Initial flue-cured tobacco goods yard tobacco vehicle warehouse-in and warehouse-out guidance method and system

Abstract

The embodiment of the invention provides an initial flue-cured tobacco goods yard tobacco vehicle warehouse-in and warehouse-out guidance method and system, and the method comprises the steps: collecting the initial flue-cured tobacco warehouse-in and warehouse-out historical data of a goods yard, training and optimizing a goods allocation demand prediction model based on the initial flue-cured tobacco warehouse-in and warehouse-out historical data, and obtaining a goods allocation demand prediction result; classifying the goods locations of the goods yard based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the goods locations by adopting an ant colony search algorithm, and establishing a goods location distribution model to obtain a goods location distribution result; and establishing a goods allocation path selection model based on the goods allocation demand prediction result and the goods allocation distribution result, and realizing optimal path selection of a vehicle in-out link. The method effectively guides the in-out warehouse process of the primary flue-cured tobacco vehicle, can effectively utilize goods yard resources, and improves the raw material response speed.

Description

Technical Field

[0001] This document relates to the field of warehousing and logistics technology, and in particular to a method and system for guiding tobacco vehicles in and out of a first-cured tobacco yard. Background Art

[0002] The storage of first-cured tobacco is a key link in the storage of raw materials in the tobacco industry. It mainly involves transporting the first-cured tobacco leaves from the tobacco station to the first-cured tobacco yard by tobacco leaf transport vehicles for storage in the warehouse. After that, the first-cured tobacco leaves are added and baked according to the requirements of the leaf beating and re-baking group formula. In this process, the following problems may be encountered:

[0003] 1. Limited cargo yard resources

[0004] Taking Yunnan Tobacco and Tobacco Leaf Company as an example, the annual storage volume of first-cured tobacco is about 2.6 million dan, and the storage volume of first-cured tobacco in the open-air freight yard is about 600,000 dan. After the tobacco truck arrives, the tobacco leaves on the vehicle are vacated to a single cargo space or multiple cargo spaces according to the requirements of the freight yard management personnel until the freight yard resources are used up. In this process, the freight yard performs corresponding re-drying in accordance with the company's relevant requirements for leaf threshing and re-drying to free up cargo spaces. If the existing freight yard resources are not fully utilized, the freight yard resources will be wasted, that is, the freight yard stores tobacco leaves that are not needed for leaf threshing and re-drying in the short term, and a large amount of first-cured tobacco leaves are stored in the tobacco station and cannot be supplied, resulting in mildew of the tobacco leaves, bringing huge economic losses.

[0005] 2. Untimely response to raw materials

[0006] When the raw materials enter the warehouse, the allocation is random, resulting in the priority of shipping out the cargo spaces close to the redrying workshop to meet the needs of the leaf group formula, resulting in the inability to effectively ship out the cargo spaces far from the redrying workshop but meeting the leaf group formula for roasting. Because the raw materials of the leaf group formula are aggregated, if they are not roasted in time, the raw materials of this grade will be detained in the warehouse for a long time. First, occupying the cargo space resources affects the storage of other raw materials. Second, long-term storage brings great pressure on raw material management and maintenance, and the risk of mildew is greatly increased. In summary, the raw materials in the warehouse are not responsive to the leaf threshing and roasting feeding in a timely manner. Summary of the invention

[0007] One or more embodiments of this specification provide a method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard, including:

[0008] Collecting historical data of freshly-cured tobacco in and out of the warehouse, training and optimizing a cargo space demand prediction model based on the historical data of freshly-cured tobacco in and out of the warehouse, and obtaining a cargo space demand prediction result;

[0009] Ant colony search algorithm is used to classify the cargo spaces in the cargo yard based on the location and destination of the raw materials of flue-cured tobacco and the distance between the cargo spaces, and a cargo space allocation model is established to obtain the cargo space allocation result.

[0010] A cargo space path selection model is established based on the cargo space demand prediction results and cargo space allocation results to achieve optimal path selection for vehicle entry and exit links.

[0011] Furthermore, the method of collecting the historical data of the freshly flue-cured tobacco in and out of the warehouse, training and optimizing the cargo space demand prediction model based on the historical data of the freshly flue-cured tobacco in and out of the warehouse, and obtaining the cargo space demand prediction result is as follows:

[0012] The collected historical data of freshly flue-cured tobacco in and out of the freight yard are divided into a training set and a test set;

[0013] The recursive neural network (RNN) model is trained by using the training set to capture the time dependency in the training set sequence data, and the cargo space demand is predicted based on the time dependency to obtain an initial model for cargo space demand prediction;

[0014] The prediction accuracy of the initial model for cargo space demand prediction is tested through a test set, and the model parameters are optimized according to the test results. When the prediction accuracy of the model is greater than a preset threshold, the final cargo space demand prediction model is output, and the current cargo space demand prediction result is obtained through the cargo space demand prediction model.

[0015] Furthermore, the ant colony search algorithm is used to classify the cargo spaces in the cargo yard based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the cargo spaces, and a cargo space allocation model is established to obtain the cargo space allocation result. The specific method is as follows:

[0016] Based on the current cargo space demand forecast results, the method of using the ant colony search algorithm to calculate the probability of each path selection is as follows:

[0017]

[0018] Among them, i and j represent the warehouse where the raw materials of flue-cured tobacco are located and the next destination respectively, k represents the choice of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the movement of ants in guiding the search of ant colonies; the heuristic function factor β reflects the relative importance of heuristic information in guiding the search of ant colonies;

[0019] According to the optimized collection distance and the collection distance before optimization, the reduction ratio of the collection distance is calculated as follows:

[0020]

[0021] Among them, S ij Indicates the distance from one cargo location to another; A nmrepresents the raw material demand of each cargo stack, X represents the number of cross-regions per unit of each raw material before optimization, the number of regions after optimization is Y, and P represents the layout planning method of SLP-GA;

[0022] Build a cargo space allocation model to allocate corresponding raw materials to each cargo space in the cargo yard.

[0023] Furthermore, the specific method of establishing a cargo space path selection model based on the cargo space demand prediction result and the cargo space allocation result to achieve the optimal path selection for vehicle entry and exit is:

[0024] According to the number of collection points, the collection points are classified through DBSCAN cluster analysis to generate the initial path;

[0025] The initial path is deconstructed by using destruction, repair and insertion operators, and a better neighborhood is selected through an adaptive algorithm. After multiple iterations, the optimal path is obtained.

[0026] Furthermore, when the prediction accuracy of the model is ≥85%, the final cargo space demand prediction model is output.

[0027] Furthermore, the allocation of corresponding raw materials to each cargo space in the cargo yard includes:

[0028] Determine the raw material placement area in the cargo yard based on the raw material origin;

[0029] In different areas, corresponding storage locations are allocated according to the different varieties and parts of raw materials from corresponding origins.

[0030] Furthermore, the method specifically comprises:

[0031] Use DBSCAN algorithm to cluster cargo locations;

[0032] The initial path generation is based on the grouping after the cargo location is clustered, the initial T value and the number of cycles in the TA criterion are set, and the operator score and weight are reset;

[0033] A set of destruction and repair operators are selected using the roulette method to generate a new path S*;

[0034] The Metropolis acceptance criterion is adopted, that is, the new path S* is first compared with the current path S. If the new path S* is better than the current path S, the current path S is updated and further compared with the optimal path Sbest. If it is better than the optimal path Sbest, the optimal path Sbest is updated, otherwise it remains unchanged. When the new path S* is greater than the current path S, but the difference is less than the initial T value, the path is also accepted to avoid falling into the local optimum, and the T value is gradually reduced at a certain rate.

[0035] Adjust the operator score according to the path update situation and update the corresponding weight;

[0036] Continue to use the roulette method to select a set of destruction and repair operators, repeat the above steps until the number of cycles is reached, and obtain the final optimal path Sbest.

[0037] One or more embodiments of this specification provide a tobacco vehicle entry and exit guidance system for a flue-cured tobacco yard, including:

[0038] The cargo space demand prediction module is used to collect the historical data of the first-cured tobacco in and out of the warehouse, train and optimize the cargo space demand prediction model based on the historical data of the first-cured tobacco in and out of the warehouse, and obtain the cargo space demand prediction result;

[0039] Cargo space allocation module: It is used to classify cargo spaces in the cargo yard based on the location and destination of the raw materials of primary flue-cured tobacco and the distance between cargo spaces, establish a cargo space allocation model, and obtain cargo space allocation results by using an ant colony search algorithm;

[0040] Path selection module: used to establish a cargo space path selection model based on the cargo space demand prediction results and cargo space allocation results, so as to achieve the optimal path selection for vehicle entry and exit links.

[0041] One or more embodiments of the present specification provide an electronic device, including:

[0042] processor; and,

[0043] A memory arranged to store computer executable instructions, which, when executed, enable the processor to implement the steps of the above-mentioned method for guiding the entry and exit of tobacco vehicles in a primary-cured tobacco yard.

[0044] One or more embodiments of the present specification provide a storage medium for storing computer-executable instructions, which, when executed, implement the steps of the above-mentioned method for guiding the entry and exit of tobacco vehicles in a primary-cured tobacco yard.

[0045] By adopting the embodiment of the present invention, the process of entering and leaving the warehouse of the first-cured tobacco trucks is effectively guided, the freight yard resources can be effectively utilized, and the raw material response speed can be improved.

[0046] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate one or more embodiments of this specification or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0048] Figure 1 A flow chart of a method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard provided in one or more embodiments of this specification;

[0049] Figure 2 A schematic diagram of the implementation process of a method for guiding the entry and exit of tobacco vehicles in a first-cured tobacco yard provided in one or more embodiments of this specification;

[0050] Figure 3 A schematic diagram of the composition of a tobacco vehicle entry and exit guidance system for a flue-cured tobacco yard provided in one or more embodiments of this specification;

[0051] Figure 4 A schematic diagram of the structure of an electronic device provided for one or more embodiments of this specification. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the following will be combined with the drawings in one or more embodiments of this specification to clearly and completely describe the technical solutions in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this document.

[0053] Method Embodiment

[0054] According to an embodiment of the present invention, a method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard is provided. Figure 1 A flowchart of a method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard provided in one or more embodiments of this specification, Figure 2 A schematic diagram of the implementation process of a method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard provided in one or more embodiments of this specification, such as Figure 1 , Figure 2 As shown, the method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard according to an embodiment of the present invention specifically includes:

[0055] S1. Collect the historical data of freshly cured tobacco in and out of the warehouse, train and optimize the cargo space demand prediction model based on the historical data of freshly cured tobacco in and out of the warehouse, and obtain the cargo space demand prediction result.

[0056] The historical data of the first-cured tobacco in and out of the freight yard over the years are collected, and the collected historical data of the first-cured tobacco in and out of the freight yard are divided into a training set and a test set; in this embodiment, the historical data from 2018 to 2021 are collected as the training set, and the data from 2022 to 2023 are collected as the test set.

[0057] The recursive neural network RNN ​​model is trained through the training set to capture the time dependency in the training set sequence data, and the cargo space demand is predicted based on the time dependency to obtain the initial model for cargo space demand prediction; based on the self-learning method, the RNN algorithm is used to autonomously learn the patterns and rules in the demand data, and accurate predictions are generated based on this information to achieve accurate response to demand prediction. The mathematical expression is as follows:

[0058] (h_t=\sigma(W_{xh}x_t+W_{hh}h_{t-1}+b_h));

[0059] (y_t=W_{hy}h_t+b_y);

[0060] Among them, (h_t) represents the output of the hidden layer, (x_t) represents the input data, (y_t) represents the prediction result, (W_{xh}), (W_{hh}) and (W_{hy}) are weight matrices, (b_h) and (b_y) are bias terms, and (\sigma) is the activation function.

[0061] The prediction accuracy of the initial model for cargo space demand prediction is tested through a test set, and the model parameters are optimized according to the test results. When the prediction accuracy of the model is greater than a preset threshold, the final cargo space demand prediction model is output, and the current cargo space demand prediction result is obtained through the cargo space demand prediction model. In this embodiment, when the prediction accuracy of the model is ≥85%, the final cargo space demand prediction model is output, and cargo space allocation modeling analysis is carried out.

[0062] S2. Using the ant colony search algorithm, the cargo locations in the cargo yard are classified based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the cargo locations, and a cargo location allocation model is established to obtain the cargo location allocation result.

[0063] Based on the current cargo space demand forecast results, the method of using the ant colony search algorithm to calculate the probability of each path selection is as follows:

[0064]

[0065] Among them, i and j represent the warehouse where the raw materials of flue-cured tobacco are located and the next destination respectively, k represents the choice of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the movement of ants in guiding the search of ant colonies; the heuristic function factor β reflects the relative importance of heuristic information in guiding the search of ant colonies;

[0066] The collection distance mainly refers to the actual driving distance of each tobacco truck in the cargo yard. When the tobacco truck cannot place all the tobacco leaves in the same cargo position, it needs to unload at multiple cargo positions. This distance is the reduction ratio of the total path distance of each tobacco truck for unloading. The reduction ratio of the collection distance is calculated based on the optimized collection distance and the collection distance before optimization, as shown below:

[0067]

[0068] Among them, S ij Indicates the distance from one cargo location to another; A nm represents the raw material demand of each cargo stack, X represents the number of cross-regions per unit of each raw material before optimization, the number of regions after optimization is Y, and P represents the layout planning method of SLP-GA;

[0069] Construct a cargo space allocation model to allocate corresponding raw materials to each cargo space in the cargo yard. Specifically: determine the raw material placement area in the cargo yard according to the origin of the raw materials; allocate corresponding cargo spaces in different areas according to the different varieties and parts of the raw materials from the corresponding origins.

[0070] S3. A cargo space path selection model is established based on the cargo space demand prediction results and cargo space allocation results to achieve optimal path selection for vehicle entry and exit.

[0071] The number of collection points represents the concentrated cargo positions where the first-cured tobacco needs to be unloaded. The principle of unloading the first-cured tobacco in the open-air cargo yard is to unload directly when the cargo position is empty. If there are raw materials in the cargo position, the unloaded raw materials must be at the same level as the cargo position raw materials, and mixing is not allowed. For example: a tobacco truck is carrying C3F raw materials. There are currently no empty C3F cargo positions. There are 5-6, or even 7-8 cargo positions that meet the C3F requirements for unloading. The specific unloading location is mainly based on the actual situation of different cargo positions in the cargo yard and the situation of incoming tobacco trucks. In principle, the requirement of full stacking is limited. Another principle is to facilitate unloading. Therefore, it is necessary to classify the collection points according to the number of collection points through DBSCAN clustering analysis so that the tobacco trucks know where to unload. The specific method is as follows:

[0072] According to the number of collection points, DBSCAN cluster analysis is used to classify the collection points and generate a high-quality initial path. The initial path is then deconstructed using destruction, repair, and insertion operators, and a better neighborhood is selected through an adaptive algorithm. After multiple iterations, the optimal path is obtained. When the first flue-cured tobacco is in and out of the warehouse, the corresponding algorithm implementation steps are as follows:

[0073] Use DBSCAN algorithm to cluster cargo locations;

[0074] The initial path generation is based on the grouping after the cargo location is clustered, the initial T value and the number of cycles in the TA criterion are set, and the operator score and weight are reset;

[0075] A set of destruction and repair operators are selected using the roulette method to generate a new path S*;

[0076] The Metropolis acceptance criterion is adopted, that is, the new path S* is first compared with the current path S. If the new path S* is better than the current path S, the current path S is updated and further compared with the optimal path Sbest. If it is better than the optimal path Sbest, the optimal path Sbest is updated, otherwise it remains unchanged. When the new path S* is greater than the current path S, but the difference is less than the initial T value, the path is also accepted to avoid falling into the local optimum, and the T value is gradually reduced at a certain rate.

[0077] Adjust the operator score according to the path update situation and update the corresponding weight;

[0078] Continue to use the roulette method to select a set of destruction and repair operators, repeat the above steps until the number of cycles is reached, and obtain the final optimal path Sbest.

[0079] The beneficial effects of the present invention are as follows:

[0080] The present invention guides the tobacco carts to which specific cargo position they should be placed and how much raw primary flue-cured tobacco materials should be placed in each cargo position during the warehousing stage, and guides the tobacco carts to which cargo position they should leave and how much raw primary flue-cured tobacco materials should be left during the leaving cargo position, thereby meeting the "first in, first out" principle, effectively guiding the entry and exit processes of the raw primary flue-cured tobacco carts, making effective use of cargo yard resources, and improving the raw material response speed.

[0081] System Example

[0082] According to an embodiment of the present invention, a tobacco vehicle entry and exit guidance system for a flue-cured tobacco yard is provided. Figure 3 A schematic diagram of the composition of a tobacco vehicle entry and exit guidance system for a flue-cured tobacco yard provided in one or more embodiments of this specification, such as Figure 3 As shown, the tobacco vehicle entry and exit guidance system for the first-cured tobacco goods yard according to the embodiment of the present invention specifically includes:

[0083] The cargo space demand prediction module 30 is used to collect the historical data of the first-cured tobacco in and out of the cargo yard, train and optimize the cargo space demand prediction model based on the historical data of the first-cured tobacco in and out of the cargo yard, and obtain the cargo space demand prediction result;

[0084] The cargo space allocation module 32 is used to classify the cargo spaces in the cargo yard based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the cargo spaces, establish a cargo space allocation model, and obtain a cargo space allocation result by using an ant colony search algorithm;

[0085] The path selection module 34 is used to establish a cargo space path selection model based on the cargo space demand prediction result and the cargo space allocation result, so as to realize the optimal path selection for the vehicle in and out of the warehouse.

[0086] The embodiment of the present invention is a system embodiment corresponding to the above-mentioned method embodiment. The specific operations of each module can be understood by referring to the description of the method embodiment, which will not be repeated here.

[0087] Device Example 1

[0088] An embodiment of the present invention provides an electronic device, such as Figure 4 As shown, it includes: a memory 40, a processor 42, and a computer program stored in the memory 40 and executable on the processor 42. When the computer program is executed by the processor 42, the following method steps are implemented:

[0089] S1. Collect the historical data of the first flue-cured tobacco in and out of the warehouse, train and optimize the cargo space demand prediction model based on the historical data of the first flue-cured tobacco in and out of the warehouse, and obtain the cargo space demand prediction result;

[0090] S2. Using an ant colony search algorithm, based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the cargo locations, the cargo locations in the cargo yard are classified, a cargo location allocation model is established, and the cargo location allocation result is obtained;

[0091] S3. A cargo space path selection model is established based on the cargo space demand prediction results and cargo space allocation results to achieve optimal path selection for vehicle entry and exit.

[0092] Device Example 2

[0093] An embodiment of the present invention provides a computer-readable storage medium, on which a program for implementing information transmission is stored. When the program is executed by the processor 42, the following method steps are implemented:

[0094] S1. Collect the historical data of the first flue-cured tobacco in and out of the warehouse, train and optimize the cargo space demand prediction model based on the historical data of the first flue-cured tobacco in and out of the warehouse, and obtain the cargo space demand prediction result;

[0095] S2. Using an ant colony search algorithm, based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the cargo locations, the cargo locations in the cargo yard are classified, a cargo location allocation model is established, and the cargo location allocation result is obtained;

[0096] S3. A cargo space path selection model is established based on the cargo space demand prediction results and cargo space allocation results to achieve optimal path selection for vehicle entry and exit.

[0097] The computer-readable storage medium in this embodiment includes, but is not limited to, ROM, RAM, magnetic disk or optical disk, etc.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for guiding the entry and exit of tobacco vehicles in a flue-cured tobacco yard, characterized in that: include: Collecting historical data of freshly-cured tobacco in and out of the warehouse, training and optimizing a cargo space demand prediction model based on the historical data of freshly-cured tobacco in and out of the warehouse, and obtaining a cargo space demand prediction result; Ant colony search algorithm is used to classify the cargo spaces in the cargo yard based on the location and destination of the raw materials of flue-cured tobacco and the distance between the cargo spaces, and a cargo space allocation model is established to obtain the cargo space allocation result. A cargo space path selection model is established based on the cargo space demand prediction results and cargo space allocation results to achieve optimal path selection for vehicle entry and exit links.

2. The method according to claim 1, characterized in that The specific method of collecting the historical data of the first-cured tobacco in and out of the warehouse, training and optimizing the cargo space demand prediction model based on the historical data of the first-cured tobacco in and out of the warehouse, and obtaining the cargo space demand prediction result is as follows: The collected historical data of freshly flue-cured tobacco in and out of the freight yard are divided into a training set and a test set; The recursive neural network (RNN) model is trained by using the training set to capture the time dependency in the training set sequence data, and the cargo space demand is predicted based on the time dependency to obtain an initial model for cargo space demand prediction; The prediction accuracy of the initial model for cargo space demand prediction is tested through a test set, and the model parameters are optimized according to the test results. When the prediction accuracy of the model is greater than a preset threshold, the final cargo space demand prediction model is output, and the current cargo space demand prediction result is obtained through the cargo space demand prediction model.

3. The method according to claim 1, characterized in that The ant colony search algorithm is used to classify the cargo spaces in the cargo yard based on the location and destination of the primary flue-cured tobacco raw materials and the distance between the cargo spaces, and a cargo space allocation model is established to obtain the cargo space allocation result. The specific method is as follows: Based on the current cargo space demand forecast results, the method of using the ant colony search algorithm to calculate the probability of each path selection is as follows: Among them, i and j represent the warehouse where the raw materials of flue-cured tobacco are located and the next destination respectively, k represents the choice of different paths, the pheromone factor α reflects the relative importance of the amount of pheromone accumulated on the path during the movement of ants in guiding the search of ant colonies; the heuristic function factor β reflects the relative importance of heuristic information in guiding the search of ant colonies; According to the optimized collection distance and the collection distance before optimization, the reduction ratio of the collection distance is calculated as follows: Among them, S ij Indicates the distance from one cargo location to another; A nm It represents the raw material demand of each cargo stack, X represents the number of cross-regions per unit of each raw material before optimization, the number of regions after optimization is Y, and P represents the layout planning method of SLP-GA; Build a cargo space allocation model to allocate corresponding raw materials to each cargo space in the cargo yard.

4. The method according to claim 1, characterized in that: The specific method of establishing a cargo space path selection model based on the cargo space demand prediction result and the cargo space allocation result to achieve the optimal path selection for the vehicle entry and exit link is: According to the number of collection points, the collection points are classified through DBSCAN cluster analysis to generate the initial path; The initial path is deconstructed by using destruction, repair and insertion operators, and a better neighborhood is selected through an adaptive algorithm. After multiple iterations, the optimal path is obtained.

5. The method according to claim 2, characterized in that: When the prediction accuracy of the model is ≥85%, the final cargo space demand prediction model is output.

6. The method according to claim 3, characterized in that The allocation of corresponding raw materials to each cargo space in the cargo yard includes: Determine the raw material placement area in the cargo yard based on the raw material origin; In different areas, corresponding storage locations are allocated according to the different varieties and parts of raw materials from corresponding origins.

7. The method according to claim 4, characterized in that The method specifically comprises: Use DBSCAN algorithm to cluster cargo locations; The initial path generation is based on the grouping after the cargo location is clustered, the initial T value and the number of cycles in the TA criterion are set, and the operator score and weight are reset; A set of destruction and repair operators are selected using the roulette method to generate a new path S*; The Metropolis acceptance criterion is adopted, that is, the new path S* is first compared with the current path S. If the new path S* is better than the current path S, the current path S is updated and further compared with the optimal path Sbest. If it is better than the optimal path Sbest, the optimal path Sbest is updated, otherwise it remains unchanged. When the new path S* is greater than the current path S, but the difference is less than the initial T value, the path is also accepted to avoid falling into the local optimum, and the T value is gradually reduced at a certain rate. Adjust the operator score according to the path update situation and update the corresponding weight; Continue to use the roulette method to select a set of destruction and repair operators, repeat the above steps until the number of cycles is reached, and obtain the final optimal path Sbest.

8. A tobacco vehicle entry and exit guidance system for a flue-cured tobacco yard, characterized in that: include: The cargo space demand prediction module is used to collect the historical data of the first-cured tobacco in and out of the warehouse, train and optimize the cargo space demand prediction model based on the historical data of the first-cured tobacco in and out of the warehouse, and obtain the cargo space demand prediction result; Cargo space allocation module: It is used to classify cargo spaces in the cargo yard based on the location and destination of the raw materials of primary flue-cured tobacco and the distance between cargo spaces, establish a cargo space allocation model, and obtain cargo space allocation results by using an ant colony search algorithm; Path selection module: used to establish a cargo space path selection model based on the cargo space demand prediction results and cargo space allocation results, so as to achieve the optimal path selection for vehicle entry and exit links.

9. An electronic device, characterized in that: include: processor; as well as, A memory arranged to store computer executable instructions, wherein when the computer executable instructions are executed, the processor implements the steps of the method for guiding the entry and exit of tobacco vehicles in a first-cured tobacco yard as claimed in any one of claims 1 to 7.

10. A storage medium, characterized in that: Used to store computer executable instructions, which, when executed, implement the steps of the method for guiding the entry and exit of tobacco vehicles in a first-cured tobacco yard as claimed in any one of claims 1 to 7.

Images