A site selection method, apparatus, device, medium and product

Abstract

The application discloses a site selection method and device, equipment, medium and product, and relates to the technical field of data processing. The site selection method comprises the following steps: acquiring grain flow stream data; determining a feasible time for each transportation node that meets a first constraint condition according to the grain flow stream data, wherein the first constraint condition indicates that the grain can be unloaded at the transportation node and the ship can safely sail on the waterway; establishing a multi-objective integer programming model, wherein an objective function of the model is used to realize the dual objectives of minimizing the time-related grain loss risk and the task overdue cost, and a second constraint condition of the model comprises a storage transportation channel feasibility constraint condition based on the transportation node and the grain storage institution and a grain unloading operation feasibility constraint condition based on the grain flow task requirement and the feasible time; generating a candidate site selection scheme according to the second constraint condition; and solving the multi-objective integer programming model based on the candidate site selection scheme to obtain a site selection scheme that minimizes the objective function value under the condition of meeting the second constraint condition. The application can balance the feasibility and economy of grain transportation.

Description

Technical Field

[0001] This application relates to the field of data processing technology, and in particular to a site selection method, apparatus, equipment, medium and product. Background Technology

[0002] In the past, the focus of grain issues was mainly on how to increase grain production at the source. With the significant increase in grain production, the grain issue has gradually shifted to how to improve the level of grain circulation in the transportation process. In this regard, adopting a reasonable grain transportation site selection plan can effectively avoid grain loss, reduce logistics costs, and thus improve the economic and social benefits of grain logistics.

[0003] Traditional grain transportation site selection technology typically determines transportation nodes at the grain flow (grain logistics) level based on the objectives of minimizing transportation costs or minimizing time, using models such as integer programming and heuristic algorithms, combined with the demand distribution of grain transportation tasks.

[0004] However, traditional grain transportation site selection techniques do not consider the impact of transportation conditions and their dynamic changes on grain transportation, which can lead to situations where selected transportation nodes cannot operate within the required timeframe due to unmet transportation conditions. Furthermore, traditional grain transportation site selection techniques only consider optimizing transportation costs or time, which can result in the following: sacrificing time efficiency to meet waterway navigation conditions leads to transportation delays and increased grain losses; excessively compressing transportation time can increase grain losses; and excessively long waiting times can cause a surge in related costs (such as ship demurrage fees). For these reasons, traditional grain transportation site selection techniques cannot balance the safety, efficiency, and cost of grain transportation, ultimately leading to an imbalance between the feasibility and economic viability of grain transportation solutions. Summary of the Invention

[0005] This application provides a site selection method, apparatus, equipment, medium, and product to address or at least partially address the defects or deficiencies in related technologies.

[0006] Firstly, this application provides a site selection method, the site selection method comprising: Acquire grain flow data and water flow data; grain flow data includes task requirement data for grain transportation tasks in the preset grain transportation task set, and water flow data includes channel depth data and ship draft data. Based on the grain flow data and the water flow data, for each transport node in the preset transport node set, a feasible time that satisfies the first constraint condition is determined within the preset time set; the first constraint condition indicates that there is sufficient time to complete the grain transshipment operation at the transport node and that the ship can safely navigate the waterway, and the ship belongs to the preset ship set. A multi-objective integer programming model is established, including an objective function and a second constraint. The objective function is used to achieve the dual objectives of minimizing time-related grain loss risk and minimizing task overdue costs. The second constraint includes feasibility constraints on grain transportation channels based on the transportation nodes and grain storage institutions, and feasibility constraints on grain transshipment operations based on the task requirement data and the feasible time. The grain storage institutions belong to a pre-set set of grain storage institutions. Candidate site selection schemes are generated based on the second constraint; the candidate site selection schemes include the transportation node, the grain storage facility, the grain transshipment operation time window of the grain transportation task at the transportation node, and the handling time cost of the grain transportation task from transshipment at the transportation node to the grain storage facility; Based on the candidate location schemes, the multi-objective integer programming model is solved to obtain the target location scheme that minimizes the function value of the objective function while satisfying the second constraint condition.

[0007] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes the type of grain; The objective function is: ; in, This indicates the time-related risk of food loss. This represents the overdue cost of the task; Let S represent the objective function, I represent the preset set of transportation nodes, J represent the preset set of grain transportation tasks, and K represent the preset set of grain storage institutions. Represents binary decision variables. Setting it to 1 indicates the decision of grain transportation task i to transfer grain from transportation node s to grain storage facility j. Setting it to 0 indicates that the grain transportation task i does not transfer grain from transportation node s to grain storage facility j. This indicates the type of grain being transferred from transport node s. The grain loss rate caused by the time spent transshipping grain during the process of transporting grain to grain storage facilities. This represents the predicted grain transshipment operation time for grain transportation task i at transportation node s. This represents the daily rental rate for vessel k. This represents the demurrage rate for vessel k. This represents the predicted demurrage time for ship k.

[0008] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes the amount of grain transported and the type of grain. The time cost of transporting grain from the transport node to the grain storage facility is determined by the following formula: ; in, This represents the time cost of transporting grain from transport node s (where the grain is transferred) to grain storage facility j for grain transport task i. This represents the length of the transfer path from transport node s to grain storage facility j. This indicates the transport speed of the grain transshipment equipment. This represents the amount of grain transported for grain transport task i. This represents the efficiency coefficient of the grain transfer equipment. Indicates the type of grain for grain transportation task i. Physical property correction factor , and This represents the weighting coefficient.

[0009] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes a task time window; the channel depth data includes the estimated channel depth and the minimum safe passage depth limit; and the ship draft data includes the estimated ship draft and the maximum permissible draft limit. The first set of constraints includes the mission time window constraint, the channel depth constraint, the ship draft constraint, and the ship safe berthing constraint. The task time window constraint includes the requirement that the grain transshipment operation at the transportation node, starting from time t, can be completed within the task time window of the grain transportation task. The channel depth constraint condition includes that the estimated channel depth at time t is greater than or equal to the minimum safe passage depth limit of the channel. The ship draft constraint conditions include that the estimated ship draft at time t of the ship performing the grain transport mission is less than or equal to the maximum permissible draft limit of the ship. The constraints for safe berthing of the vessel include that the estimated channel depth at time t is greater than or equal to the estimated draft of the vessel at time t. Wherein, time t belongs to the preset time set.

[0010] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes the task time window, the amount of grain transported, and the type of grain. The feasibility constraints of the grain transport channel include: there is a practically feasible transport channel between the transport node and the grain storage facility; the capacity of the transport node is sufficient to handle the grain transport volume of the grain transport task; the transfer equipment of the transport node is operable and adaptable to the grain type of the grain transport task; and the handling time cost of the grain transport task from the transport node to the grain storage facility is less than the maximum allowable cost limit. The feasibility constraints of the grain transshipment operation include: the grain transportation task is within the task time window of the grain transshipment operation at the transportation node, and each moment of the grain transportation task within the grain transshipment operation time window at the transportation node is the feasible moment corresponding to the transportation node.

[0011] Optionally, in some embodiments of this application, generating candidate location schemes based on the second constraint includes: The first transportation node and the first grain storage institution that meet the feasibility constraints of the grain storage and transportation channel are fused and coded to obtain the first code; The first grain transshipment operation time window, which satisfies the feasibility constraints of the grain transshipment operation for the first transportation node and the first grain transportation task, and the transportation time cost of the first grain transportation task from the first transportation node to the first grain storage institution are fused and encoded to obtain the second code. The first code and the second code are fused to obtain a candidate addressing scheme.

[0012] Secondly, this application provides an addressing device, the addressing device comprising: The data acquisition module is configured to acquire grain flow data and water flow data. The grain flow data includes the task requirement data of grain transportation tasks in the preset grain transportation task set, and the water flow data includes channel water depth data and ship draft data. The timing determination module is configured to determine, based on the grain flow data and the water flow data, a feasible time within a preset time set for each transport node in a preset transport node set that satisfies a first constraint condition; the first constraint condition indicates that there is sufficient time to complete the grain transshipment operation at the transport node and that the vessel can navigate safely in the waterway, wherein the vessel belongs to a preset vessel set. The model building module is configured to build a multi-objective integer programming model including an objective function and a second constraint. The objective function is used to achieve the dual objectives of minimizing time-related grain loss risk and minimizing task overdue costs. The second constraint includes feasibility constraints on grain transportation channels based on the transportation nodes and grain storage institutions, and feasibility constraints on grain transshipment operations based on the task requirement data and the feasible time. The grain storage institutions belong to a pre-set set of grain storage institutions. The scheme generation module is configured to generate candidate site selection schemes based on the second constraint condition; the candidate site selection schemes include the transportation node, the grain storage institution, the grain transshipment operation time window of the grain transportation task at the transportation node, and the handling time cost of the grain transportation task from transshipment at the transportation node to the grain storage institution; The model solving module is configured to solve the multi-objective integer programming model based on the candidate location schemes, and obtain the target location scheme that minimizes the function value of the objective function while satisfying the second constraint condition.

[0013] Thirdly, this application provides a computer device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the addressing method described in the first aspect above.

[0014] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the addressing method described in the first aspect.

[0015] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the addressing method described in the first aspect.

[0016] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application provides a site selection method, apparatus, equipment, medium, and product. It employs multi-objective integer programming to achieve both minimizing time-related grain loss risk and minimizing task overdue costs, thus balancing efficiency and cost in grain transportation and achieving multi-objective optimization. A first constraint establishes a hard constraint requirement of "grain transshipment + navigation safety," thereby determining the feasible time for transportation nodes to "complete grain transshipment + ensure navigation safety." This ensures navigation safety as a fundamental aspect of grain transportation and forms one of the feasibility constraints for grain transshipment operations in the multi-objective integer programming model, preventing selected transportation nodes from being unable to operate within the task deadline due to substandard transportation conditions. A second constraint establishes feasibility constraints for grain storage and transportation channels and grain transshipment operations, enabling the selection of a site selection scheme that achieves multi-objective optimization from among feasible options when solving the multi-objective integer programming model. In this way, a balance is achieved in the safety (guaranteed by navigation safety-related constraints), efficiency (guaranteed by minimizing time-related grain loss risks and feasibility constraints for grain storage and transportation channels and grain transshipment operations), and cost (guaranteed by minimizing mission overdue costs) of grain transportation, so that the feasibility and economy of the grain transportation scheme based on the final location are balanced. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A schematic flowchart illustrating a location selection method provided in an embodiment of this application; Figure 2 A functional module diagram of an address selection device provided in an embodiment of this application; Figure 3 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0019] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] In one exemplary embodiment, such as Figure 1 As shown, a location selection method is provided. This method is executed by a computer device, specifically a terminal or server, either alone or jointly. The terminal can be, but is not limited to, various desktop computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. The server can be a standalone server, a server cluster consisting of multiple servers, or a cloud server.

[0022] First, some terms or concepts involved in the embodiments of this application will be introduced.

[0023] Grain logistics refers to the systematic logistics activities that involve multiple links such as transportation, storage, loading and unloading, handling, packaging, distribution processing, delivery, and information processing throughout the entire process of grain from the source of production to the end consumer. Its core is to ensure the quantity security, quality stability, and efficiency improvement of grain during the circulation process. It is a key link connecting agricultural production and market consumption.

[0024] Waterway transportation: a mode of transportation that uses ships to transport goods or passengers on natural or artificial waterways (such as oceans, rivers, lakes, canals, etc.). It has the characteristics of large carrying capacity, low cost and low energy consumption, and occupies an important position in the long-distance transportation of bulk commodities (such as grain, ore, coal, etc.). However, it is greatly affected by natural factors such as waterway conditions (water depth, width, etc.), tides, and weather.

[0025] Site selection optimization: Under certain constraints (such as geographical environment, cost budget, demand distribution, etc.), through mathematical modeling, algorithm calculation and other means, the optimal location of facilities (such as warehouses, docks, factories, etc.) is selected from multiple potential candidate locations to achieve specific goals (such as cost minimization, efficiency maximization, service coverage, etc.). It is widely used in logistics, industry, service industry and other fields.

[0026] Multi-objective optimization: For problems involving two or more conflicting objectives, the process of finding the optimal solution by establishing a mathematical model. Its core is to find a balance among multiple objectives (i.e., Pareto optimal solution) rather than the optimality of a single objective. It is commonly used in scenarios such as resource allocation, engineering design, and decision analysis, and requires comprehensive consideration of the weights and constraints of each objective.

[0027] Integer programming: A class of mathematical programming problems in which some or all of the decision variables are required to be integers. It is used to solve scenarios in which variables cannot be divided in real-world problems (such as the number of facilities, the number of tasks to be assigned, etc.). It is an important branch of operations research and is often combined with heuristic algorithms to solve complex large-scale problems.

[0028] In the embodiments of this application, such as Figure 1 As shown, the site selection method includes steps 101 to 105. Wherein: Step 101: Obtain grain flow data and water flow data; grain flow data includes task requirement data for grain transportation tasks in the preset grain transportation task set, and water flow data includes channel depth data and ship draft data.

[0029] In this step, grain flow data can be obtained from grain logistics and water flow data from waterway transportation.

[0030] The preset grain transportation task set I includes multiple grain transportation tasks, where grain transportation task i ∈ I. The task requirement data for grain transportation task i includes the task time window and the amount of grain to be transported. and types of grain The task time window refers to the time window from the start of the grain transport task i. and deadline The constructed time window [ ].

[0031] Channel depth data includes estimated channel depth. (Time-dependent, meaning the estimated channel depth will vary at different times) and minimum safe passage depth limits. , This refers to the estimated channel depth at time t. In one optional example, the channel depth is estimated. = Channel depth on nautical chart (obtained from nautical chart) + Tide height at time t in the tide table (obtained from the tide table) + Water depth correction value corresponding to the weather forecast at time t (this correction value is an empirical value).

[0032] Ship draft data includes the estimated ship draft Dk(t) (which is time-dependent, meaning the estimated ship draft will vary at different times) and the maximum permissible draft limit. Dk(t) represents the estimated draft of ship k at time t. In one alternative example, a draft model can be constructed for ship k based on the actual load, actual draft, and navigation conditions (such as weather and tides) collected for ship k. Then, the estimated draft Dk(t) can be determined using this draft model based on the load (i.e., the amount of grain transported) of ship k at time t and the weather forecast, tides, and other navigation conditions at time t.

[0033] Step 102: Based on the grain flow data and water flow data, determine the feasible time that satisfies the first constraint condition for each transport node in the preset transport node set within the preset time set; the first constraint condition indicates that there is sufficient time to complete the grain transshipment operation at the transport node and that the ship can safely navigate the waterway, and the ship belongs to the preset ship set.

[0034] The preset set of transportation nodes S includes multiple transportation nodes, where s∈S. The transportation nodes in the preset set of transportation nodes S are selectable grain logistics nodes, such as grain transshipment nodes.

[0035] The preset time set T includes multiple times, where time t∈T. Optionally, the times in the preset time set T can be selected according to a preset time period. For example, from the time interval [8:00, 12:00), one time is selected every hour to obtain the preset time set [t1=8:00, t2=9:00, t3=10:00, t4=11:00].

[0036] The predefined set of ships K includes multiple ships k, where ship k∈K.

[0037] Optionally, the first constraint includes the mission time window constraint, the channel depth constraint, the ship's draft constraint, and the ship's safe berthing constraint, wherein: The task time window constraints (related to the task time window in the grain flow data) include: the grain transshipment operation at transport node s starting from time t can be carried out within the task time window of grain transport task i. The task time window constraint means that if grain transshipment operations begin at transportation node s from time t, the time required for the grain transshipment operations is T. oad The start time of grain transshipment operations Let t be the end time. For t+T oad The start time of the grain transshipment operation and end time It must fall entirely within the task time window. Within, that is, it needs to meet ≤ < ≤ This ensures that there is sufficient time at transport node s within the task time window of food transport task i. The grain transshipment operation was completed within [time period].

[0038] Channel depth constraints (involving channel depth data in the flow data) include: the estimated channel depth at time t (t∈T). Greater than or equal to the minimum safe water depth limit for navigation in the channel It is a necessary waterway condition to ensure that ships can pass.

[0039] Ship draft constraints (involving ship draft data in the water flow data) include: the estimated ship draft Dk(t) of the ship performing the grain transport mission i at time t (t∈T) is less than or equal to the ship's maximum permissible draft limit. This is a necessary condition for ships to ensure that they can transport grain.

[0040] The constraints for safe berthing of ships (involving channel depth data and ship draft data from the water flow data) include: the estimated channel depth at time t (t∈T). A ship's estimated draft Dk(t) at time t (t∈T) is greater than or equal to the ship's estimated draft at time t (t∈T), which is a necessary condition to ensure that the ship can safely anchor in the waterway.

[0041] By integrating multi-dimensional constraints such as task time window, channel depth, ship draft, and safe berthing, the feasibility of grain transshipment operations at each candidate transport node at different times is quantified. This allows for the selection of times that simultaneously meet the above multi-dimensional constraints from a preset time set for each candidate transport node, forming feasible time data for each transport node. This provides an accurate spatiotemporal constraint foundation for the subsequent multi-objective integer programming model, ensuring that the multi-objective integer programming model is solved within the range that conforms to actual operating conditions. This avoids problems such as ship safety risks, grain transport delays, or operation interruptions caused by improper matching of transport node operation times from the source.

[0042] Among them, the time T required for grain transshipment operations oad It is a dynamically changing value, which is affected by factors such as the efficiency of transshipment equipment and the physical properties of grain. The time T required for grain transshipment operations is also a variable. oad It includes the following three parts: Grain transfer equipment start-up time: This refers to the time required for grain transfer equipment to reach normal operating status from startup. Grain unloading time: refers to the time spent unloading grain from a ship (unloading it to a certain transportation node); Grain storage preparation time: The time required for various preparatory work (such as cleaning and inspection at a transportation node) to prepare grain for storage in a grain storage facility. Optionally, the grain storage facility can be a silo.

[0043] In this step, feasible times that simultaneously satisfy the above-mentioned task time window constraints, channel depth constraints, ship draft constraints, and ship safe berthing constraints can be determined for transport node s within a preset time set T, and an operational time matrix M corresponding to transport node s can be generated. s,t Characterize it.

[0044] For example, the preset time set T is [t1=8:00, t2=9:00, t3=10:00, t4=11:00], for transport node s1: At time t1, the estimated channel depth is as follows. =5m≥Estimated ship draft Dk( ) = 4m, and =3m, Dk( ) =5m, and the time T required for grain transshipment operations to begin at transport node s1 from time t1. oad =2h, the grain transshipment operation can be completed within the task time window [8:00, 12:00] of grain transportation task i, and is marked as 1; At time t2, the estimated channel depth is as follows. =3.5m < estimated ship draft Dk ( )=4m, marked as 0; At time t3, the estimated channel depth is as follows. =4.2m≥Estimated ship draft Dk( ) = 4m, and =3m, Dk( ) =5m, and the time T required for grain transshipment operations to begin at transport node s1 from time t3. oad =2h, the grain transshipment operation can be completed within the task time window [8:00, 12:00] of grain transportation task i, and is marked as 1; At time t4, the time T required for the grain transshipment operation to begin at transport node s1 from time t4 is... oad =3h (i.e., T) oad (With fluctuations), the grain transshipment operation cannot be completed within the task time window [8:00, 12:00] of grain transportation task i, that is, the grain transshipment cannot be completed before 12:00, and is marked as 0.

[0045] At this point, we can obtain the workable time matrix Ms1,t=[1, 0, 1, 0] for transport node s. The dimension of the workable time matrix is ​​consistent with the dimension of the preset time set. s1,t =[1, 0, 1, 0] indicates that the feasible times for transport node s to satisfy the first constraint condition within the preset time set T are t1 and t3.

[0046] Step 103: Establish a multi-objective integer programming model including an objective function and a second constraint. The objective function is used to achieve the dual objectives of minimizing time-related grain loss risk and minimizing task overdue costs. The second constraint includes feasibility constraints on grain transportation channels based on transportation nodes and grain storage institutions, as well as feasibility constraints on grain transshipment operations based on task requirement data and feasible time. The grain storage institutions belong to the pre-set set of grain storage institutions.

[0047] In one alternative implementation, the objective function can be: ; in, Let S represent the objective function, I represent the preset set of transportation nodes, J represent the preset set of grain transportation tasks, J represent the preset set of grain storage institutions, J includes multiple grain storage institutions j, where j∈J, and K represent the preset set of ships. Represents binary decision variables. Setting it to 1 indicates the decision of grain transportation task i to transfer grain from transportation node s to grain storage facility j. Setting the value to 0 indicates the decision of grain transportation task i not to transfer grain from transportation node s to grain storage facility j. In the subsequent solution of the multi-objective integer programming model, the corresponding value for each set of (s, i, j) can be determined. Is it more beneficial to optimize the objective function to choose 1 or to choose 0, thus determining the optimal combination of (s, i, j) for the objective function? This indicates the type of grain being transferred from transport node s. The grain loss rate caused by the time spent transshipping grain during the process of transporting grain to grain storage facilities. This represents the predicted grain transshipment operation time for grain transportation task i at transportation node s. This represents the daily rental rate for vessel k. This represents the demurrage rate for vessel k. This represents the predicted demurrage time for ship k.

[0048] In one optional example, and It can be obtained through simulation testing or fitting historical data. It can be the difference between the waiting time of ship k after arriving at transportation node s and the allowable waiting time agreed upon in the grain transportation contract / order. The waiting time of ship k after arriving at transportation node s can be obtained through simulation testing or fitting of historical data.

[0049] In the above objective function, This indicates the time-related risk of food loss, among which, That is, “grain loss rate × time”, which represents the risk of grain loss due to extended operation time during transshipment and storage; This represents the cost of task overdue, where, Demurrage costs are the economic costs incurred by a vessel due to waiting time exceeding the agreed timeframe for a grain transport mission.

[0050] Solving the above objective function yields results that simultaneously satisfy the dual objectives of minimizing time-related food loss risk and minimizing task overdue costs. Specifically, the values ​​of s, i, j, and k that can simultaneously minimize both time-related food loss risk and task overdue costs are obtained.

[0051] In the multi-objective integer programming model, the objective function defines a dual objective: minimizing the time-related risk of food loss and minimizing the cost of task overdue, thus achieving multi-objective planning. In this model, the values ​​of s, i, j, and k are limited to integers based on their meanings, thereby achieving integer programming.

[0052] The second constraint is used to limit the domain of variables or the relationship between variables in the objective function, so that when solving a multi-objective integer programming model, the solution that minimizes the objective function can be found among the feasible schemes that satisfy the second constraint. The second constraint will be described in detail below.

[0053] Optionally, the feasibility constraints of the grain transport corridor in the second constraint include: the existence of a practically feasible transport corridor between the transport node and the grain storage facility; the capacity of the transport node to handle the grain transport volume of the task; the transshipment equipment at the transport node being operational and suitable for the types of grain transported; and the time cost of transporting grain from the transport node to the grain storage facility being less than the maximum permissible cost limit. The maximum permissible cost limit can be a preset value based on experience or statistics regarding transport time.

[0054] For example, assuming there is a feasible transportation channel between transportation node s1 and grain storage institution j2, when s in the objective function takes the value s1, the range of j includes j2, that is, there is a combination of s1-j2; assuming there is no feasible transportation channel between transportation node s1 and grain storage institution j2, when s in the objective function takes the value s1, the range of j does not include j2, that is, there is no combination of s1-j2.

[0055] For example, assuming that the capacity of transportation node s2 can handle the amount of grain transported in the grain transport task, then the range of values ​​for s in the objective function includes s2; assuming that the capacity of transportation node s2 cannot handle the amount of grain transported in the grain transport task, then the range of values ​​for s in the objective function does not include s2.

[0056] For example, assuming that the transshipment equipment of transport node s3 is currently operational and compatible with the grain type of grain transport task i2, then when i in the objective function takes the value i2, the range of values ​​for s includes s3, that is, there exists an i2-s3 combination; assuming that the transshipment equipment of transport node s3 is currently inoperable or not compatible with the grain type of grain transport task i2, then when i in the objective function takes the value i2, the range of values ​​for s does not include s3, that is, there is no i2-s3 combination.

[0057] For example, suppose the time cost of transporting grain in task i from transport node s4 to grain storage facility j3 is... Less than the maximum allowable cost limit Then, when s in the objective function takes the value s4, the range of j includes j3, meaning there exists a combination of s4-j3; assuming the time cost of transporting grain task i from transport node s4 to grain storage facility j3... Greater than or equal to the maximum allowable cost limit Therefore, when s in the objective function takes the value s4, the range of j does not include j3, meaning there is no combination s4-j3. The method for determining the handling time cost of grain transportation from a certain transportation node to a certain grain storage facility will be described in detail later.

[0058] Optionally, the feasibility constraint for grain transshipment operations in the second constraint includes: the grain transshipment operation time window of the grain transportation task at the transportation node is within the task time window, and each moment within the grain transshipment operation time window of the grain transportation task at the transportation node is a feasible moment corresponding to that transportation node. Specifically, the grain transshipment operation time window of the grain transportation task at the transportation node is a time period within the task time window of the grain transportation task that satisfies all of the following conditions: each included moment satisfies the feasible moment corresponding to that transportation node, and is greater than or equal to the time T required for the grain transshipment operation at that transportation node. oad Continuous and uninterrupted.

[0059] For example, suppose that the grain transportation task i3 is within the task time window of the grain transshipment operation at transportation node s5. Within the range of ], when i takes the value i3 in the objective function, the range of s includes s5, meaning there exists an i3-s5 combination; assuming that the grain transportation task i3 is not within the grain transshipment operation time window of transportation node s5, then... If the value of i in the objective function is i3, then the range of values ​​of s does not include s5, meaning there is no i3-s5 combination.

[0060] For example, assuming that each moment in the grain transshipment operation time window of grain transportation task i4 is a feasible moment corresponding to transportation node s6, then when i in the objective function takes the value i4, the range of values ​​of s includes s6, that is, there exists an i4-s6 combination; assuming that one or more moments in the grain transshipment operation time window of grain transportation task i4 are not feasible moments corresponding to transportation node s6, then when i in the objective function takes the value i4, the range of values ​​of s does not include s6, that is, there is no i4-s6 combination.

[0061] Multi-objective integer programming models minimize Under the premise of meeting the various spatiotemporal constraints of the grain flow-water flow dual network (such as feasible time, task time window, transportation time cost, etc.), it can balance the two objectives of "reducing grain loss" and "reducing the economic cost of ship demurrage", and avoid unreasonable site selection schemes caused by excessive pursuit of one objective, such as simply compressing time leading to equipment overload and grain loss, or excessively extending waiting time leading to a surge in demurrage fees. Ultimately, it outputs a site selection scheme that takes into account both efficiency and cost.

[0062] The following section introduces the optional methods for determining the "time cost of transporting grain from a certain transportation node to a certain grain storage facility" mentioned earlier.

[0063] In this embodiment of the application, the handling time cost between the grain transshipment equipment at the wharf and the grain storage facility is defined as a decision variable. It is used to quantify the internal handling time consumption caused by the length of the transshipment path, the efficiency of the transshipment equipment, and the differences in the layout of the grain storage facility during the process of grain being transferred from the ship to the grain storage facility. This handling time cost is dynamically generated by analyzing the technical parameters of the transshipment equipment, the spatial distribution of the grain storage facility, and the physical characteristics of the grain.

[0064] First, a physical model of the internal handling path can be established based on the length, inclination angle, transport speed of the grain transshipment equipment (such as transshipment belt conveyors) at the wharf front and the spatial layout of the grain storage facilities. Then, combined with the physical characteristics of the grain and the efficiency parameters of the transshipment equipment, the handling time cost of each potential transshipment path can be quantified. The formula for calculating the handling time cost can be obtained by simulation testing or fitting historical operation data based on the physical model, and can be used to optimize the constraints and trade-offs of the internal handling links in the objective function.

[0065] Alternatively, the time cost of transporting grain from a certain transportation node to a certain grain storage facility can be determined by the following formula: ; in, This represents the time cost of transporting grain from transport node s (where the grain is transferred) to grain storage facility j for grain transport task i. This represents the length of the transfer path from transport node s to grain storage facility j. This indicates the transport speed of grain transfer equipment (such as transfer belt conveyors). This represents the amount of grain transported for grain transport task i. This represents the efficiency coefficient of grain transfer equipment. Indicates the type of grain for grain transportation task i. Physical property correction factor , and This represents the weighting coefficient.

[0066] In one optional example, It can be determined through on-site surveying; This can be determined by obtaining the technical parameters of the grain transfer equipment; This can be obtained through simulation testing or fitting historical data; The physical property correction coefficient can be obtained through simulation testing or fitting historical data. For example, among common grain types, the physical property correction coefficient for wheat can be 0.85, for corn it can be 0.92, for rice it can be 0.78, and for soybeans it can be 0.95. , and It can be obtained by simulation testing or fitting historical data based on the specific spatial layout of transportation nodes and grain storage institutions, the specific technical parameters of grain transfer equipment, the specific grain types and the specific grain transportation volume.

[0067] Among them, physical property correction coefficient The significance is to adapt to the differences in handling different grains, reflecting the impact of the physical properties of grains on internal handling costs and time, and the value can be between 0 and 1.

[0068] By quantifying the time consumption of grain transfer equipment at the wharf and grain storage facilities, factors that were originally difficult to incorporate directly into the objective function, such as transfer path length, equipment efficiency, silo layout differences, and grain physical characteristics, are transformed into calculable decision variables and used as one of the constraints of the objective function. This more accurately reflects the actual time cost of grain from ship to storage facility, providing a more comprehensive basis for constraints and trade-offs for multi-objective integer programming models. It enhances the optimization capability of multi-objective integer programming models for internal handling links, ensuring that the final site selection scheme can reasonably control the time cost of internal handling links while taking into account time-related grain loss risks and task overdue costs.

[0069] Step 104: Generate candidate site selection schemes based on the second constraint. The candidate site selection schemes include transportation nodes, grain storage facilities, the time window for grain transshipment operations at transportation nodes, and the time cost for transporting grain from transportation nodes to grain storage facilities.

[0070] In this embodiment of the application, candidate location schemes can be generated based on the second constraint in the following ways: The first transportation node and the first grain storage institution that meet the feasibility constraints of the grain storage and transportation channel are fused and coded to obtain the first code; The first grain transshipment operation time window and the handling time cost of the first grain transport task from the first transport node to the first grain storage facility are fused together to obtain the second code, which satisfies the feasibility constraints of the grain transshipment operation for the first transport node and the first grain transport task (i.e., any grain transport task in the preset set of grain transport tasks). The first and second codes are combined to obtain candidate location schemes.

[0071] The above method uses a two-layer coding design to achieve a comprehensive quantitative description of feasible site selection schemes. The first layer of coding represents the matching path between transportation nodes and grain storage institutions, while the second layer of coding represents the decision variables of grain transshipment operation time window and handling time cost.

[0072] The first layer of encoding uses an integer combination encoding form, such as "s2-j5", where s2 represents the second transportation node in the preset transportation node set S, and j5 represents the fifth grain storage facility in the preset grain storage facility set J. In the first encoding "s2-j5": the path between transportation node s2 and grain storage facility j5 needs to be a practically feasible transportation channel; the capacity of transportation node s2 needs to be able to handle the grain transport volume of grain transport task i3; the transfer equipment of transportation node s2 needs to be operable and adaptable to the grain type of grain transport task i3; and the time cost of transporting grain from transportation node s2 to grain storage facility j5 for grain transport task i3 is also considered. It needs to be less than the maximum allowable cost limit. If the path between transport node s2 and grain storage facility j5 is actually infeasible, or the capacity of transport node s2 cannot handle the grain transport volume of any single grain transport task, or the transshipment equipment of transport node s2 is inoperable or unsuitable for the grain type of any single grain transport task, or the time cost of transporting grain from transport node s2 to grain storage facility j5 for all grain transport tasks is too high. Greater than or equal to the maximum allowable cost limit (i.e., the transportation time and cost are too high due to the excessively long path), then the code "s2-j5" is considered an invalid code.

[0073] The second layer of encoding uses a "time interval + real number" encoding format, for example, "[t8,t 12 [-0.75], for the aforementioned grain transportation task i3 and transportation node s2, [t8,t 12 [ ] can represent the grain transshipment operation time window of grain transportation task i3 at transportation node s2, where the objective function is the predicted grain transshipment operation time. It must satisfy the condition that it does not exceed the time window for the grain transshipment operation. 0.75 can represent the handling time cost of grain transportation task i3 from grain transshipment at transportation node s2 to grain storage facility j5. In the second encoding "[t8,t 12 In ]-0.75”, [t8,t 12 It must fall strictly within the time window of the grain transportation task i3, and [t8,t] 12 Each time point in the equation must be a feasible time point corresponding to transport node s2 (i.e., the channel water depth, ship draft, and other channel and ship conditions meet the requirements), and the handling time cost of 0.75 must be greater than the maximum permissible cost limit. Otherwise, encode "s2-j5-[t8,t 12 "-0.75" is invalid.

[0074] The two-layer coding system integrates "transportation node - grain storage facility" with "grain transshipment operation time window - handling time cost" to form a complete site selection decision unit, such as "s2-j5-[t8,t". 12 The code "-0.75" indicates the selection of the transportation channel between transportation node s2 and grain storage facility j5. A certain grain transportation task i (e.g., grain transportation task i3, grain transportation task i4, etc.) is located at transportation node s2 from t8 to t9. 12 The grain transshipment operation can be completed within the specified time window, and the handling time cost of this transportation channel is 0.75. This coding method not only ensures that the location decision unit corresponds to the constraints (such as feasible time, handling time cost, task time window, etc.), but also provides a more accurate search dimension for solving the multi-objective integer programming model, enabling the solution process to accurately focus on the feasible solution space.

[0075] Step 105: Solve the multi-objective integer programming model based on the candidate location schemes to obtain the target location scheme that minimizes the function value of the objective function while satisfying the second constraint.

[0076] In an optional embodiment, the multi-objective integer programming model in this application can be solved by any algorithm for solving multi-objective integer programming models, such as genetic algorithm, simulated annealing algorithm or particle swarm optimization algorithm, to obtain a Pareto optimal solution set. The Pareto optimal solution set includes all location schemes that minimize the function value of the objective function while satisfying the second constraint condition. Then, the target location scheme is selected from the Pareto optimal solution set according to the decision-maker's preference weight for cost and time.

[0077] For example, taking the NSGA-II (Non-dominated Sorting Genetic Algorithm II) genetic algorithm to solve for the Pareto optimal solution set, the solution process is as follows: 1. Initialize the population: The N candidate site selection schemes are used as N initial solutions to obtain an initialized population. The initialized population provides "seeds" for the subsequent evolutionary process.

[0078] 2. Fuzzy fitness calculation: For each initial solution, substitute the corresponding time-related portion of the grain loss risk into the objective function. And the portion of the objective function corresponding to the task's overdue cost. .Will and Mapped to fuzzy satisfaction and Optionally, the mapping method can be a membership function, which can then be used to obtain the comprehensive fuzzy fitness. + Fuzzy fitness can more flexibly express the trade-offs between objectives, avoiding the bias caused by hard thresholds.

[0079] 3. Non-dominated sorting and crowding calculation: Non-dominated sorting: The N initial solutions in the population are non-dominated based on the comprehensive fuzzy fitness, dividing the N initial solutions into different levels (solutions on the Pareto front are in the first level, containing all non-dominated solutions, the second best is in the second level, and so on). Solutions with higher dominance levels have higher comprehensive fuzzy fitness. In this way, the optimal solution set (i.e., all solutions on the Pareto front) can be quickly identified, providing a basis for subsequent selection.

[0080] Crowding degree calculation: Calculate the crowding degree of each initial solution. Optionally, the crowding degree of initial solution i = (the comprehensive fuzzy fitness value of initial solution i - the average comprehensive fuzzy fitness of N initial solutions) / the standard deviation of the comprehensive fuzzy fitness of N initial solutions.

[0081] 4. Selection, crossover, and mutation: Selection Operation: Select parent individuals from N initial solutions using a tournament selection method. Simultaneously, apply an elite strategy to directly retain non-dominated solutions from the current population into the next generation population. That is, the next generation population includes individuals obtained from the current population through selection, crossover, and mutation operations, as well as non-dominated individuals from the current population.

[0082] Crossover operation: The individuals selected through the selection operation are subjected to a crossover operation to obtain offspring individuals. Optionally, in the crossover operation, a single-point crossover operator is used for the first level of encoding of the offspring individuals, and an arithmetic crossover operator is used for the second level of encoding of the offspring individuals.

[0083] Mutation operation: Randomly change the encoding value of the offspring individual to obtain a new offspring individual, but it is necessary to ensure that the new offspring individual satisfies the second constraint condition.

[0084] By employing selection, crossover, and mutation operations, we can simulate natural evolution and gradually approach the Pareto front while maintaining the diversity of solutions.

[0085] 5. Dynamic weight adjustment: During evolution, the weights of each objective are dynamically adjusted based on the population distribution (e.g., increasing the weight of sparse objectives when solutions are unevenly distributed). Optionally, for example, if the population is in... If the convergence is too rapid, it will increase. The weights are adjusted to promote diversity. This helps prevent the algorithm from converging prematurely, maintains the diversity of solutions, and covers a wider optimization space.

[0086] 6. Iterative optimization: Repeat steps 2-5 above until the termination condition is met (e.g., reaching the maximum number of iterations or the solution set converges). Through multiple rounds of evolution, the Pareto optimal solution set is obtained.

[0087] 7. Output Results: Output all non-dominated solutions on the Pareto front that satisfy the termination condition, for the decision-maker to choose from.

[0088] Alternatively, in another optional example, the simulated annealing algorithm can be used to solve for the Pareto optimal solution set. The specific solution process can be found in relevant technical documents and will not be elaborated here. Specifically, regarding the cooling strategy in the simulated annealing algorithm, the temperature... according to Update, including Adaptive adjustment.

[0089] Alternatively, in another optional example, the particle swarm optimization algorithm can be used to solve for the Pareto optimal solution set. The specific solution process can be found in relevant technical documents and will not be elaborated here. Regarding the update rule in the particle swarm optimization algorithm, M can be considered when updating the particle position. s,t and With constraints, speed updates can introduce a global optimum for non-dominated sorting selection.

[0090] Optionally, in the embodiments of this application, dynamic adjustment and verification of the site selection scheme based on water flow and grain flow data can be realized: based on real-time monitoring of channel depth changes (i.e., the deviation between real-time channel depth and estimated channel depth). ), fluctuations in grain transportation demand (i.e., fluctuations in the amount of grain transported for grain transportation task i) ) and ship draft adjustment (i.e., the deviation between the actual ship draft and the estimated ship draft of ship k) Based on changes in actual cargo load or navigation status, the operable time matrix of transportation nodes and the handling time cost from transportation nodes to grain storage facilities are dynamically updated. The multi-objective integer programming model is then re-run to generate an adjusted site selection scheme. Optionally, the multi-objective integer programming model can only solve locally for transportation nodes and various time windows affected by changes in water flow and grain flow data to reduce computational costs. Furthermore, the effectiveness of the site selection scheme in practical applications regarding grain loss risk, task overdue costs, and multi-objective balance can be evaluated through simulation testing or historical data backtesting, thereby determining the robustness and adaptability of the site selection scheme. Simulation testing can be used to evaluate the stability and applicability of the model's output site selection scheme in multi-objective balance by simulating different tidal scenarios (such as spring tides and neap tides, affecting channel depth) and fluctuations in grain demand (such as seasonal peaks and sudden orders).

[0091] The exemplary embodiments of this application can simultaneously collect basic data from two major networks: grain flow and water flow. The grain flow data covers the spatiotemporal distribution information of grain transportation tasks, such as task time windows, grain transportation volume, and grain types. The water flow data includes waterway transportation conditions such as channel depth and ship draft. By integrating these data, basic data of the two networks are formed, providing a comprehensive foundation for subsequent analysis.

[0092] The exemplary embodiments of this application can predict each moment. Channel depth By comparing the estimated channel depth Compared with the estimated ship draft ,when ≥ At that time, it is determined that the vessel can safely anchor in the waterway. This is the basic physical constraint for determining the feasibility of the operation and is directly related to the compatibility between the waterway and the vessel.

[0093] Based on the premise that the ship can safely berth, the exemplary embodiments of this application can be combined with the time required for grain transshipment operations. Filtering that simultaneously satisfies " ≥ "and" The time period that can be completed within the task time window ensures that the operation meets safety requirements in terms of time and does not exceed the time range agreed upon in the task, thus achieving a precise match between time and space constraints.

[0094] The exemplary embodiments of this application achieve a balance of multiple objectives by simultaneously minimizing "time-related food loss risk" and "task overdue costs." Among these, the food loss rate... (Related to grain type, equipment efficiency, etc.) and operating time The product of these factors quantifies the time-related risk of food loss; daily ship rental rates. Late fees With lag time The product of these factors quantifies the economic cost of the lag period. Decision variables. (The matching relationship between the task, transportation node, and grain storage institution) associates the two types of objectives, ensuring that the multi-objective integer programming model does not favor a single objective during the solution process.

[0095] In the exemplary embodiments of this application, the constraints of the multi-objective integer programming model are closely related to the objective function through function parameters. For example, the feasible time constraint limits the effective operation time range and affects... and The value of ; the constraint on transportation time cost is indirectly related to the impact on operational efficiency. and Task time window constraints define the time frame from the perspective of task requirements. The feasible interval is determined. These constraints interact with the parameters in the objective function to ensure that the optimization results not only conform to the actual operating conditions but also achieve a balance between the two objectives.

[0096] In an exemplary embodiment of this application, a formula for calculating handling time cost is constructed by integrating the transfer path length, transfer equipment transport speed, transport volume demand, equipment efficiency coefficient, grain physical property correction coefficient, and multiple weighting coefficients. Specifically, the ratio of transfer path length to transfer equipment transport speed reflects the impact of the transfer path on time; the ratio of transport volume demand to equipment efficiency coefficient reflects the effect of transfer equipment load on cost; the grain physical property correction coefficient adapts to the handling differences of different grains; and multiple weighting coefficients are used to balance the influence of each factor, achieving accurate quantification of internal handling costs and time.

[0097] In the exemplary embodiments of this application, the transportation time cost is incorporated as a decision variable into the constraints of a multi-objective integer programming model, working in conjunction with other parameters. For example, the value of the transportation time cost is directly related to the predicted grain transshipment operation time. (Affecting time-related food loss risk), and indirectly affecting the predicted ship demurrage time by reflecting internal handling efficiency. (Associated task overdue cost) enables the multi-objective integer programming model to take into account the time cost of internal transportation links during the solution process, thereby improving the comprehensiveness of the site selection scheme.

[0098] This application constructs an analytical framework that couples grain flow and water flow into a dual-network system. From the data acquisition stage, it achieves a comprehensive integration of the spatiotemporal distribution of grain transportation tasks with waterway transportation conditions. This dual-network collaborative approach accurately captures the spatiotemporal correlation between the two. For example, by dynamically matching the time window constraints of grain transportation with water flow data such as channel depth and ship draft, the feasible time generated for each transportation node considers both the rigid time requirements of grain transportation tasks and the safety constraints of ship navigation. This avoids the problem of insufficient feasibility of site selection schemes caused by neglecting the dynamic characteristics of waterways in traditional single-network analysis, thus improving the scientific nature and adaptability of site selection decisions from the outset.

[0099] The construction of a multi-objective integer programming model and the introduction of "transportation time cost" enable refined optimization of complex operational scenarios. The model focuses on minimizing "time-related food loss risk" and "task overdue cost," organically linking these two factors through decision variables. Simultaneously, "transportation time cost" quantifies the impact of internal processes such as transfer routes and equipment efficiency, incorporating previously difficult-to-quantify implicit time costs into the optimization system. This multi-dimensional optimization logic avoids the potential for compromises that can occur in single-objective optimization. For example, it avoids increasing food loss due to excessive time compression or causing a surge in ship demurrage fees due to blind waiting. The final solution achieves a dynamic balance between efficiency and cost.

[0100] The solution algorithm for multi-objective integer programming models and the dynamic adjustment mechanism based on fluctuation data further enhance the practicality and robustness of the proposed solution. The dual-layer coding design accurately maps core decision-making elements such as the matching paths between transportation nodes and storage facilities, and the time windows for grain transshipment operations. Combined with improvements such as fuzzy fitness functions and optimized cooling strategies, the solution algorithm's efficiency and accuracy under complex constraints are improved, ensuring that a solution meeting actual needs can be selected from the Pareto optimal solution set. Simultaneously, the dynamic adjustment mechanism based on real-time tidal and demand fluctuation data can quickly update model parameters and perform local re-optimization, thus maintaining good adaptability in the face of unforeseen circumstances and effectively responding to various dynamic changes that may occur in actual operations.

[0101] The site selection method provided in this application employs multi-objective integer programming to achieve the objectives of minimizing time-related grain loss risk and minimizing task overdue costs, thus balancing efficiency and cost in grain transportation and achieving multi-objective optimization of grain transportation. The first constraint establishes a hard constraint requirement of "grain transshipment + navigation safety," thereby determining the feasible time for transportation nodes to "complete grain transshipment + ensure navigation safety," guaranteeing navigation safety as the foundation for grain transportation and helping to form one of the feasibility constraints for grain transshipment operations in the multi-objective integer programming model. This avoids situations where selected transportation nodes cannot operate within the task's timeframe due to substandard transportation conditions. The second constraint establishes feasibility constraints for grain storage and transportation channels and grain transshipment operations, enabling the selection of a site selection scheme that achieves multi-objective optimization from among feasible options when solving the multi-objective integer programming model. In this way, a balance is achieved in the safety (guaranteed by navigation safety-related constraints), efficiency (guaranteed by minimizing time-related grain loss risks and feasibility constraints for grain storage and transportation channels and grain transshipment operations), and cost (guaranteed by minimizing mission overdue costs) of grain transportation, so that the feasibility and economy of the grain transportation scheme based on the final location are balanced.

[0102] Based on the same inventive concept, this application also provides a location selection apparatus for implementing the location selection method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more location selection apparatus embodiments provided below can be found in the limitations of the location selection method described above, and will not be repeated here.

[0103] In one exemplary embodiment, such as Figure 2 As shown, an addressing device is provided, the addressing device comprising: The data acquisition module is configured to acquire grain flow data and water flow data. The grain flow data includes the task requirement data of grain transportation tasks in the preset grain transportation task set, and the water flow data includes channel water depth data and ship draft data. The timing determination module is configured to determine, based on the grain flow data and the water flow data, a feasible time within a preset time set for each transport node in a preset transport node set that satisfies a first constraint condition; the first constraint condition indicates that there is sufficient time to complete the grain transshipment operation at the transport node and that the vessel can navigate safely in the waterway, wherein the vessel belongs to a preset vessel set. The model building module is configured to build a multi-objective integer programming model including an objective function and a second constraint. The objective function is used to achieve the dual objectives of minimizing time-related grain loss risk and minimizing task overdue costs. The second constraint includes feasibility constraints on grain transportation channels based on the transportation nodes and grain storage institutions, and feasibility constraints on grain transshipment operations based on the task requirement data and the feasible time. The grain storage institutions belong to a pre-set set of grain storage institutions. The scheme generation module is configured to generate candidate site selection schemes based on the second constraint condition; the candidate site selection schemes include the transportation node, the grain storage institution, the grain transshipment operation time window of the grain transportation task at the transportation node, and the handling time cost of the grain transportation task from transshipment at the transportation node to the grain storage institution; The model solving module is configured to solve the multi-objective integer programming model based on the candidate location schemes, and obtain the target location scheme that minimizes the function value of the objective function while satisfying the second constraint condition.

[0104] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes the type of grain; The objective function is: ; in, This indicates the time-related risk of food loss. This represents the overdue cost of the task; Let S represent the objective function, I represent the preset set of transportation nodes, J represent the preset set of grain transportation tasks, and K represent the preset set of grain storage institutions. Represents binary decision variables. Setting it to 1 indicates the decision of grain transportation task i to transfer grain from transportation node s to grain storage facility j. Setting it to 0 indicates that the grain transportation task i does not transfer grain from transportation node s to grain storage facility j. This indicates the type of grain being transferred from transport node s. The grain loss rate caused by the time spent transshipping grain during the process of transporting grain to grain storage facilities. This represents the predicted grain transshipment operation time for grain transportation task i at transportation node s. This represents the daily rental rate for vessel k. This represents the demurrage rate for vessel k. This represents the predicted demurrage time for ship k.

[0105] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes the amount of grain transported and the type of grain. The time cost of transporting grain from the transport node to the grain storage facility is determined by the following formula: ; in, This represents the time cost of transporting grain from transport node s (where the grain is transferred) to grain storage facility j for grain transport task i. This represents the length of the transfer path from transport node s to grain storage facility j. This indicates the transport speed of the grain transshipment equipment. This represents the amount of grain transported for grain transport task i. This represents the efficiency coefficient of the grain transfer equipment. Indicates the type of grain for grain transportation task i. Physical property correction factor , and This represents the weighting coefficient.

[0106] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes a task time window; the channel depth data includes the estimated channel depth and the minimum safe passage depth limit; and the ship draft data includes the estimated ship draft and the maximum permissible draft limit. The first set of constraints includes the mission time window constraint, the channel depth constraint, the ship draft constraint, and the ship safe berthing constraint. The task time window constraint includes the requirement that the grain transshipment operation at the transportation node, starting from time t, can be completed within the task time window of the grain transportation task. The channel depth constraint condition includes that the estimated channel depth at time t is greater than or equal to the minimum safe passage depth limit of the channel. The ship draft constraint conditions include that the estimated ship draft at time t of the ship performing the grain transport mission is less than or equal to the maximum permissible draft limit of the ship. The constraints for safe berthing of the vessel include that the estimated channel depth at time t is greater than or equal to the estimated draft of the vessel at time t. Wherein, time t belongs to the preset time set.

[0107] Optionally, in some embodiments of this application, the task requirement data for the grain transportation task includes the task time window, the amount of grain transported, and the type of grain. The feasibility constraints of the grain transport channel include: there is a practically feasible transport channel between the transport node and the grain storage facility; the capacity of the transport node is sufficient to handle the grain transport volume of the grain transport task; the transfer equipment of the transport node is operable and adaptable to the grain type of the grain transport task; and the handling time cost of the grain transport task from the transport node to the grain storage facility is less than the maximum allowable cost limit. The feasibility constraints of the grain transshipment operation include: the grain transportation task is within the task time window of the grain transshipment operation at the transportation node, and each moment of the grain transportation task within the grain transshipment operation time window at the transportation node is the feasible moment corresponding to the transportation node.

[0108] Optionally, in some embodiments of this application, generating candidate location schemes based on the second constraint includes: The first transportation node and the first grain storage institution that meet the feasibility constraints of the grain storage and transportation channel are fused and coded to obtain the first code; The first grain transshipment operation time window, which satisfies the feasibility constraints of the grain transshipment operation for the first transportation node and the first grain transportation task, and the transportation time cost of the first grain transportation task from the first transportation node to the first grain storage institution are fused and encoded to obtain the second code. The first code and the second code are fused to obtain a candidate addressing scheme.

[0109] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 3As shown, this computer device includes a processor, memory, input / output interfaces (I / O), and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores video tag processing data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements an addressing method.

[0110] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0111] In one exemplary embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0112] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0113] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0114] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0115] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0116] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0117] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0118] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A site selection method, characterized in that, The location selection method includes: Acquire grain flow data and water flow data; grain flow data includes task requirement data for grain transportation tasks in the preset grain transportation task set, and water flow data includes channel depth data and ship draft data. Based on the grain flow data and the water flow data, for each transport node in the preset transport node set, a feasible time that satisfies the first constraint condition is determined within the preset time set; the first constraint condition indicates that there is sufficient time to complete the grain transshipment operation at the transport node and that the ship can safely navigate the waterway, and the ship belongs to the preset ship set. A multi-objective integer programming model is established, including an objective function and a second constraint. The objective function is used to achieve the dual objectives of minimizing time-related grain loss risk and minimizing task overdue costs. The second constraint includes feasibility constraints on grain transportation channels based on the transportation nodes and grain storage institutions, and feasibility constraints on grain transshipment operations based on the task requirement data and the feasible time. The grain storage institutions belong to a pre-set set of grain storage institutions. Candidate site selection schemes are generated based on the second constraint; the candidate site selection schemes include the transportation node, the grain storage facility, the grain transshipment operation time window of the grain transportation task at the transportation node, and the handling time cost of the grain transportation task from transshipment at the transportation node to the grain storage facility; Based on the candidate location schemes, the multi-objective integer programming model is solved to obtain the target location scheme that minimizes the function value of the objective function while satisfying the second constraint condition.

2. The site selection method according to claim 1, characterized in that, The task requirements data for the grain transportation mission include the type of grain; The objective function is: ； in, This indicates the time-related risk of food loss. This represents the overdue cost of the task; Let S represent the objective function, I represent the preset set of transportation nodes, J represent the preset set of grain transportation tasks, and K represent the preset set of grain storage institutions. Represents binary decision variables. Setting it to 1 indicates the decision of grain transportation task i to transfer grain from transportation node s to grain storage facility j. Setting it to 0 indicates that the grain transportation task i does not transfer grain from transportation node s to grain storage facility j. This indicates the type of grain being transferred from transport node s. The grain loss rate caused by the time spent transshipping grain during the process of transporting grain to grain storage facilities. This represents the predicted grain transshipment operation time for grain transportation task i at transportation node s. This represents the daily rental rate for vessel k. This represents the demurrage rate for vessel k. This represents the predicted demurrage time for ship k.

3. The site selection method according to claim 1, characterized in that, The task requirements data for the grain transportation mission include the amount of grain transported and the type of grain. The time cost of transporting grain from the transport node to the grain storage facility is determined by the following formula: ； in, This represents the time cost of transporting grain from transport node s (where the grain is transferred) to grain storage facility j for grain transport task i. This represents the length of the transfer path from transport node s to grain storage facility j. This indicates the transport speed of the grain transshipment equipment. This represents the amount of grain transported for grain transport task i. This represents the efficiency coefficient of the grain transfer equipment. Indicates the type of grain for grain transportation task i. Physical property correction factor , and This represents the weighting coefficient.

4. The site selection method according to claim 1, characterized in that, The task requirements data for the grain transportation mission include the task time window; the channel depth data includes the estimated channel depth and the minimum safe passage depth limit; and the ship draft data includes the estimated ship draft and the maximum permissible draft limit. The first set of constraints includes the mission time window constraint, the channel depth constraint, the ship draft constraint, and the ship safe berthing constraint. The task time window constraint includes the requirement that the grain transshipment operation at the transportation node, starting from time t, can be completed within the task time window of the grain transportation task. The channel depth constraint condition includes that the estimated channel depth at time t is greater than or equal to the minimum safe passage depth limit of the channel. The ship draft constraint conditions include that the estimated ship draft at time t of the ship performing the grain transport mission is less than or equal to the maximum permissible draft limit of the ship. The constraints for safe berthing of the vessel include that the estimated channel depth at time t is greater than or equal to the estimated draft of the vessel at time t. Wherein, time t belongs to the preset time set.

5. The site selection method according to claim 1, characterized in that, The task requirements data for the grain transportation mission include the task time window, grain transportation volume, and grain type. The feasibility constraints of the grain transport channel include: there is a practically feasible transport channel between the transport node and the grain storage facility; the capacity of the transport node is sufficient to handle the grain transport volume of the grain transport task; the transfer equipment of the transport node is operable and adaptable to the grain type of the grain transport task; and the handling time cost of the grain transport task from the transport node to the grain storage facility is less than the maximum allowable cost limit. The feasibility constraints of the grain transshipment operation include: the grain transportation task is within the task time window of the grain transshipment operation at the transportation node, and each moment of the grain transportation task within the grain transshipment operation time window at the transportation node is the feasible moment corresponding to the transportation node.

6. The site selection method according to claim 5, characterized in that, The step of generating candidate location schemes based on the second constraint includes: The first transportation node and the first grain storage institution that meet the feasibility constraints of the grain storage and transportation channel are fused and coded to obtain the first code; The first grain transshipment operation time window, which satisfies the feasibility constraints of the grain transshipment operation for the first transportation node and the first grain transportation task, and the transportation time cost of the first grain transportation task from the first transportation node to the first grain storage institution are fused and encoded to obtain the second code. The first code and the second code are fused to obtain a candidate addressing scheme.

7. A location selection device, characterized in that, The location selection device includes: The data acquisition module is configured to acquire grain flow data and water flow data. The grain flow data includes the task requirement data of grain transportation tasks in the preset grain transportation task set, and the water flow data includes channel water depth data and ship draft data. The timing determination module is configured to determine, based on the grain flow data and the water flow data, a feasible time within a preset time set for each transport node in a preset transport node set that satisfies a first constraint condition; the first constraint condition indicates that there is sufficient time to complete the grain transshipment operation at the transport node and that the vessel can navigate safely in the waterway, wherein the vessel belongs to a preset vessel set. The model building module is configured to build a multi-objective integer programming model including an objective function and a second constraint. The objective function is used to achieve the dual objectives of minimizing time-related grain loss risk and minimizing task overdue costs. The second constraint includes feasibility constraints on grain transportation channels based on the transportation nodes and grain storage institutions, and feasibility constraints on grain transshipment operations based on the task requirement data and the feasible time. The grain storage institutions belong to a pre-set set of grain storage institutions. The scheme generation module is configured to generate candidate site selection schemes based on the second constraint condition; the candidate site selection schemes include the transportation node, the grain storage institution, the grain transshipment operation time window of the grain transportation task at the transportation node, and the handling time cost of the grain transportation task from transshipment at the transportation node to the grain storage institution; The model solving module is configured to solve the multi-objective integer programming model based on the candidate location schemes, and obtain the target location scheme that minimizes the function value of the objective function while satisfying the second constraint condition.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the addressing method according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the addressing method according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the addressing method according to any one of claims 1-6.

Images