current container loading and unloading stage in the current container loading and unloading stage concentration as the current container loading and unloading stage to be adjusted; set several containers that need to be loaded and unloaded currently to obtain the current container set. S32. Set the loading and unloading priority data for each container in the current container set to obtain the current initial container loading and unloading priority data set; the priority data in the current initial container loading and unloading priority data set is represented by natural numbers, and the larger the value, the higher the priority; set the value limit corresponding to the status parameter of each type of container loading and unloading resource to obtain the container loading and unloading resource status parameter limit value set; for example, when the occupancy rate of the yard berth reaches 100%, the busy and idle status of the quay crane / yard crane is 1 (in operation) or 2 (fault), etc.; in combination with the current initial container loading and unloading priority data set, take the container with the highest priority as the current container to be loaded and unloaded. S4. Input the status parameters of the loading and unloading resources at the start time of each current loading and unloading stage and the scale data of the corresponding containers into the corresponding mapping equations in the final container loading and unloading resource status parameter mapping equation matrix through a loop to obtain a mapping data set; then adjust the current initial container loading and unloading priority data set according to the number of status parameters of the loading and unloading resources that reach the corresponding resource status limit in the mapping data set to obtain the current final container loading and unloading priority data set. S4 includes the following steps: S41. In combination with the container loading and unloading resource status parameter type set and the container scale parameter type set, obtain the status parameters of various types of loading and unloading resources at the start time of the current container loading and unloading stage to be adjusted to obtain the current start time container loading and unloading resource status parameter set; then collect the scale parameters of each container in the current container set to obtain the current container scale parameter matrix. The steps for obtaining the status parameters of various types of loading and unloading resources at the start time of the current container loading and unloading stage to be adjusted in S41 to obtain the current start time container loading and unloading resource status parameter set include the following steps: S411. Set several historical time points before the start of the current loading and unloading process to obtain the historical time point set; in combination with the container loading and unloading resource status parameter type set and the historical time point set, collect the status parameters of each type of container loading and unloading resource corresponding to each historical time point to obtain the current historical container loading and unloading resource status parameter matrix. S412. According to the current historical container loading and unloading resource status parameter matrix and using the BP neural network model, predict the status parameters of various types of loading and unloading resources at the start time of the current container loading and unloading stage to be adjusted to obtain the current start time container loading and unloading resource status parameter set. S42. Input the scale parameter corresponding to the current container to be loaded and unloaded in the current container scale parameter matrix and each state parameter in the current container loading and unloading resource status parameter set into the corresponding mapping equation in the final container loading and unloading resource status parameter end-time mapping equation matrix for mapping to obtain the container loading and unloading resource status parameter set at the current end time; When there is a resource status parameter in the current container loading and unloading resource status parameter set that is the same as the corresponding resource status parameter limit value in the container loading and unloading resource status parameter limit value set, adjust the priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set until there is no resource status parameter in the current container loading and unloading resource status parameter set that is the same as the corresponding resource status parameter limit value in the container loading and unloading resource status parameter limit value set; otherwise, there is no need to adjust the current initial container loading and unloading priority data set; after the adjustment is completed, take the next loading and unloading stage of the current container to be adjusted as the current container to be adjusted loading and unloading stage, replace the current container loading and unloading resource status parameter set at the current start time with the current container loading and unloading resource status parameter set at the current end time, and repeat S41 and S42 until the current container to be adjusted loading and unloading stage is the last loading and unloading stage in the current container loading and unloading stage set; The adjustment of the priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set in S42 includes the following steps: S421. Set the value range of each priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set to obtain the current priority data value range set c2; as follows, ; Among them, 、 represent the lower limit and upper limit of the i-th priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set, represents the total number of priority data corresponding to the containers that have not started loading and unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set; Construct a Harris hawk population for adjusting the loading and unloading priority; set the maximum number of iterations of the Harris hawk population for adjusting the loading and unloading priority to be and the current number of iterations to be , which are respectively denoted as the maximum number of iterations for loading and unloading adjustment and the current number of iterations for loading and unloading adjustment; the number of search space dimensions of the Harris hawk population for adjusting the loading and unloading priority is the same as ; S422. Set the handling priority to adjust the initial positions of each Harris hawk in the Harris hawk population according to the set of current priority data value ranges, and obtain the second initial position matrix. ; ; Among them, represents the position component of the initial position of the j-th Harris hawk in the Harris hawk population with adjusted handling priority on the i-th priority data dimension corresponding to the containers that have not started handling or have not completed handling in the current initial container handling priority dataset, and d2 represents the scale of the Harris hawk population with adjusted handling priority; The generation formula of ; In the formula, rand2ji represents a random number between 0 and 1 generated for ; S423. Construct the fitness function of the Harris hawk population with adjusted handling priority ; as follows, ; In the formula, represents the total number of resource status parameters that are the same as the resource status parameter limit values in the container handling resource status parameter limit value set corresponding to the set of container handling resource status parameters obtained by applying a set of priority data obtained in each round of iteration to S32 and executing S41 and S42; S424. Start iteration. Before iteration, set the current iteration count of the handling adjustment to 1; in the first round of iteration, use the fitness function of the Harris hawk population with adjusted handling priority to calculate the fitness values of the initial positions of each Harris hawk in the second initial position matrix, and obtain the third fitness value set; take the maximum fitness value in the third fitness value set and the corresponding initial position of the Harris hawk as the third global best fitness and the third global best position respectively; update the initial positions of each Harris hawk in the second initial position matrix according to the third global best fitness and the third global best position; after the update is completed, increment the current iteration count of the handling adjustment by 1 and enter the next round of iteration; In each other round of iteration, use the fitness function of the Harris hawk population with adjusted handling priority Calculate the fitness value of the position of each Harris hawk in the Harris hawk population adjusted by the loading and unloading priority obtained in the previous round of iterations to obtain a fourth fitness value set; use the maximum fitness value in the fourth fitness value set and the corresponding position of the Harris hawk as the fourth global optimal fitness and the fourth global optimal position respectively; update the position of each Harris hawk in the Harris hawk population adjusted by the loading and unloading priority obtained in the previous round of iterations according to the fourth global optimal fitness and the fourth global optimal position; after the update is completed, add 1 to the current iteration number of the loading and unloading adjustment and enter the next round of iterations; S425, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until The first final global optimal fitness is used as the number of loading and unloading limits reached after optimization. When the number of loading and unloading limits reached after optimization is 0, the adjustment is completed, and the second final global optimal position is used as the current adjusted container loading and unloading priority data set; otherwise, return to S424 to continue iterating until the number of loading and unloading limits reached after optimization is 0; S43. When the loading and unloading of the current container to be loaded and unloaded is completed, the current container corresponding to the priority data next to the current container to be loaded and unloaded in the current initial container loading and unloading priority data set is used as the current container to be loaded and unloaded, and S41, S42 and S43 are repeated until all containers in the current container set are loaded and unloaded. The current adjusted container loading and unloading priority data set obtained after adjusting the priority data in the loading and unloading process of the last current container in the current container set is used as the current final container loading and unloading priority data set.

[0023] Embodiment 2 See also Figure 4 , this embodiment discloses an artificial intelligence-based container terminal loading and unloading resource scheduling system, the system can implement the method of the above embodiment, including a current loading and unloading stage setting module, a container loading and unloading associated parameter setting module, a historical container loading and unloading data collection module, a container loading and unloading resource state parameter moment mapping equation construction module, a current container loading and unloading priority set data setting module and a current container loading and unloading priority data adjustment module; The current loading and unloading stage setting module divides the process of loading and unloading the current container into stages to obtain a current container loading and unloading stage set; The container loading and unloading associated parameter setting module sets several types of terminal container loading and unloading resource state parameters and container scale parameters to obtain a container loading and unloading resource state parameter type set and a container scale parameter type set; The historical container handling data acquisition module cooperates with the container handling resource status parameter type set and the container scale parameter type set to collect several groups of historical container handling resource status parameters and corresponding container scale parameters at the start and end times of each handling stage of container handling, and obtains a historical container handling resource status parameter matrix set and a historical container scale parameter matrix; The container handling resource status parameter end-time mapping equation construction module constructs a final container handling resource status parameter end-time mapping equation matrix by using the historical container handling resource status parameter matrix set and the historical container scale parameter matrix; The current container handling priority set data setting module sets the handling priority data of each current container to obtain a current initial container handling priority data set; The current container handling priority data adjustment module inputs the handling resource status parameters and the corresponding container scale data at the start time of each current handling stage into the corresponding mapping equation in the final container handling resource status parameter end-time mapping equation matrix through a loop to obtain the container handling resource status parameter set at the current end time; and then adjusts the current initial container handling priority data set according to the number of resource status parameters reaching the limit in the container handling resource status parameter set at the current end time to obtain a current final container handling priority data set.

[0024] In the description of this specification, the descriptions referring to terms such as "one embodiment", "example", "specific example", etc. mean 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 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.

[0025] The preferred embodiments of the invention disclosed above are only used to help illustrate the invention. The preferred embodiments do not describe all the details in detail, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations can be made according to the content of this specification. This specification selects and specifically describes these embodiments in order to better explain the principle and practical application of the invention, so that those skilled in the art in the relevant technical field can well understand and utilize the invention.

Claims

1. A container terminal loading and unloading resource scheduling method based on artificial intelligence, characterized in that: The following steps are involved: S1. Collect several groups of historical container loading and unloading resource state parameters and corresponding container scale parameters at the start and end times of each loading and unloading stage of container loading and unloading, and obtain a historical container loading and unloading resource state parameter matrix set and a historical container scale parameter matrix; S2, using the historical container handling resource state parameter matrix set and the historical container scale parameter matrix to construct the final container handling resource state parameter moment mapping equation matrix; S3, setting the loading and unloading priority data of each current container to obtain the current initial container loading and unloading priority data set; S4, inputting the loading and unloading resource state parameters at the start time of each current loading and unloading stage and the size data of the corresponding container into the corresponding mapping equation in the final container loading and unloading resource state parameter mapping equation matrix through a loop, to obtain a mapping data set; Then, the current initial container loading and unloading priority data set is adjusted according to the number of resource status parameters that reach the corresponding resource status limit in the mapping data set to obtain the current final container loading and unloading priority data set.

2. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 1 is characterized in that: The S1 comprises the following steps: S11. Setting several types of terminal container loading and unloading resource state parameters to obtain a container loading and unloading resource state parameter type set; dividing the current container loading and unloading process into stages to obtain a current container loading and unloading stage set; and setting several types of container scale parameters to obtain a container scale parameter type set; S12. In conjunction with the container loading and unloading resource state parameter type set, the container scale parameter type set and the current container loading and unloading stage set, several groups of historical container loading and unloading resource state parameters and corresponding container scale parameters at the start and end times of each loading and unloading stage of container loading and unloading are collected at the same terminal to obtain a historical container loading and unloading resource state parameter matrix set and a historical container scale parameter matrix.

3. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 2 is characterized in that: The S2 comprises the following steps: S21, constructing an initial mapping equation of each container loading and unloading resource state parameter corresponding to the end time of each container loading and unloading stage in conjunction with the container loading and unloading resource state parameter type set, the current container loading and unloading stage set, and the container scale parameter type set, to obtain an initial container loading and unloading resource state parameter mapping equation matrix; S22. Use the historical container loading and unloading resource state parameter matrix set and the historical container scale parameter matrix to adjust each initial container loading and unloading resource state parameter moment mapping equation in the initial container loading and unloading resource state parameter moment mapping equation matrix to obtain the final container loading and unloading resource state parameter moment mapping equation matrix.

4. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 3 is characterized in that: The S22 comprises the following steps: S221, respectively substitute the data of the start time of each stage of the historical container loading and unloading resource state parameter matrix set and the data in the historical container scale parameter matrix into the corresponding initial container loading and unloading resource state parameter moment mapping equation in the initial container loading and unloading resource state parameter moment mapping equation matrix for mapping, and obtain the historical moment container loading and unloading resource state parameter matrix set; S222, setting a moment-by-moment container loading and unloading resource state parameter mapping error threshold and adjusting the moment-by-moment container loading and unloading resource state parameter mapping equation to be adjusted by calculating the error data between the historical moment-by-moment container loading and unloading resource state parameter matrix set and the historical container loading and unloading resource state parameter matrix set.

5. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 4 is characterized in that: The S3 comprises the following steps: S31, taking the first current container loading and unloading stage in the current container loading and unloading stage set as the current container loading and unloading stage to be adjusted; setting a number of containers that currently need to be loaded and unloaded to obtain a current container set; S32. Set the loading and unloading priority data of each container in the current container set to obtain a current initial container loading and unloading priority data set; set the value limits corresponding to each type of container loading and unloading resource state parameter to obtain a container loading and unloading resource state parameter limit value set; and use the container with the highest priority as the current container to be loaded and unloaded in conjunction with the current initial container loading and unloading priority data set.

6. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 5 is characterized in that: The S4 comprises the following steps: S41, acquiring various types of loading and unloading resource state parameters at the start time of the current loading and unloading phase to be adjusted in conjunction with the container loading and unloading resource state parameter type set and the container scale parameter type set, to obtain the container loading and unloading resource state parameter set at the current start time; and then collecting the scale parameter of each container in the current container set to obtain the current container scale parameter matrix; S42, inputting the scale parameter corresponding to the current container to be loaded and unloaded in the current container scale parameter matrix and each state parameter in the container loading and unloading resource state parameter set at the current start time into the corresponding mapping equation in the final container loading and unloading resource state parameter mapping equation matrix for mapping, to obtain the container loading and unloading resource state parameter set at the current end time; When there is a resource status parameter in the container loading and unloading resource status parameter set at the current end time that is identical to the resource status parameter limit value corresponding to the container loading and unloading resource status parameter limit value set, the priority data corresponding to the container that has not started loading and unloading or has not completed loading and unloading in the current initial container loading and unloading priority data set is adjusted until there is no resource status parameter in the container loading and unloading resource status parameter set at the current end time that is identical to the resource status parameter limit value corresponding to the container loading and unloading resource status parameter limit value set; otherwise, there is no need to adjust the current initial container loading and unloading priority data set; after the adjustment is completed, the next loading and unloading stage of the current loading and unloading stage to be adjusted is used as the current loading and unloading stage to be adjusted, and the container loading and unloading resource status parameter set at the current end time is used to replace the container loading and unloading resource status parameter set at the current start time, and S41 and S42 are repeated until the current loading and unloading stage to be adjusted is the last loading and unloading stage in the current container loading and unloading stage set; S43. When the loading and unloading of the current container to be loaded and unloaded is completed, the current container corresponding to the priority data next to the current container to be loaded and unloaded in the current initial container loading and unloading priority data set is used as the current container to be loaded and unloaded, and S41, S42 and S43 are repeated until all containers in the current container set are loaded and unloaded. The current adjusted container loading and unloading priority data set obtained after adjusting the priority data in the loading and unloading process of the last current container in the current container set is used as the current final container loading and unloading priority data set.

7. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 6 is characterized by: In S41, the BP neural network model is used to obtain the various types of loading and unloading resource status parameters at the start time of the current container loading and unloading phase to be adjusted.

8. The method for scheduling container terminal loading and unloading resources based on artificial intelligence according to claim 7 is characterized in that: In S42, the priority data corresponding to the containers that have not started loading or unloading or have not completed loading or unloading in the current initial container loading and unloading priority data set is adjusted, including the following steps: S421, setting the value intervals of each priority data corresponding to the containers that have not started loading or unloading or have not completed loading and unloading in the current initial container loading and unloading priority data set to obtain the current priority data value interval set; constructing a Harris Hawk population for loading and unloading priority adjustment; setting the maximum number of iterations of the Harris Hawk population for loading and unloading priority adjustment to And the current number of iterations is , are recorded as the maximum number of iterations of loading and unloading adjustment and the current number of iterations of loading and unloading adjustment respectively; S422, setting the loading and unloading priority according to the current priority data value interval set to adjust the initial position of each Harris hawk in the Harris hawk population to obtain a second initial position matrix; S423, constructing a fitness function for adjusting the Harris hawk population for the loading and unloading priority; S424, start iteration; in each round of iteration, use the fitness function of the Harris hawk population adjusted by the loading and unloading priority to calculate the fitness value of the position of each Harris hawk in the Harris hawk population adjusted by the loading and unloading priority obtained in the previous round of iteration, and update the position of each Harris hawk in the Harris hawk population adjusted by the loading and unloading priority obtained in the previous round of iteration; S425, when When , stop the iteration and get the second final global best fitness and the second final global best position; otherwise, continue to iterate until until the first final global optimal fitness is used as the number of loading and unloading limits reached after optimization. When the number of loading and unloading limits reached after optimization is 0, the adjustment is completed, and the second final global optimal position is used as the current adjusted container loading and unloading priority data set; otherwise, return to S424 to continue iterating until the number of loading and unloading limits reached after optimization is 0.

9. A system for implementing the method for scheduling container terminal loading and unloading resources based on artificial intelligence as described in any one of claims 1 to 8.

Images