Method, device and equipment for site selection of commercial concrete shared weighbridge and storage medium

Abstract

The present application relates to a kind of commercial concrete shared weighbridge site selection method, device, equipment and storage medium, belong to facility site selection technical field, wherein the commercial concrete shared weighbridge site selection method includes obtaining the commercial concrete demand data and weighbridge state data of commercial concrete distribution area, based on commercial concrete demand data and weighbridge state data draw the commercial concrete demand graph and weighbridge state graph of commercial concrete distribution area;Commercial concrete demand graph and weighbridge state graph are identified using the preset double-branch neural network model, and the action value graph is obtained, the action value graph is used to reflect the action value corresponding to the action of commercial concrete shared weighbridge site selection in commercial concrete distribution area;Commercial concrete shared weighbridge site selection is carried out based on the action value highest commercial concrete shared weighbridge site selection action in action value graph.The present application can consider complex commercial concrete site selection factor, can respond to the change of commercial concrete demand in real time, provide efficient site selection strategy, reduce energy consumption and unreasonable consumption in commercial concrete transportation, save cost.

Description

Technical Field

[0001] This invention relates to the field of facility site selection technology, and in particular to a method, apparatus, equipment and storage medium for site selection of shared weighbridges for commercial concrete. Background Technology

[0002] With the development of my country's construction industry, the commercial concrete (commercial concrete) supply industry has also matured. To ensure sufficient supply of commercial concrete according to orders, buyers need to weigh concrete transport vehicles, and weighbridges are the primary tool for this purpose. The traditional solution is a "one-to-one" approach, where a separate weighbridge is set up at each construction site, serving only one site. The advantage of this traditional solution is that it is immediately put into use after weighing, allowing for the accurate detection of unreasonable large losses during concrete transportation. However, the disadvantage is the high cost of setting up a separate weighbridge for each site. Some sites are close to each other, and within this short distance, there is no need to worry about large unreasonable losses during concrete transportation. Therefore, using the same weighbridge for weighing concrete transport vehicles at nearby sites is a reasonable and feasible approach, effectively reducing costs compared to the traditional "one-to-one" solution.

[0003] However, the location selection of such shared weighbridges has become a new problem. Different construction sites have different demands for ready-mixed concrete, and the supply capacity of ready-mixed concrete plants also varies. The distance between the ready-mixed concrete plant, the construction site, and the shared weighbridge, as well as the transportation difficulties, are all factors to consider when selecting the location of shared weighbridges. Furthermore, the demand for ready-mixed concrete is constantly changing, so the location of the shared weighbridge may need to be changed frequently. However, the cost of frequently changing the shared weighbridge may be higher than that of building a new weighbridge. Therefore, coordinating the location selection of shared weighbridges is a challenge.

[0004] This shows that existing technologies cannot provide accurate site selection solutions for shared weighbridges used in commercial concrete production. Summary of the Invention

[0005] In view of this, it is necessary to provide a method, device, equipment and storage medium for selecting the location of a shared weighbridge for commercial concrete, so as to solve the problem that the existing technology cannot provide an accurate location selection scheme for a shared weighbridge for commercial concrete.

[0006] To address the above problems, this invention provides a method for selecting the location of a shared weighbridge for commercial concrete production, comprising:

[0007] Obtain commercial concrete demand data and weighbridge status data for the commercial concrete delivery area, and draw commercial concrete demand map and weighbridge status map for the commercial concrete delivery area based on the commercial concrete demand data and weighbridge status data.

[0008] A pre-defined dual-branch neural network model is used to identify the demand map of ready-mixed concrete and the status map of the weighbridge to obtain an action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area.

[0009] The location of the shared weighbridge for commercial concrete is selected based on the action with the highest action value in the action value graph.

[0010] In one possible implementation, the process involves acquiring commercial concrete demand data and weighbridge status data for the commercial concrete delivery area, and then drawing a commercial concrete demand map and a weighbridge status map for the commercial concrete delivery area based on the commercial concrete demand data and weighbridge status data.

[0011] The commercial concrete delivery area is gridded, and the commercial concrete plants, commercial concrete weighbridges, and construction sites in the commercial concrete delivery area are mapped to the grid area.

[0012] Determine the waybill data for each construction site within a preset time step, and determine the pixel value of the corresponding grid for the construction site based on the waybill data to obtain the ready-mixed concrete demand map;

[0013] Determine the active state of each concrete weighbridge, and based on the active state, determine the pixel value of the corresponding grid of the concrete weighbridge to obtain the weighbridge status map.

[0014] In one possible implementation, a pre-defined dual-branch neural network model is used to identify the ready-mixed concrete demand map and the weighbridge status map to obtain an action value map, including:

[0015] The first branch network of the pre-defined dual-branch neural network model is used to extract features from the ready-mixed concrete demand map to obtain the ready-mixed concrete demand feature map.

[0016] The second branch network of the pre-defined dual-branch neural network model is used to extract features from the weighbridge status map to obtain the weighbridge status feature map;

[0017] The demand characteristic map of commercial concrete and the status characteristic map of the weighbridge are fused to obtain a characteristic fusion map, and the action value map is determined based on the characteristic fusion map.

[0018] In one possible implementation, determining the action value map based on the feature fusion map includes:

[0019] Based on the feature fusion map, a reinforcement learning algorithm is used to estimate the action value of performing each type of commercial concrete shared weighbridge action on each grid in the grid region;

[0020] The action value map is determined based on the highest action value on each grid in the grid region.

[0021] In one possible implementation, the actions of shared weighbridges for commercial concrete include adding weighbridges, deleting weighbridges, and moving weighbridges.

[0022] In one possible implementation, a reinforcement learning algorithm is used based on the feature fusion map to estimate the action value of performing each type of commercial concrete shared weighbridge action on each grid in the grid region, including:

[0023] For each sub-time step, a reinforcement learning algorithm is used to calculate the action value of each commercial concrete shared weighbridge action. The action value includes the cost and reward of the commercial concrete shared weighbridge action. Each sub-time step can execute one commercial concrete shared weighbridge action.

[0024] In one possible implementation, the location selection of the shared weighbridge for commercial concrete is based on the action with the highest action value in the action value graph, including:

[0025] Determine the target commercial concrete shared weighbridge site selection action with the highest action value in each grid of the action value map;

[0026] Perform the target commercial concrete shared weighbridge site selection action in the area corresponding to the grid.

[0027] The present invention also provides a shared weighbridge site selection device for commercial concrete, comprising:

[0028] The image creation module is used to acquire commercial concrete demand data and weighbridge status data in the commercial concrete delivery area, and to draw commercial concrete demand map and weighbridge status map of the commercial concrete delivery area based on the commercial concrete demand data and weighbridge status data.

[0029] The action value calculation module is used to identify the ready-mixed concrete demand map and the weighbridge status map using a preset dual-branch neural network model to obtain the action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area.

[0030] The site selection module is used to select the site for the commercial concrete shared weighbridge based on the action with the highest action value in the action value graph.

[0031] The present invention also provides an electronic device, including a memory and a processor, wherein,

[0032] Memory, used to store programs;

[0033] A processor, coupled to a memory, is used to execute a program stored in the memory to implement the steps in the commercial concrete shared weighbridge site selection method of any of the above embodiments.

[0034] The present invention also provides a computer-readable storage medium for storing a computer-readable program or instruction, which, when executed by a processor, can implement the steps in the commercial concrete shared weighbridge site selection method of any of the above embodiments.

[0035] The beneficial effects of this invention are as follows: The shared weighbridge site selection method for commercial concrete provided by this invention transforms the commercial concrete demand data and weighbridge status data of the commercial concrete delivery area into a commercial concrete demand map and a weighbridge status map. A dual-branch neural network model is then used to identify these maps, resulting in an action value map that reflects the action value corresponding to the shared weighbridge site selection action in the commercial concrete delivery area. The shared weighbridge site selection is then performed based on the action with the highest action value. This method can consider complex commercial concrete site selection factors, respond to changing commercial concrete demand in real time, provide an efficient site selection strategy, reduce energy consumption and unreasonable consumption during commercial concrete transportation, and save costs. Attached Figure Description

[0036] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 A flowchart illustrating a method for selecting a shared weighbridge for commercial concrete production, provided in an embodiment of the present invention;

[0038] Figure 2 A flowchart illustrating one implementation of S101 provided in this embodiment of the invention;

[0039] Figure 3 A flowchart illustrating one implementation of S102 provided in this embodiment of the invention;

[0040] Figure 4 This is a schematic diagram of the structure of a dual-branch neural network model provided in an embodiment of the present invention;

[0041] Figure 5 A flowchart illustrating a method for determining action value maps according to an embodiment of the present invention;

[0042] Figure 6 A flowchart illustrating a weighbridge site selection method provided in an embodiment of the present invention;

[0043] Figure 7 This is a schematic diagram of the structure of a device provided in an embodiment of the present invention;

[0044] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0045] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which constitute a part of the present invention and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0046] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0047] In this embodiment of the invention, in order to concisely express the problem, the symbols required to define the problem are first agreed upon as follows:

[0048] Construction site collection, for Where x and y are the x-coordinate and y-coordinate of the construction site address, and These refer to the start and stop times of the construction site. The construction site's demand for ready-mixed concrete can only occur during [specific time periods]. and between;

[0049] The ready-mixed concrete plant cluster includes all ready-mixed concrete plants that can supply any construction site. It is the production site of ready-mixed concrete and the starting point of ready-mixed concrete transportation.

[0050] The set of time steps ;

[0051] The set of all possible weighbridge locations is a candidate set of weighbridge locations. This includes suitable locations inside or near the construction site, as well as all other possible locations. This set is designed to include as many possible locations as possible during the designation process to provide ample optimization space for the algorithm.

[0052] The set of all weighbridges that remain open (active) at time step t. The algorithm will select some weighbridges to be opened and others to be closed at certain time steps. A weighbridge is active and belongs to this set when it is opened and closed.

[0053] : Demand set, for ,in, , , , representing the construction site p In the tOne demand for ready-mixed concrete was generated in the time step, requiring one truck to be transported from the plant. s A single transportation transaction and a single order from the construction site may generate multiple demands. r Preprocessing is required when inputting data;

[0054] W: Waybill set For a , One waybill will be generated immediately. ,in, , ,and , Is it away The nearest weighbridge;

[0055] : Measurement function, unit is meter, for all Based on the road network, calculate the distances between all potentially involved locations;

[0056] The cost of adding a new weighbridge;

[0057] The cost of moving a weighbridge;

[0058] : This is a real number and represents the weight reliability penalty factor. The farther the weighbridge is from the construction site, the lower the reliability of the weight. This factor is greater than 1 and is used to emphasize the importance of the distance between the weighbridge and the construction site.

[0059] The newly opened weighbridge at time t;

[0060] The weighbridge transfer set at time step t, for ,have , .

[0061] The problem of site selection for shared weighbridges for commercial concrete: Given For t=123...T, facing the set of waybills at time step t Find the optimal action , To minimize the following objectives:

[0062]

[0063] in, It is the sum of the distances from the factory to the weighbridge for all waybills, aiming to optimize the total transportation distance in order to reduce transportation costs and achieve energy conservation and emission reduction. It is the weighing reliability penalty factor multiplied by the sum of the distances from the weighbridge to the construction site for all waybills. This is used to constrain the weighbridge from being too far from the construction site, thus ensuring weighing reliability. and This refers to the sum of the costs of setting up a new weighbridge and relocating a weighbridge, ensuring that existing weighbridges can be effectively utilized.

[0064] A specific embodiment of the present invention discloses a method for selecting the location of a shared weighbridge for commercial concrete, comprising:

[0065] S101, Obtain commercial concrete demand data and weighbridge status data in the commercial concrete delivery area, and draw commercial concrete demand map and weighbridge status map of the commercial concrete delivery area based on the commercial concrete demand data and weighbridge status data.

[0066] S102, a preset dual-branch neural network model is used to identify the demand map of ready-mixed concrete and the status map of the weighbridge to obtain the action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area.

[0067] S103, Select the location of the commercial concrete shared weighbridge based on the action with the highest action value in the action value graph.

[0068] In this embodiment of the invention, the ready-mixed concrete delivery area refers to an area that simultaneously has ready-mixed concrete plants, construction sites, and shared ready-mixed concrete weighbridges, and where site selection and planning for the shared ready-mixed concrete weighbridges are required. Within this delivery area, ready-mixed concrete delivery demand will arise. The ready-mixed concrete demand data includes the construction sites requiring ready-mixed concrete, the quantity of ready-mixed concrete needed, the ready-mixed concrete plants providing the concrete, and the shared ready-mixed concrete weighbridges used to weigh the concrete. Weighbridge status data includes the status of all shared ready-mixed concrete weighbridges within the delivery area, such as operating status, maintenance status, pending transfer status, and stopped status. The ready-mixed concrete demand diagram and the weighbridge status diagram are used to display the ready-mixed concrete demand and weighbridge status within the delivery area, respectively. The specific drawing method will be described in detail later in this invention.

[0069] In this embodiment of the invention, the preset dual-branch neural network model can identify the demand map of ready-mixed concrete and the status map of the weighbridge, and output an action value map. The action value map is used to reflect the action value corresponding to the action of selecting a shared weighbridge for ready-mixed concrete in the ready-mixed concrete delivery area. Based on the action value map, the location of the shared weighbridge for ready-mixed concrete can be selected.

[0070] The present invention provides a method for selecting a shared weighbridge for ready-mixed concrete. This method transforms ready-mixed concrete demand data and weighbridge status data in the ready-mixed concrete delivery area into a ready-mixed concrete demand map and a weighbridge status map. A dual-branch neural network model is then used to identify these maps, resulting in an action value map that reflects the action value corresponding to the shared weighbridge selection action in the ready-mixed concrete delivery area. The method selects the shared weighbridge location based on the action with the highest action value. This approach considers complex factors in ready-mixed concrete selection, responds to changing demand in real time, provides an efficient selection strategy, reduces energy consumption and unreasonable consumption during ready-mixed concrete transportation, and saves costs.

[0071] As one possible embodiment of the present invention, in this embodiment, such as Figure 2 As shown, the process involves acquiring commercial concrete demand data and weighbridge status data for the commercial concrete delivery area, and then creating a commercial concrete demand map and a weighbridge status map for the commercial concrete delivery area based on these data. This includes:

[0072] S201 divides the commercial concrete delivery area into a grid and maps the commercial concrete plant, commercial concrete weighbridge and construction site in the commercial concrete delivery area into the grid area;

[0073] S202, determine the waybill data for each construction site within a preset time step, and determine the pixel value of the corresponding grid for the construction site based on the waybill data to obtain the ready-mixed concrete demand map;

[0074] S203, determine the active state of each concrete weighbridge, and determine the pixel value of the corresponding grid of the concrete weighbridge based on the active state to obtain the weighbridge state diagram.

[0075] In this embodiment of the invention, the ready-mixed concrete delivery area can be gridded into N×N grid regions. Then, the geographical locations of all ready-mixed concrete plants, shared weighbridges, and construction sites are extracted and mapped onto the grid. Generally, the side length of each grid needs to be between 150 and 250 meters to achieve fine-grained modeling of the delivery area while also reducing the action space. Furthermore, the waybill data includes the addresses of the originating plant, the weighbridges along the route, and the destination construction site. This step requires associating the waybill with the already discretized plants and construction sites, and placing the demand within a given time step at the corresponding location of the construction site in the grid to construct a demand graph. A demand graph. The size of the grid area is the same as the N×N grid area of ​​the ready-mixed concrete delivery area, where the pixel value of each grid is the number of transportation activities generated at the construction site at time step t. Furthermore, since the algorithm involves continuously optimizing the layout of the shared weighbridges over multiple consecutive time steps (i.e., over multiple consecutive days), it is necessary to maintain the active state of the weighbridges, as shown in the weighbridge state diagram. The size of the grid area is the same as the N×N grid area of ​​the ready-mixed concrete delivery area, where each grid pixel value is 0 or 1, where 1 represents that the weighbridge is active and 0 represents that there is no weighbridge at that location. Based on this, a ready-mixed concrete demand map and a weighbridge status map of the ready-mixed concrete delivery area can be constructed.

[0076] This invention constructs a commercial concrete demand map and a weighbridge status map of the commercial concrete delivery area based on commercial concrete demand data and weighbridge status data, which facilitates the subsequent recognition by the neural network model.

[0077] As one possible embodiment of the present invention, in this embodiment, such as Figure 3 As shown, a pre-defined dual-branch neural network model is used to identify the demand map of commercial concrete and the weighbridge status map to obtain an action value map, including:

[0078] S301, the first branch network of the preset dual-branch neural network model is used to extract features from the ready-mixed concrete demand map to obtain the ready-mixed concrete demand feature map;

[0079] S302, the second branch network of the preset dual-branch neural network model is used to extract features from the weighbridge status map to obtain the weighbridge status feature map;

[0080] S303, perform feature fusion on the demand feature map of commercial concrete and the status feature map of the weighbridge to obtain a feature fusion map, and determine the action value map based on the feature fusion map.

[0081] In this embodiment of the invention, the two branches of the provided dual-branch neural network model use consecutive downsampling layers to extract high-order features of the environmental state, obtaining feature maps of different levels. Each feature map of the same level is then fused through a gated feature fusion layer to determine the importance of the concrete demand features and the weighbridge status features, resulting in fused feature maps of different levels. Specifically, as shown... Figure 4 As shown, the downsampling layer consists of two successive convolutional layers connected to a max-pooling layer. Taking the output of the first-level downsampling layer as an example, the gating fusion mechanism of ready-mixed concrete demand and weighbridge status characteristics is as follows:

[0082] High-order feature map extracted from a ready-mixed concrete demand map And a high-order feature map extracted from a weighbridge status image. First, a linear transformation is performed through convolution:

[0083] ,

[0084] in, This represents the convolution operation. and For convolution kernel, and This is a bias term.

[0085] Next, the feature map after linear transformation will be... and The gating signal is calculated using an activation function, which uses... Sigmoid function:

[0086]

[0087] in, for Sigmoid function, It is the gating weight of the element in the interval [0, 1], which controls the fusion ratio of the two feature maps.

[0088] Based on the gating signal G, the demand map for ready-mixed concrete and the weighbridge status map are weighted and summed to obtain the fused feature map. :

[0089]

[0090] in, This indicates a point-by-point multiplication operation, which means using a gating signal. right and Apply appropriate weighting.

[0091] First-order fusion feature diagram of ready-mixed concrete demand and weighbridge status The output to be spliced ​​into the first-level downsampling layer and Then, they are used as inputs for the second-level bi-branch downsampling. , ]and[ , Repeat the above steps until all operations for each branch are completed.

[0092] In this embodiment of the invention, the lower half of the network estimates the value of placing and deleting a weighbridge in each square from the higher-order features, as well as the value of stopping the action (stopping the decision process at this time step). The final output space size of the network is [ ; ; The algorithm consists of adding a weighbridge action value map, deleting a weighbridge action value map, and stopping action value. This part uses successive upsampling layers, each consisting of a deconvolutional layer followed by two consecutive convolutional layers. To consider the decision of whether to stop at the current time step from a global perspective, this network inputs the highest-order feature map output from the branch modeling part into a multilayer perceptron to estimate the value of the decision to stop at that time step. By concatenating the feature maps of each level of the branch modeling part into the action value estimation feature map of the same size, fine-grained information can be effectively preserved, supplementing the detailed information lost by the high-order features obtained through the convolutional neural network.

[0093] As one possible embodiment of the present invention, in this embodiment, such as Figure 5 As shown, the action value map is determined based on the feature fusion map, including:

[0094] S501, based on the feature fusion map, uses a reinforcement learning algorithm to estimate the action value of performing each type of commercial concrete shared weighbridge action on each grid in the grid region;

[0095] S502, determine the action value map based on the highest action value on each grid in the grid region.

[0096] In this embodiment of the invention, when estimating the value of placing and deleting a weighbridge in each square, or the value of moving a weighbridge, based on the feature fusion map, it is necessary to optimize the estimation process by combining a reinforcement learning algorithm. The specific reinforcement learning algorithm is as follows:

[0097] enter( , P, S, T , Environmental Action Modeling Network Exploration rate Experience replay cache M, discount factor Learning rate Target network update frequency C); Output the trained environment action modeling network; Initialize the experience storage cache M; Initialize the network Parameters; Initialize target network parameters Define the path set R = reachable paths (start point, end point); for each training step:

[0098] Choose actions based on a greedy strategy. :

[0099]

[0100] if If the action ends or the number of sub-time steps for the day exceeds the total number of sub-time steps, then the processing for the day ends.

[0101] Otherwise, execute Receive rewards and the next state ;

[0102] Will Add to the experience replay cache, and randomly select a small batch from the experience replay library. Calculate the target Q value;

[0103]

[0104] Minimize the loss function using gradient descent and update the network parameters. :

[0105]

[0106] Every C steps, the network parameters are... The parameters are copied to the target network and ultimately returned as environmental action modeling network parameters. .

[0107] Furthermore, the shared weighbridge operations for commercial concrete include adding weighbridges, deleting weighbridges, and moving weighbridges.

[0108] Furthermore, based on the feature fusion map, a reinforcement learning algorithm is used to estimate the action value of performing each type of commercial concrete shared weighbridge action on each grid in the grid region, including:

[0109] For each sub-time step, a reinforcement learning algorithm is used to calculate the action value of each commercial concrete shared weighbridge action. The action value includes the cost and reward of the commercial concrete shared weighbridge action. Each sub-time step can execute one commercial concrete shared weighbridge action.

[0110] In this embodiment of the invention, the reinforcement learning algorithm is based on the DQN algorithm and features a flexible sub-time step design. Considering that the installation and transportation of shared weighbridges require time, one time step is defined as one day. However, considering that there may be zero or more new demands within a region in a day, it may be necessary to make zero or more weighbridge action decisions within one time step. Therefore, an ending action is designed, dividing the day into zero to multiple sub-time steps, each step determining the action of one weighbridge, until the model determines that the decision for that day should end, and then proceeding to the decision for the next day. To maintain robustness, this technique sets an experience upper limit L for each day's sub-time step, and the optimization objective is reflected in the reward during the reinforcement learning training phase. reward The specific calculation formula is as follows:

[0111]

[0112] in, For orders that need to be processed on day t, and Let each be a set of actions performed at the current sub-time step on day t, involving either adding or transferring a weighbridge. Specifically, since only one action is performed at each sub-time step, therefore... and The value cannot be greater than 0 at the same time, and can be at most equal to 1. Based on this, the reward value for performing one of the actions of adding a weighbridge, moving a weighbridge, or deleting a weighbridge in each current state can be calculated, which can facilitate the deep learning algorithm to optimize it and obtain the best weighbridge location action.

[0113] Furthermore, such as Figure 6 As shown, the site selection for a shared weighbridge for commercial concrete is based on the action with the highest action value in the action value graph, including:

[0114] S601, determine the target commercial concrete shared weighbridge site selection action with the highest action value in each grid of the action value map;

[0115] S602, execute the target commercial concrete shared weighbridge site selection action in the area corresponding to the grid.

[0116] In this embodiment of the invention, based on the action value map obtained from the foregoing embodiments, each grid corresponds to an action value for performing a certain commercial concrete shared weighbridge site selection action. The commercial concrete shared weighbridge site selection action with the highest action value is determined as the target commercial concrete shared weighbridge site selection action for that grid, and within the area corresponding to that grid, one of the following actions is performed: creation, transfer, or deletion of the weighbridge.

[0117] The present invention provides a method for selecting a shared weighbridge for ready-mixed concrete. This method transforms ready-mixed concrete demand data and weighbridge status data in the ready-mixed concrete delivery area into a ready-mixed concrete demand map and a weighbridge status map. A dual-branch neural network model is then used to identify these maps, resulting in an action value map that reflects the action value corresponding to the shared weighbridge selection action in the ready-mixed concrete delivery area. The method selects the shared weighbridge location based on the action with the highest action value. This approach considers complex factors in ready-mixed concrete selection, responds to changing demand in real time, provides an efficient selection strategy, reduces energy consumption and unreasonable consumption during ready-mixed concrete transportation, and saves costs.

[0118] To better implement the shared weighbridge site selection method for commercial concrete in this embodiment of the invention, based on the shared weighbridge site selection method for commercial concrete, the corresponding method is as follows: Figure 7 As shown, this embodiment of the invention also provides a shared weighbridge site selection device for commercial concrete, the shared weighbridge site selection device 700 for commercial concrete comprising:

[0119] The image creation module 701 is used to acquire commercial concrete demand data and weighbridge status data in the commercial concrete delivery area, and to draw commercial concrete demand map and weighbridge status map of the commercial concrete delivery area based on the commercial concrete demand data and weighbridge status data.

[0120] The action value calculation module 702 is used to identify the ready-mixed concrete demand map and the weighbridge status map using a preset dual-branch neural network model to obtain the action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area.

[0121] The site selection operation module 703 is used to select the site of the commercial concrete shared weighbridge based on the action with the highest action value in the action value graph.

[0122] The commercial concrete shared weighbridge location selection device 700 provided in the above embodiments can realize the technical solutions described in the above commercial concrete shared weighbridge location selection method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content of the above commercial concrete shared weighbridge location selection method embodiments, which will not be repeated here.

[0123] like Figure 8 As shown, the present invention also provides an electronic device 800. The electronic device 800 includes a processor 801, a memory 802, and a display 803. Figure 8 Only some components of the electronic device 800 are shown, but it should be understood that it is not required to implement all the components shown, and more or fewer components may be implemented instead.

[0124] In some embodiments, processor 801 may be a central processing unit (CPU), a microprocessor, or other data processing chip, used to run program code stored in memory 802 or process data, such as the shared weighbridge location method for commercial concrete in this invention.

[0125] In some embodiments, processor 801 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 801 may be local or remote. In some embodiments, processor 801 may be implemented on a cloud platform. In some embodiments, the cloud platform may include private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0126] In some embodiments, memory 802 may be an internal storage unit of electronic device 800, such as a hard disk or memory of electronic device 800. In other embodiments, memory 802 may also be an external storage device of electronic device 800, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. equipped on electronic device 800.

[0127] Furthermore, the memory 802 may include both internal storage units of the electronic device 800 and external storage devices. The memory 802 is used to store application software and various types of data installed on the electronic device 800.

[0128] In some embodiments, display 803 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 803 is used to display information from electronic device 800 and to display a visual user interface. Components 801-803 of electronic device 800 communicate with each other via a system bus.

[0129] In some embodiments, when the processor 801 executes the shared weighbridge location program for commercial concrete stored in the memory 802, the following steps may be implemented:

[0130] Obtain commercial concrete demand data and weighbridge status data for the commercial concrete delivery area, and draw commercial concrete demand map and weighbridge status map for the commercial concrete delivery area based on the commercial concrete demand data and weighbridge status data.

[0131] A pre-defined dual-branch neural network model is used to identify the demand map of ready-mixed concrete and the status map of the weighbridge to obtain an action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area.

[0132] The location of the shared weighbridge for commercial concrete is selected based on the action with the highest action value in the action value graph.

[0133] It should be understood that when the processor 801 executes the shared weighbridge location program for commercial concrete in the memory 802, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0134] Furthermore, this embodiment of the invention does not specifically limit the type of electronic device 800 mentioned. Electronic device 800 can be a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, laptop computer, or other portable electronic device. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, electronic device 800 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0135] Accordingly, embodiments of the present invention also provide a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions in the commercial concrete shared weighbridge site selection method provided in the above-described method embodiments.

[0136] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0137] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for selecting a site for a shared weighbridge for commercial concrete, characterized in that, include: Obtain commercial concrete demand data and weighbridge status data for the commercial concrete delivery area, and draw a commercial concrete demand map and a weighbridge status map for the commercial concrete delivery area based on the commercial concrete demand data and the weighbridge status data. A preset dual-branch neural network model is used to identify the ready-mixed concrete demand map and the weighbridge status map to obtain an action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area. The location of the shared weighbridge for commercial concrete is selected based on the action with the highest action value in the action value diagram. The process of acquiring commercial concrete demand data and weighbridge status data for the commercial concrete delivery area, and drawing commercial concrete demand maps and weighbridge status maps for the commercial concrete delivery area based on the commercial concrete demand data and the weighbridge status data, includes: The commercial concrete delivery area is gridded, and the commercial concrete plants, commercial concrete weighbridges, and construction sites in the commercial concrete delivery area are mapped to the grid area; Determine the waybill data for each construction site within a preset time step, and determine the pixel value of the corresponding grid for each construction site based on the waybill data to obtain the ready-mixed concrete demand map; The active state of each concrete weighbridge is determined, and the pixel value of the corresponding grid of the concrete weighbridge is determined based on the active state to obtain the weighbridge state diagram.

2. The method for selecting a shared weighbridge for commercial concrete production according to claim 1, characterized in that, The process of using a pre-defined dual-branch neural network model to identify the ready-mixed concrete demand map and the weighbridge status map to obtain an action value map includes: The first branch network of a preset dual-branch neural network model is used to extract features from the ready-mixed concrete demand map to obtain a ready-mixed concrete demand feature map. The second branch network of a preset dual-branch neural network model is used to extract features from the weighbridge status map to obtain a weighbridge status feature map. The demand feature map of commercial concrete and the status feature map of the weighbridge are fused to obtain a feature fusion map, and an action value map is determined based on the feature fusion map.

3. The method for selecting a shared weighbridge for commercial concrete production according to claim 2, characterized in that, The process of determining the action value map based on the feature fusion map includes: Based on the feature fusion map, a reinforcement learning algorithm is used to estimate the action value of performing each type of commercial concrete shared weighbridge action on each grid in the grid region; An action value map is determined based on the highest action value on each grid in the grid region.

4. The method for selecting a shared weighbridge for commercial concrete production according to claim 3, characterized in that, The actions for shared weighbridges for commercial concrete include adding weighbridges, deleting weighbridges, and moving weighbridges.

5. The method for selecting a shared weighbridge for commercial concrete production according to claim 3, characterized in that, The step of estimating the action value of each type of commercial concrete shared weighbridge action on each grid in the grid region using a reinforcement learning algorithm based on the feature fusion map includes: For each sub-time step, a reinforcement learning algorithm is used to calculate the action value of each commercial concrete shared weighbridge action. The action value includes the cost and reward of the commercial concrete shared weighbridge action. Each sub-time step can execute one commercial concrete shared weighbridge action.

6. The method for selecting a shared weighbridge for commercial concrete production according to claim 3, characterized in that, The selection of a shared weighbridge for commercial concrete based on the action with the highest action value in the action value graph includes: Determine the target commercial concrete shared weighbridge site selection action with the highest action value in each grid of the action value map; The target commercial concrete shared weighbridge site selection action is performed in the area corresponding to the grid.

7. A site selection device for a shared weighbridge for commercial concrete, applicable to the site selection method for a shared weighbridge for commercial concrete as described in any one of claims 1 to 6, characterized in that, include: The image creation module is used to acquire commercial concrete demand data and weighbridge status data in the commercial concrete delivery area, and to draw a commercial concrete demand map and a weighbridge status map of the commercial concrete delivery area based on the commercial concrete demand data and the weighbridge status data. The action value calculation module is used to identify the ready-mixed concrete demand map and the weighbridge status map using a preset dual-branch neural network model to obtain an action value map. The action value map is used to reflect the action value corresponding to the location selection action of the shared weighbridge in the ready-mixed concrete delivery area. The site selection operation module is used to select the site for the commercial concrete shared weighbridge based on the action with the highest action value in the action value diagram.

8. An electronic device, characterized in that, Including memory and processor, among which, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the commercial concrete shared weighbridge site selection method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the commercial concrete shared weighbridge site selection method according to any one of claims 1 to 6.

Images